CN115871709A

CN115871709A - Method, device, equipment, medium and vehicle for planning station-entering track of automatic driving vehicle

Info

Publication number: CN115871709A
Application number: CN202211228487.XA
Authority: CN
Inventors: 王珺旸
Original assignee: Uisee Technologies Beijing Co Ltd
Current assignee: Uisee Technologies Beijing Co Ltd
Priority date: 2022-10-09
Filing date: 2022-10-09
Publication date: 2023-03-31

Abstract

The embodiment of the disclosure provides a method, a device, equipment, a medium and a vehicle for planning an arrival track of an automatic driving vehicle. The trajectory planning method comprises the following steps: generating a plurality of to-be-selected navigation tracks including a first navigation track; under the condition that the first navigation track does not accord with the station entering constraint condition, selecting an optimal navigation track from a plurality of navigation tracks to be selected; under the condition that the optimal navigation track is not the first navigation track, acquiring the transverse distance between track points on the optimal navigation track and a target path; determining the position of a waiting point according to the transverse distance and the position of the target stop point; and issuing the optimal navigation track and the position of the waiting point to realize the running track control of the automatic driving vehicle. Based on the waiting point determined by the method of the embodiment of the disclosure, the computing device can control the automatic driving vehicle to avoid driving to the waiting point without stopping when the automatic driving vehicle drives along the first navigation track, and then the probability of successful station entry caused by subsequent unavailable lane change is reduced.

Description

Method, device, equipment, medium and vehicle for planning station-entering track of automatic driving vehicle

Technical Field

The disclosure relates to the technical field of automatic driving, in particular to a method, a device, equipment, a medium and a vehicle for planning an arrival track of an automatic driving vehicle.

Background

In professional yard applications such as container terminals, warehouse cargo stations, etc., the scenes faced by the autonomous logistics vehicles include open road scenes and inbound scenes. In the station entering scene, in order to ensure that goods are normally loaded and unloaded at the station, the logistics vehicles need to ensure that the logistics vehicles can successfully enter the station as much as possible, namely, the logistics vehicles run to a target stop point beside the station in parallel with the station as much as possible, so that the transverse distance between the vehicle body and the station can meet the set precision.

In order to simultaneously be compatible with automatic driving control of logistics vehicles in an open road scene and an entry scene, a current vehicle entry trajectory planning method reuses a planning method based on a navigation mode adopted in the open road scene, and sets a non-obstacle-avoidance path (namely, a non-obstacle-avoidance area often mentioned in the prior art) on a target path where the target stop point is located (the path can be understood as a path which is parallel to a platform and the transverse distance from the platform meets set accuracy). When the station entering track planning method is implemented, even if an obstacle is detected in a path which does not avoid the obstacle, the vehicle can be driven to a target path, the logistics vehicle is not enabled to transversely avoid the obstacle, and the vehicle is controlled to brake and control in the longitudinal direction to realize obstacle avoidance.

The station-entering track planning method based on the navigation mode is reused without considering the problems caused by switching of a planner, so that the direction of dangerous obstacles behind the self-vehicle is considered to be reused in the navigation mode. However, the approach track planning method in the multiplexing navigation mode does not consider that other logistics vehicles and the like occupy target paths under the complex approach scene, so that the approach track is locked only when the self vehicle is too close to the target station, but the logistics vehicles cannot successfully approach the station according to the approach track due to the constraint of vehicle steering characteristics.

Disclosure of Invention

In order to solve the technical problem, the embodiment of the present disclosure provides a method, an apparatus, a device, a medium, and a vehicle for planning an arrival trajectory of an automatically driven vehicle.

In a first aspect, an embodiment of the present disclosure provides a method for planning an arrival trajectory of an autonomous vehicle, including:

generating a plurality of candidate voyage tracks under the station entering planning state of the automatic driving vehicle, wherein the plurality of candidate voyage tracks comprise a first voyage track, the extension of the first voyage track is at least partially overlapped with a target path, and the target path is a path which is parallel to a target station platform and passes through a target stop point;

judging whether the first navigation track meets the station-entering constraint condition or not;

if not, selecting an optimal navigation track from the multiple navigation tracks to be selected;

under the condition that the optimal crossing track is not the first crossing track, acquiring the transverse distance between each track point on the optimal crossing track and the target path;

determining the position of a waiting point according to the transverse distance and the position of a target stop point, wherein the waiting point is a track point which is positioned on the optimal navigation track, ensures that the automatic driving vehicle realizes vehicle alignment after changing the track from the optimal navigation track to the target path and has the minimum longitudinal distance with the target stop point;

and issuing the optimal navigation track and the position of the waiting point to realize the running track control of the automatic driving vehicle.

In a second aspect, an embodiment of the present disclosure provides another method for planning an arrival trajectory of an autonomous vehicle, including:

determining a target path and at least one other path in a plurality of paths to be selected when the automatic driving vehicle is in a station entering planning state, wherein the target path is a path which is parallel to a target platform and passes through a target stop point;

acquiring the transverse distance from each other path to the target path;

determining the positions of waiting points on the other paths according to the transverse distance and the positions of the target stop points, wherein the waiting points are position points which ensure that the automatic driving vehicle realizes vehicle alignment after changing the path from the other paths to the target path and have the minimum longitudinal distance with the target stop points;

and issuing the positions of the waiting points corresponding to the other paths.

In a third aspect, an embodiment of the present disclosure provides an arrival trajectory planning apparatus for an autonomous vehicle, including:

the automatic selection vehicle comprises a candidate track generation unit, a selection unit and a selection unit, wherein the candidate track generation unit is used for generating a plurality of candidate navigation tracks under the station entering planning state of the automatic driving vehicle, the candidate navigation tracks comprise a first navigation track, the extension section of the first navigation track is at least partially overlapped with a target path, and the target path is a path which is parallel to a target platform and passes through a target stop point;

the station-entering constraint judging unit is used for judging whether the first ferry track meets station-entering constraint conditions or not;

the optimal track selection unit is used for selecting an optimal navigation track from the multiple navigation tracks to be selected under the condition that the arrival constraint judgment unit judges that the first navigation track does not accord with the arrival constraint condition;

a transverse distance obtaining unit, configured to determine a transverse distance between each track point on the optimal ferry track and the target path when the optimal ferry track is not the first ferry track;

the waiting point determining unit is used for determining the position of a waiting point according to the transverse distance and the position of a target stop point, wherein the waiting point is a track point which is positioned on the optimal navigation track, ensures that the automatic driving vehicle realizes vehicle alignment after changing the channel from the optimal navigation track to the target path and has the minimum longitudinal distance with the target stop point;

in a fourth aspect, an embodiment of the present disclosure provides an apparatus for planning an arrival trajectory of an autonomous vehicle, including:

the route selection unit is used for determining a target route and at least one other route in a plurality of routes to be selected when the automatic driving vehicle is in a station entering planning state, wherein the target route is a route which is parallel to a target platform and passes through a target stop point;

a transverse distance obtaining unit, configured to determine a transverse distance from each of the other paths to the target path;

the waiting point determining unit is used for determining the positions of the waiting points on the other paths according to the transverse distance and the position of the target stop point, wherein the waiting points are position points which ensure that the automatic driving vehicle realizes vehicle straightening after changing the path from the other paths to the target path and have the minimum longitudinal distance with the target stop point;

and the data issuing unit is used for issuing the positions of the waiting points corresponding to the other paths.

In a fifth aspect, embodiments of the present disclosure provide a computing device comprising a processor and a memory, the memory for storing a computer program; the computer program, when loaded by the processor, causes the processor to perform the method of planning an inbound trajectory for an autonomous vehicle as described above.

In a sixth aspect, the disclosed embodiments provide a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the processor is enabled to implement the method for planning the inbound trajectory of an autonomous vehicle as described above.

In a seventh aspect, an embodiment of the present disclosure provides an autonomous vehicle, including a vehicle-mounted control chip, where the vehicle-mounted control chip is configured to execute the method for planning an arrival trajectory of the autonomous vehicle.

Compared with the prior art, the technical scheme provided by the embodiment of the disclosure has the following advantages:

according to the scheme provided by the embodiment of the disclosure, under the condition that the first navigation track is determined not to conform to the station entering constraint condition and the station entering track cannot be locked, the optimal navigation track is selected from a plurality of navigation tracks, the transverse distance between the optimal navigation track and the target path is determined, and the position of the equal leaning point on the optimal navigation track is determined according to the transverse distance. Based on the waiting point determined by the method of the embodiment of the disclosure, the computing device can control the automatic driving vehicle to avoid driving to the waiting point and not stopping when the automatic driving vehicle drives along the first navigation track, and then the probability of successful station entry caused by subsequent unavailable lane change is reduced.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.

In order to more clearly illustrate the embodiments of the present disclosure or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It will be apparent to those skilled in the art that other drawings can be obtained from these drawings without inventive exercise, wherein:

FIG. 1 is a schematic diagram of a typical station layout;

FIG. 2 is a flow chart of a method for planning an arrival trajectory of an autonomous vehicle according to some embodiments of the present disclosure;

FIG. 3 is a schematic illustration of determining a candidate voyage trajectory in accordance with some embodiments of the present disclosure;

FIG. 4 is a simplified station architecture diagram;

FIG. 5 is a flowchart of another method for planning an inbound trajectory for an autonomous vehicle according to an embodiment of the present disclosure;

FIG. 6 is a schematic diagram of an arrival trajectory planning apparatus for an autonomous vehicle provided by an embodiment of the present disclosure;

fig. 7 is a schematic structural diagram of an arrival trajectory planning apparatus for an autonomous vehicle according to another embodiment of the present disclosure;

fig. 8 is a schematic structural diagram of a computing device provided by some embodiments of the present disclosure.

Detailed Description

Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but rather are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.

The term "include" and variations thereof as used herein are open-ended, i.e., "including but not limited to". The term "based on" is "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the following description. It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.

It is noted that references to "a" or "an" in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will appreciate that references to "one or more" are intended to be exemplary and not limiting unless the context clearly indicates otherwise.

The embodiment of the disclosure provides a method for planning an arrival track of an automatic driving vehicle, which is used for multiplexing a track planning strategy of a navigation mode, and realizing the planning of the arrival track and ensuring the successful arrival of the vehicle to the maximum extent.

It should be noted that the method for planning the arrival trajectory of the autonomous vehicle provided by the embodiment of the disclosure is executed by a computing device. The computing device may be a vehicle machine system of an autonomous vehicle. In some scenario applications, the computing device may also be a remote server, an edge server, or a station server communicatively connected to the autonomous vehicle.

In order to facilitate understanding of a specific implementation process of the automatic vehicle arrival planning method provided by the embodiment of the disclosure, some technical terms mentioned hereinafter are first explained or distance is first determined.

The navigation mode state is a mode state in which the autonomous vehicle travels on a normal road for trajectory planning. The aforementioned normal road is a road other than a station area and a road within a certain distance centered on a station. In the prior art, a navigation track is generated by a track planning method used in a navigation mode state, and is used for guiding a track of an automatically-driven vehicle running on a normal road.

Since the inbound trajectory planning method disclosed in this embodiment determines the inbound trajectory by using the trajectory planning method used in the transit mode state, the to-be-selected flight trajectory mentioned hereinafter refers to not only the planned trajectory in the transit mode state but also the to-be-selected trajectory for realizing the inbound trajectory planning.

The arrival planning state refers to a state in which the arrival trajectory planning is started and the arrival trajectory is locked after the automatic driving vehicle travels to a specific distance from the field station. In particular embodiments, the computing device may initiate the inbound planning state after the autonomous vehicle has traveled a specified distance from the yard, where the specified distance may be set based on the size of the yard, the speed at which the autonomous vehicle is traveling, the type of structure of the autonomous vehicle, and the like.

The yard is a logistics storage site or a product production site for loading and unloading goods. The station mentioned in the embodiments of the present disclosure includes at least a platform and a station road. The station road is a road which is located beside and parallel to the platform and used for parking and passing vehicles.

Fig. 1 is a schematic diagram of a typical station layout. As shown in fig. 1, the station includes two stations, and each of the two stations has a corresponding station road. The target station is a station for loading and unloading goods which is selected in advance from the two stations. The path is an actual travelable road parallel to the extension of the platform (i.e. parallel to the extension of the station road). In some embodiments, a route may be directly understood as a station road. In other embodiments, the route may not be directly understood as a station road, but should be understood as a travelable road that is further determined on the basis of the station road. For example, as shown in FIG. 1, in some embodiments, multiple paths are provided on each yard road. It should be noted that the relative path parallel to the extension direction of the platform should be understood to be expanded, and in practical applications, the path parallel to the platform may be understood as the included angle between the path and the platform is smaller than a predetermined angle threshold, for example, the angle threshold may be 3 °.

The target stopping point is a predetermined vehicle stopping point located on the target path. When the autonomous vehicle is properly parked at the target parking point, a loading and unloading bridge can be erected between the target platform and the side of the cargo bed of the autonomous vehicle, thereby facilitating loading and unloading of cargo.

The target path is the path through the target waypoint in all paths. As in FIG. 1, the path through the target stop A is the target path.

It should be noted that in practical applications, a station may include only a platform and a station road without any sign, and there is no aforementioned path, target stop point, and station road marking as shown in fig. 1, which are only virtual points or lines according to the layout of the station, the type of autonomous vehicle, and the stopping position of the autonomous vehicle, and the computing device may determine the position coordinates of the aforementioned path, target stop point, and station road marking according to a spatial localization technique.

Body straightening refers to the straightening of the entire body of the autonomous vehicle, the longitudinal direction being substantially parallel to the direction of extension of the target platform. In particular, body straightening should be such that the longitudinal direction of the cargo bed or bucket of the autonomous vehicle is substantially parallel to the direction of extension of the target platform.

Other technical terms refer to specific scenarios and specific implementation steps, which are explained in the following in the course of explaining specific embodiments of the present solution.

Fig. 2 is a flowchart of an approach path planning method for an autonomous vehicle according to some embodiments of the present disclosure. As shown in fig. 2, the method for planning the arrival trajectory of the autonomous vehicle provided by the embodiment of the disclosure includes S110-S160.

It should be noted that, in the case that the inbound track is not locked, the method for planning the inbound track of the autonomous vehicle provided by the embodiment of the present disclosure is executed cyclically according to a set period, and a plurality of steps in the following method should be executed cyclically. It should also be noted, however, that certain steps in the following methods may not be performed cyclically, but rather in certain situations, and in which certain steps are performed in what specific situations as will be described in more detail below.

S110: and generating a plurality of to-be-selected navigation tracks under the station entering planning state of the automatic driving vehicle, wherein the plurality of to-be-selected navigation tracks comprise a first navigation track.

In an embodiment of the disclosure, after the autonomous vehicle travels a certain distance from the distance field station, the computing device switches the autonomous driving path planning state to the inbound planning state. As explained above, the trajectory planning method for the computing device to reuse the navigation mode state in the station entering planning state plans the navigation trajectories, and selects the navigation trajectories meeting the conditions from the planned navigation trajectories as the station entering trajectories.

In the embodiment of the disclosure, in the station entry planning state, the computing device generates a plurality of ferry tracks to be selected. The candidate flight path is a flight path to be selected, which may be selected as an inbound path.

Fig. 3 is a schematic diagram of a planned candidate voyage trajectory according to some embodiments. For a more visual representation, more paths are provided in FIG. 3 than in FIG. 1, but the center lane lines are removed. As shown in fig. 3, each candidate voyage trajectory includes a lane change section and an extension section.

The lane changing section is a curve track section for controlling the automatic driving vehicle to change the lane from the current driving path to another path and realizing the steering shaft of the automatic driving vehicle to be aligned. The traveling direction of the steering wheel on the steering shaft of the aforementioned yaw finger is parallel to the extending direction of the target path. As shown in fig. 3, for each path, the computing device generates a corresponding lane change segment.

The extension section is a track section which starts from the lane changing terminal of the lane changing section and extends towards the station direction and is parallel to the extending direction of the platform. The extension is a planned trajectory segment that coincides with the corresponding path, as defined by the extension.

It should be noted that the computing device plans the lane change segment and the extension segment of the to-be-selected navigation track, and actually plans the track points on the lane change segment and the extension segment according to a preset interval (for example, 20 cm), and connects the track points smoothly to identify the lane change segment and the extension segment.

Specifically, how to generate a plurality of to-be-selected ferry tracks in the station-entering planning state is specifically analyzed in the following text.

It should also be noted that, among the multiple candidate voyage tracks, a lane change segment in one candidate voyage track may be a straight line segment. And under the condition that a lane changing section in a to-be-selected navigation track is a straight line, the to-be-selected navigation track is a navigation track superposed with the current path of the automatic driving vehicle.

As stated above, the plurality of candidate voyage trajectories include the first voyage trajectory. The first navigation track is a navigation track to be selected, the extension section of which is at least partially overlapped with the target path.

S120: judging whether the first navigation track meets the station-entering constraint condition or not; if not, go to S130.

The inbound constraint condition is a judgment condition which is preset and used for screening the first navigation track and determining whether the first navigation track can be locked as the inbound track. How to set the specific inbound constraint condition and how to judge whether the first ferry track meets the inbound constraint condition, and then, specific analysis is performed in the following text.

S130: and selecting an optimal navigation track from the plurality of navigation tracks to be selected.

If the computing device determines that the first ferry track does not meet the arrival constraint condition, it is determined that the first ferry track cannot be locked as the arrival track, and therefore the computing device still selects an optimal ferry track from the plurality of candidate ferry tracks according to the ferry planning mode for subsequent vehicle control.

In specific implementation, the computing device evaluates a plurality of candidate voyage tracks according to the track screening rule in the voyage mode, and selects the candidate voyage track with the optimal evaluation as the optimal voyage track. The track filtering rules may include a track performability rule, a track safety rule, and a track smoothness rule. How to determine the optimal navigation track according to the track screening rule is not a concern of the embodiment, and therefore, the description is not specifically made, and reference may be made to related technical documents.

It should be noted that the computing device selects an optimal navigation track from the plurality of screening tracks according to the track screening rule in the navigation mode, and the first navigation track may be determined as the optimal navigation track.

S140: and under the condition that the optimal navigation track is not the first navigation track, acquiring the transverse distance between each track point on the optimal navigation track and the target path.

The lateral distance is the distance perpendicular to the direction of extension of the target station. The transverse distance between each track point on the optimal navigation track and the target path is the vertical distance between the track point and the target path. In the case of a computing device using the Frenet coordinate system, the lateral distance is the distance in the direction l in the Frenet coordinate system.

In the embodiment of the disclosure, the transverse distance between each track point on the optimal navigation track and the target path is obtained by making a perpendicular line from the track point on the optimal navigation track to the target path, and using the length of the corresponding perpendicular line as the transverse distance.

As stated previously, because the first navigation trajectory is a navigation trajectory in which the extension at least partially coincides with the target path, and the lateral distance from the extension of the first navigation trajectory to the target path is 0, there is no need to seek (to maintain the smoothness and the analysis comprehensiveness of the discussion, the need to specifically why no seek is explained later), the computing device first determines whether the optimal navigation trajectory is the first navigation trajectory.

If the optimal voyage trajectory is not the first voyage trajectory, the computing device may determine a lateral distance of the extended segment of the optimal voyage trajectory from the target path, and the lateral distance must be greater than 0.

S150: and determining the position of the waiting point according to the transverse distance and the position of the target stop point.

The waiting point is a position point which is positioned on the optimal track, ensures that the automatic driving vehicle realizes vehicle alignment after changing the track from the optimal track to the target path, and has the minimum longitudinal distance with the target stop point. As shown in fig. 4, the point where it is located is a waiting point.

The position of the waiting point is determined based on the aforementioned lateral distance, the body structure of the autonomous vehicle and the maximum steering ability of the steerable wheels of the autonomous vehicle, and the position of the target stopping point. Specifically, the computing device can perform route simulation according to the transverse distance, the longitudinal distance from each track point to the target stop point, the automatically-driven vehicle body structure and the maximum steering capacity, determine whether each track point can reach the target stop point under the constraint of the vehicle body structure and the constraint of the maximum steering capacity, and determine that the track point is a waiting point if the target stop point cannot be reached from a certain track point.

S160: and issuing the optimal navigation track and the position of the waiting point to realize the running track control of the automatic driving vehicle.

Because the station entering track is not locked in the current period, but the vehicle still needs to be controlled at the time, the optimal ferry track is issued to realize the running track control of the automatic driving vehicle. It should be noted that the meanings of the locations at which the optimal ferry trajectory and the waiting point are issued differ for different types of computing devices.

And under the condition that the computing equipment is a vehicle-mounted machine system of the automatic driving vehicle, issuing the optimal ferry track is to forward the optimal ferry track to a vehicle control module of the vehicle-mounted machine system, so that the vehicle control module can control the vehicle according to the optimal ferry track, the road obstacle characteristics, a power train, a steering system and a braking system of the vehicle. The position of the issued waiting point is that the position of the waiting point is issued to the vehicle module, so that the vehicle control module determines whether to brake and wait before the waiting point according to the position of the waiting point and the actual position of the vehicle, and then the vehicle can be parked at or before the waiting point.

And under the condition that the computing equipment is a remote server, an edge server or a station server, issuing the position information of the optimal navigation track and the waiting point, wherein the information of the optimal navigation track and the waiting point is sent to a vehicle-mounted machine system of the automatic driving vehicle, so that the vehicle-mounted machine system realizes vehicle control according to the optimal navigation track.

It should be noted that the aforementioned S160 is performed independently of S140-S150. In practical applications, S160 may be performed in parallel with S140-S150.

By adopting the planning method for the station-entering track of the automatic driving vehicle provided by the embodiment of the disclosure, under the condition that the first navigation track is determined to be not in accordance with the station-entering constraint condition and the station-entering track cannot be locked by the computing equipment, the optimal navigation track is selected from a plurality of navigation tracks, the transverse distance between a track point on the optimal navigation track and a target path is determined, and the position of an equal leaning point on the optimal navigation track is determined according to the transverse distance.

It is assumed that the optimal voyage trajectory determined by the computing device is not the first voyage trajectory and the autonomous vehicle then continues to travel along the optimal voyage trajectory. In order to ensure that the autonomous vehicle can successfully switch from the optimal ferry trajectory to the target path and successfully approach the station, i.e., successfully achieve the alignment of the car and stop at the target stop point, it is necessary to ensure that the autonomous vehicle switches with maximum steering capability before the extreme switch-over point in the optimal ferry trajectory. If the autonomous vehicle is driven before the limit lane change timing point, the autonomous vehicle can only be controlled to stop at the limit lane change timing point.

The waiting point determined in the previous embodiment is the limit lane change opportunity point on the optimal navigation path. Based on the waiting point determined by the method of the embodiment of the disclosure, the computing device can control the automatic driving vehicle to avoid driving to the waiting point and not stopping when the automatic driving vehicle drives on the first navigation track, and further avoid the problem that the automatic driving vehicle cannot successfully enter the station after changing the lane.

In some embodiments of the present disclosure, the computing device generates multiple candidate flight paths, and also generates pointing directions of track points on the candidate flight paths. The pointing direction may be a head pointing direction of the autonomous vehicle. In this case, S150 may specifically be: and determining the position of the waiting point according to the transverse distance, the corresponding pointing direction and the position of the target stop point. That is, in some embodiments, the computing device may perform route simulation based on the aforementioned lateral distance, longitudinal distance and pointing direction from each track point to the target stop point, and the autonomously driven vehicle body structure and maximum steering capability, determine whether the target stop point can be reached from each track point under the constraints of the vehicle body structure and the maximum steering capability, and determine that a track point is a waiting point if the target stop point cannot be reached from a certain track point.

Of course, in practical applications, since the angle between the pointing direction and the longitudinal direction is not large, and in practical applications, the problem of tolerance is also considered, the pointing direction of each track point may not be considered when determining the waiting point.

As mentioned above, in the method for planning an arrival trajectory of an autonomous vehicle provided by the embodiment of the present disclosure, some steps may be periodically executed in a loop, and some steps may not be periodically executed in a loop. With respect to the aforementioned S110-S160, wherein S110-S130 must be performed periodically in a loop. The positions of the issued waiting points in S140 to S150 and S160 may not be periodically executed, but executed when a specific condition is satisfied.

As previously mentioned, the purpose of determining the waiting point in the disclosed embodiments is to avoid the vehicle traveling along the optimal navigation trajectory beyond the waiting point without achieving a successful stop. To implement the function of the waiting point, after issuing the optimal navigation track and the position of the waiting point in S160, the computing device may further execute S170.

S170: and under the condition that the automatic driving vehicle is predicted to run to the waiting point and not locked with the entering track, the automatic driving vehicle is controlled to stop at the waiting point or before the waiting point.

In the disclosed embodiments, the computing device, after determining the autonomous driving trajectory, also predicts a state of the autonomous vehicle traveling along the optimal navigation trajectory and a state of the locked-in trajectory in the future. If the computing device predicts that the autonomous vehicle still does not lock into the inbound trajectory when traveling to the waiting point, it is determined that the autonomous vehicle is to be parked at or before the waiting point to ensure that subsequent trips to the target route from a parked state and successful inbound can be made.

It should be noted that it may be possible in practical cases to execute the aforementioned S170 only in a case where the autonomous vehicle does not lock the approach trajectory and travels forward along the approach trajectory. Whereas if the autonomous vehicle has locked the inbound track and is traveling along the inbound track, the aforementioned S170 need not be executed.

In an extreme case, the method for planning the inbound trajectory for multiple cycles by the computing device selects only one of the other navigation trajectories except the first navigation trajectory as the optimal navigation trajectory once, determines the position of the waiting point corresponding to the optimal navigation trajectory, and does not perform the aforementioned S170 when the first navigation trajectory is taken as the optimal navigation trajectory or the first navigation trajectory is locked as the inbound trajectory in other cycles.

As before, a plurality of candidate voyage trajectories are generated in S110. In some embodiments of the present disclosure, the computing device may employ S111-S113 as follows.

S111: determining a planning starting point and determining a lane changing longitudinal distance.

The planning starting point is a starting point for realizing the automatic driving vehicle path planning. The method of determining the starting point of the plan is different for different situations. For example, when the autonomous vehicle is in a stopped state, a reference point of the coordinate system of the autonomous vehicle itself (in the case where the autonomous vehicle is a conventional two-axis vehicle such as a van, the reference point is a rear axle center point) may be used as a planning start point. For another example, in order to avoid control jitter and other problems during the running of the vehicle when the autonomous vehicle is in a running state, a stable point located in front of the vehicle may be determined from the planned route in the previous cycle, and the undetermined point may be used as a planned starting point.

The lane change longitudinal distance is a travel distance in the longitudinal direction of the lane when the autonomous vehicle performs a lane change. In the embodiment of the disclosure, the determination method of the lane change longitudinal distance is analyzed later.

S112: and determining a plurality of lane changing end points according to the position of the planning starting point and the lane changing longitudinal distance, wherein the plurality of lane changing end points comprise position points positioned on the target path.

After determining the position of the planning start point and after determining the lane change longitudinal distance, a plurality of lane change end points may be determined. In a specific embodiment, the method for determining a plurality of lane change end points according to the position of the planning start point and the lane change longitudinal distance is as follows: firstly, a positioning point is determined according to the longitudinal coordinate of a planning starting point and the lane changing longitudinal distance. And then, making a vertical line perpendicular to each path by using the positioning point, and taking the intersection point of the vertical line and each path as a lane changing terminal point of the corresponding path.

It should be noted that the aforementioned plurality of lane change end points include an intersection point with the target path, that is, a position point located on the target path.

S113: and determining a plurality of lane changing sections according to the position of the planned starting point, the positions of the lane changing end points, the kinematic state of the automatic driving vehicle at the planned starting point and the kinematic state of the automatic driving vehicle in the alignment of the lane changing end points.

After determining the position of the planning start point and the positions of the respective lane change end points, a plurality of lane change segments may then be determined.

In some embodiments of the present disclosure, the lane-change segment may be modeled using a cubic polynomial. For convenience, the following explanation of the process of determining the lane change segment based on the cubic polynomial and the aforementioned parameters is in the Frenet coordinate system.

In the Frenet coordinate system, a cubic polynomial of the lane change segment can be established as

Wherein a is ₀ ～a ₃ Is a coefficient polynomial coefficient, s represents the longitudinal coordinate of a point on the lane change segment, and l represents the lateral coordinate of a point on the lane change segment.

The longitudinal coordinate s (start) and the transverse coordinate l (start) of the lane change starting point can be determined according to the position of the planned starting point, and the longitudinal speed of the lane change starting point can be determined according to the kinematic state of the automatic driving vehicle at the planned starting point

And a transverse speed pick>

The longitudinal coordinate s (end) and the transverse coordinate l (end) of the lane changing end point can be determined according to the position of the lane changing end point. Based on the timing of the swing of the autonomous vehicle at the end of the lane change, the longitudinal speed at the start and end of the lane change may be determined>

The coefficient of the cubic polynomial can be obtained by solving the cubic polynomial by adopting the data, and the formula expression mode of the lane change segment is also determined.

S114: and determining a plurality of extension sections according to the positions of the lane changing end points, wherein the extension sections are track sections parallel to the target platform.

And determining a plurality of extension sections according to the positions of the plurality of lane changing end points, wherein the lane changing end points are used as starting points, line sections parallel to the path are made, and the line sections are used as extension sections of the corresponding navigation tracks. The end point of the extension segment may be determined from the longitudinal coordinates of the target stop point. Specifically, a normal perpendicular to the path may be made at the target stop point, and the normal and the line segment of each path may be used as the end point of the extension segment.

S115: and connecting the plurality of lane changing sections with the corresponding extension sections to determine a plurality of navigation tracks to be selected.

And after the lane changing section and the corresponding extension section are determined, the lane changing section and the corresponding extension section are connected, and then a plurality of to-be-selected navigation tracks can be determined.

In some embodiments of the present disclosure, the method of determining a lane change longitudinal distance in S111 may include S111A-S111G.

S111A: the recommended longitudinal distance is determined based on the road environment and the kinematic state of the autonomous vehicle.

The recommended longitudinal distance is determined according to the road environment and the motion state of the autonomous vehicle, and is determined according to the speed limit regulation of the road, the obstacle condition of the road and the like. The disclosed example can adopt the existing method for determining the recommended longitudinal distance according to the road environment and the kinematic state of the vehicle, and the content is not described herein, and the details can be found in the related technical documents.

S111B: and determining the position of the limit lane changing righting point.

The limit lane changing and righting point is a position point which is closest to the target stop point and is used for realizing the righting of the vehicle body when the automatic driving vehicle changes the lane to the target path. Fig. 4 is a simplified station diagram. As shown in FIG. 4, the positions of extreme trajectory rectification points are represented by diamond-solid.

The method of determining the limit lane change true point is not the same for different types of vehicles.

In case the autonomous vehicle is a non-towed vehicle, i.e. a conventional van or the like. Under the condition, the correct station entering can be realized by righting the vehicle body at the target stop point, so that the position of the target stop point can be directly used as the position of the limit lane changing righting point, namely the target stop point is directly used as the limit lane changing righting point.

In the case where the autonomous vehicle is a trailer vehicle, i.e., the autonomous vehicle includes a tractor and a trailer, the limit lane change swinger is a position at which the tractor changes lanes to the target path and the vehicle body is swiped. Correspondingly, the trailer has not been set. The successful arrival and stop of the automatic driving vehicle comprise the correction and the arrival and stop of the trailer, so the position of the limit deviation point needs to be determined according to the structure of the automatic driving vehicle, the steering capacity of the tractor, the connection mode of the front vehicle and the trailer and the position of the target stop point.

In some embodiments of the present disclosure, where the autonomous vehicle is a trailing vehicle, determining the location of the extreme lane change justify point includes S111B1-S111B2.

S111B1: and determining a correcting running distance according to the structure of the trailer and the typical steering included angle between the trailer and the tractor, wherein the correcting running distance is the longitudinal distance which is run by the tractor when the trailer is enabled to change the track to the target path and is completely corrected.

The following determines the swing-driving distance by means of formula derivation.

The model of the towed vehicle is determined as follows:

where phi = theta _f -θ _t In the above formula, x _t For longitudinal displacement of the trailer, y _t For transverse displacement of the trailer, theta _t For trailer yaw angle, theta _f For trailer tractors yaw angle, L _t Is the wheelbase of the trailer, L _f Is the wheelbase of the tractor. .

Given the initial steering angle of the trailer, the tractor travels a certain distance forward when the tractor is steered (i.e., at an angle of 0 degrees to the direction of travel of the path) to steer the trailer. Bringing the model into known conditions can be obtained

In view of

Make->

It is possible to obtain models>

From the foregoing model, at a known θ _t Initial value of (a) _t0 When theta is greater than theta _t The convergence law of (4) is only related to the wheelbase of the trailer and the linearized equation can be used>

Wherein theta is _tx Is a point of reference for model linearization. Considering theta _t Most of the time, the angle is basically changed between small turning angles based on theta _tx Linearization of =0 ° makes it possible to achieve =>

At an initial value of the angle theta between trailer and tractor _t0 In the case of (2), an initial solution of the aforementioned model can be obtained

Suppose when the included angle is less than theta _thres When the trailer is considered to be in a correct position, the trailer can be obtained

For the case that the tractor comprises n trailers, assuming that the straightening process of each trailer is straightened on the premise that the trailer is straightened, the straightening travel distance can be obtained as

However, the estimation of the swing-out travel distance of the aforementioned multi-section trailers is relatively conservative, because the actual swing-out process of the multi-section trailers is not a one-by-one swing-out of one trailer, but rather the trailer of the next section has already started to gradually swing out when the preceding trailer starts to swing out. However, the conservative estimated corrected travel distance can better guarantee the successful arrival of the trailer vehicle, so the corrected travel distance model can be adopted in practical application.

In addition, in practical application, the included angle between the trailer and the tractor and between adjacent trailers is generally not more than 30 degrees. The trailer is generally considered to be ajar when the included angle is less than 3 °. Assuming worst condition theta in actual use _t0 =30 °, set termination condition θ _thres Is less than or equal to 3 degrees. Substituting into the above formula

The distance of the tractor running along the target path, namely the swing running distance, can be calculated from the initial turning angle of the trailer to 30 degrees in the process of the trailer swing.

S111B2: and determining the position of the limit lane changing righting point according to the righting running distance and the position of the target stop point.

After the swing driving distance is determined, the swing driving distance is moved in the reverse direction along the target path by taking the position of the target stop point as a reference, and the position of the limit lane changing swing point can be determined.

S111C: and determining the available longitudinal distance according to the position of the planning starting point and the position of the limit correcting point.

After determining the position of the extreme runout point, the available longitudinal distance can then be determined from the position of the extreme runout point and the position of the starting point of the plan. Specifically, the computing device determines the available longitudinal distance according to the longitudinal coordinate of the extreme swing point and the longitudinal coordinate of the planning start point.

S111D: a smaller longitudinal distance of the recommended longitudinal distance and the available longitudinal distance is determined.

After the recommended longitudinal distance and the available longitudinal distance are determined, a comparison of the two may determine a smaller longitudinal distance.

S111E: judging whether the smaller longitudinal distance is larger than a threshold longitudinal distance; if yes, go to S111F.

S111F: the smaller longitudinal distance is taken as the lane change longitudinal distance.

The threshold longitudinal distance is the longitudinal distance required by the automatic driving vehicle to change the current path to the target path by adopting the maximum steering capacity, and the threshold longitudinal distance is the safety distance for ensuring that the vehicle safely steers and does not roll or roll over and other accidents occur.

If the smaller longitudinal distance is greater than the threshold longitudinal distance, it is determined that a safety accident cannot be caused by changing lanes with the smaller longitudinal distance, and therefore the smaller longitudinal distance can be used as the lane changing longitudinal distance.

In some embodiments of the present disclosure, if the smaller longitudinal distance is less than the threshold longitudinal distance, the lane change longitudinal distance is no longer determined in order to ensure a safe lane change for the autonomous vehicle. Under the second condition, the automatic driving vehicle can not successfully enter the station, the automatic driving vehicle can be directly controlled to stop, and the lane is directly changed to the target path based on the maximum steering capacity of the automatic driving vehicle, so that the position of the target stop point of the vehicle body after entering the station is close to the maximum extent possible, and the included angle between the vehicle body after entering the station and the target path is minimum.

In S120, it is necessary to determine whether the first voyage trajectory meets the inbound restriction. In some embodiments of the present disclosure, the computing device determining whether the first ferry track meets the inbound constraint may include S121-S126.

S121: judging whether an obstacle exists on the first navigation track; if yes, go to step S122.

S122: and judging that the first navigation track does not accord with the station entering constraint condition.

The obstacle is an obstacle that prevents the autonomous vehicle from changing lanes to the target route on the first voyage trajectory. In practical applications, the obstacle may be the closest obstacle to the autonomous vehicle in the first ferry track due to obstruction by the obstacle, and the like. And if the first navigation track is judged to have the obstacle, judging that the first navigation track does not accord with the station-entering constraint condition, and then, stopping the station.

S123: judging whether the automatic driving vehicle runs along the first navigation track to meet safety constraints or not; if not, go to S124.

S124: and judging that the first navigation track does not accord with the station entering constraint condition.

The safety constraint condition is a constraint condition for judging whether the autonomous vehicle collides with another autonomous vehicle or another vehicle when the autonomous vehicle travels along the first transit track. In the disclosed embodiments, the computing device may perform collision detection based on the maximum possible speed, the minimum possible speed, and the travel speed of the vehicle in the target path when the autonomous vehicle travels along the first transit trajectory, to determine whether the autonomous vehicle will collide with other vehicles. And if the automatic driving vehicle is judged to collide with other vehicles, judging that the first navigation track does not accord with the station entering constraint condition.

S125: judging whether the included angle between the first navigation track extension section and the target path is smaller than an included angle threshold value or not; if not, go to step S126.

S126: and judging that the first navigation track does not accord with the station entering constraint condition.

And judging whether the included angle between the first navigation track extension section and the target path is smaller than an included angle threshold value, namely, determining the included angle between the direction of the first navigation track extension section and the extension direction of the target path, and judging whether the included angle is smaller than the included angle threshold value. And if the included angle is smaller than the included angle threshold value, determining that the first navigation track does not accord with the station entering constraint condition.

The above statements may conflict with the above statements and some explanations are provided. As before, the extension of the first navigation trajectory should coincide with the target path, but this is only a theoretical case. In practical applications, the first navigation track may not be exactly parallel to the target path due to calculation errors and other considerations, and a certain included angle is formed between the first navigation track and the target path. In this case, it is necessary to determine whether an included angle between the first navigation track extension section and the target path is smaller than an included angle threshold.

In practical applications, the foregoing S121, S123 and S125 may be executed in parallel or in series, and the embodiment of the present disclosure is not limited thereto. Also, in the case where S121, S123, and S125 are executed serially, the serial execution may not be divided successively. Further, in some embodiments of the present disclosure, the computing device may also determine whether the first transit trajectory meets the inbound restriction condition using only one or two of the determination conditions of S121, S123, and S125.

In some embodiments of the present disclosure, the computing device may further perform S210 before performing the aforementioned S121.

S210: and setting a non-obstacle avoidance path on the target path.

The non-obstacle avoidance path is a path having a special attribute set on the target path. The special attribute mentioned above means that even if there is an obstacle on the target route in this section of area, the section of route is considered to be free of the obstacle. It should be noted that the absence of obstacles for this path is considered only in terms of inbound trajectory planning. When the vehicle enters the station according to the station entering path determined by the station entering track planning, if the path has obstacles, the vehicle still stops and avoids the obstacles.

In some embodiments, setting the non-obstacle avoidance path on the target path may include S211-S212.

S211: and determining a non-obstacle-avoidance starting point according to the position of the limit lane changing righting point and the widening distance.

S212: and setting the path between the non-obstacle-avoiding starting point and the target stop point as a non-obstacle-avoiding path.

The non-obstacle-avoidance starting point is positioned on the target path and used for determining the position point of the non-obstacle-avoidance path range. Fig. 4 is a simplified station architecture diagram. As shown in fig. 4, the starting point of non-obstacle avoidance adopts 9632;.

In combination with the above description, the non-obstacle-avoidance path can be determined theoretically by taking the limit lane changing and aligning point as a starting point of the non-obstacle-avoidance path. However, the path from the limit lane changing and correcting point to the target stop point is set to be an ideal path without avoiding obstacles, and various practical situations or emergency situations are not left. In a specific implementation, there may occur: (1) As long as an obstacle exists on a target path before the limit lane changing and correcting point, the computing equipment can judge that the first navigation track does not accord with the station entering constraint condition; (2) Since the autonomous vehicle itself has a certain lateral width, although the limit lane change correction point is determined as the head correction point of the autonomous vehicle, the autonomous vehicle may collide with an obstacle before the limit lane change correction point.

In order to avoid the foregoing problem, in the embodiment of the present disclosure, the position of the non-obstacle avoidance starting point is determined according to the position of the limit lane changing righting point and the widening distance.

The widening distance is a distance set for appropriately lengthening the non-obstacle avoidance path. The relaxation distance may be a predetermined fixed distance or a distance determined in real time based on some other parameter.

In some embodiments, a numerical distance may be determined as the distance to be relaxed based on characteristics of the autonomous vehicle, predetermined curve characteristics of various possible first lane-change trajectories.

In some other embodiments, the computing device may determine the relaxation distance using S211A as follows.

S211A: and determining the widening distance according to the threshold longitudinal distance or the curve characteristic of the lane changing section of the first navigation track and a preset numerical distance.

As before, the threshold longitudinal distance is a safe distance to ensure that the vehicle turns safely, does not roll or roll over, and the like. That is, the threshold longitudinal distance is the projected distance in the longitudinal direction of the shortest first voyage trajectory that is likely to occur. And determining the relaxation distance by adopting the threshold longitudinal distance and a preset numerical distance, wherein the relaxation distance is obtained by adding the threshold longitudinal distance and the preset numerical distance. Since the threshold longitudinal distance is a fixed distance determined according to the characteristics of the structure of the autonomous vehicle and the like, in the case of determining a numerical distance, the relaxed distance can be determined. That is, the relaxed distance is a fixed distance determined according to the characteristics of the autonomous vehicle. It should be noted that the aforementioned preset numerical distance may be 0, and may also be set to a numerical value larger than 0, but it should not be set excessively large. In practical applications, the preset numerical distance may be set to 5m.

As before, the lane change segment of the first voyage trajectory is a curved segment, and the rear segment portion of the curved segment is close to the target path. If the autonomous vehicle changes lanes along the lane change segment of the first ferry track, the probability of the autonomous vehicle colliding with the target path obstacle is greater in the latter half of the curve segment. Therefore, the second half part of the first navigation track lane changing section can be determined according to the curve characteristic of the first navigation track lane changing section and the size characteristic of the automatic driving vehicle, and the relaxation distance can be obtained by summing the second half part and the preset numerical distance.

In some embodiments, in the case that the first navigation track lane change segment is a cubic polynomial or other curve segment that can be derived twice, the inflection point of the first navigation track lane change segment may be determined by performing the second derivation on the first navigation track lane change segment, so as to determine the second half of the curve segment using the inflection point.

In other embodiments, the vertical distance from the midpoint of the first transition track lane change segment to the target path may be obtained, and a curve segment formed by points of which the vertical distance is smaller than the set distance may be used as the second half of the first transition track lane change segment.

In some embodiments, the computing device may also add the longitudinal length of the first navigation route lane change segment and the remaining set numerical distance to determine the widening distance. As mentioned above, the longitudinal length of the first transition track lane change segment is the aforementioned smaller longitudinal distance.

As before, in some embodiments of the present disclosure, in the event that it is determined at S111E that the smaller longitudinal distance is greater than the threshold longitudinal distance, S111F is performed to treat the smaller longitudinal distance as the lane change longitudinal distance. And if the smaller longitudinal distance is smaller than the threshold longitudinal distance, directly changing the lane to the target path based on the maximum steering capacity of the automatic driving vehicle so as to enable the position of the target stop point of the vehicle body after entering the station to be close to the maximum extent and enable the included angle between the vehicle body after entering the station and the target path to be minimum.

In some embodiments of the present disclosure, in the event that S111E determines that the smaller longitudinal distance is less than the threshold longitudinal distance, the computing device may also perform S111G-S111H as follows.

S111F: and planning a second navigation track according to the threshold longitudinal distance.

S111H: and locking the second navigation track as the station entering track.

As before, if the smaller longitudinal distance is less than the threshold longitudinal distance, it is determined that the automated house is that the vehicle cannot successfully enter the station. At this time, it is still necessary to plan the arrival trajectory of the autonomous vehicle so as to arrive at the station and stop near the target stop point as much as possible, thereby facilitating the loading and unloading of the cargo.

To achieve the foregoing objective, in some embodiments of the present disclosure, the computing device plans the second voyage trajectory according to a threshold longitudinal distance if the smaller longitudinal distance is less than the threshold longitudinal distance. The second navigation track is a navigation track for changing the lane of the autonomous vehicle to the target path.

As before, in some embodiments of the present disclosure, the computing device selects and issues the optimal ferry trajectory in the event that it is determined that the first ferry trajectory does not meet the inbound constraints. There is no description of how to operate the first ferry track in compliance with the inbound constraints. What operation steps the computing device performs in the case that the first ferry trajectory meets the inbound constraint is analyzed as follows.

In some embodiments of the present disclosure, the computing device may perform S170 under a condition that it determines that the first voyage trajectory complies with the inbound constraint in performing S130.

S170: and locking the first ferry track as a station entering track, and issuing the station entering track.

That is, in some embodiments, the computing device may consider it possible to determine the inbound trajectory if the first voyage trajectory meets the constraints.

However, in practical applications, the false detection is caused by problems such as sensor drift and false detection, and in S130, it is determined that the first ferry trajectory meets the inbound constraint and meets the real situation according to the sensor detection data. In order to avoid false decisions due to sensor drift, false detection, i.e. false locking of the first ferry trajectory to the base station trajectory, the computing device may further perform S180-S190 in case it determines that the first ferry trajectory meets the inbound constraint in performing S130.

S180: the count value of the trajectory lock counter is incremented by one.

S190: and locking the first navigation track as the inbound track when the count value of the track locking counter reaches a count threshold value.

In some embodiments, the computing device sets a lock counter and sets the initial value of the counter to 0. The lock counter is a counter for determining whether to lock the inbound track. If it is determined that the first ferry track meets the inbound constraint, the computing device increments a count value of the lock counter by one and determines whether the count value of the lock counter reaches a count threshold. If the count value of the locking counter reaches the count threshold value, the first ferry track is determined to be verified for multiple times to meet the station entering constraint, the probability of false detection of the sensor is low, and therefore the first ferry track can be locked as the station entering track.

In practical applications, if the first voyage trajectory does not meet the inbound constraint, the computing device may execute S100.

S100: the count value of the trajectory lock counter is zeroed.

And resetting the technical value of the track locking technical device to zero, so that the locking counter counts again, and the judging step of locking the inbound track can be executed again.

In some embodiments of the present disclosure, the computing device performing S190 to lock the first ferry track as the inbound track may specifically include S191-S193.

S191: judging whether the first navigation track is superior to the historical track to be selected; if yes, go to S192; if not, execution proceeds to S193.

Specifically, the optimal trajectory determined in the candidate historical trajectory and still executable by the automatic driving vehicle may be locked as the inbound trajectory if the steps of counter count accumulation and count determination are not provided. And judging whether the first navigation track is superior to the historical track to be selected, and analyzing the first navigation track later.

And S192, locking the first ferry track as the station-entering track.

S193: and locking the history track to be selected as the inbound track.

If the first voyage trajectory is better than the candidate historical trajectory, it is determined that the autonomous vehicle can complete the arrival earlier when traveling along the first voyage trajectory, and thus the first voyage trajectory is locked as the arrival trajectory. And if the first ferry track is worse (i.e., not better) than the candidate history estimate, locking the candidate history track to the inbound track.

In some embodiments of the present disclosure, the determining of whether the first ferry track is better than the candidate history track in S191 may include S191A-S191C.

S191A: calculating a first longitudinal distance from a first navigation track lane change end point to a target stop point, and calculating a second longitudinal distance from a to-be-selected historical track lane change end point to the target stop point;

S191B: judging whether the first longitudinal distance is smaller than the second longitudinal distance; if yes, go to S191C.

S191C: and judging that the first navigation track is superior to the candidate historical track.

As before, the first ferry track diversion endpoint is a location point determined based on the lesser of the recommended longitudinal distance and the available longitudinal distance. The recommended longitudinal distance is a longitudinal distance determined according to the environmental state and the operational state of the vehicle, and the available longitudinal distance is a longitudinal distance determined according to the obstacle situation.

Based on the analysis, the position of the end point of the first route transition track lane change section determined in the current period may be before the end point of the to-be-selected historical route lane change, that is, the first longitudinal distance is greater than the second longitudinal distance. In this case, the large probability is that a new obstacle appears on the target path in the current cycle. If the first transit trajectory is locked as the arrival trajectory, the time it takes for the autonomous vehicle to arrive at the first transit trajectory may be longer than the time it takes to arrive at the candidate historical trajectory due to the influence of the new obstacle. Conversely, if the first longitudinal distance is less than the second longitudinal distance, the time it takes for the autonomous vehicle to enter the station according to the first navigation trajectory may be greater than the time it takes to enter the station according to the candidate historical trajectory.

In practical application, the time consumed for entering the station should be shortened as much as possible, so that the first ferry track is judged to be superior to the candidate historical track under the condition that the first longitudinal distance is smaller than the second longitudinal distance, and the first ferry track is locked as the station entering track. Otherwise, judging that the history track to be selected is superior to the first ferry track, and locking the history track to be selected as the station-entering track.

Fig. 5 is a flowchart of another method for planning an arrival trajectory of an autonomous vehicle according to an embodiment of the present disclosure. Referring to FIG. 5, another approach to planning an approach path for an autonomous vehicle includes S310-S340.

S310: and determining a target path and at least one other path in the plurality of paths to be selected when the automatic driving vehicle is in the station entering planning state, wherein the target path is a path which is parallel to the target platform and passes through the target stop point.

The plurality of candidate paths are paths for realizing that the autonomous vehicle stops at each of the stations in a vehicle body squaring manner. In the embodiment of the disclosure, the plurality of candidate routes are predetermined according to the number of stations of the station and the vehicle structure of the automatic driving vehicle.

The target stop point is a position point at which the vehicle stops on the target platform. The position of the target stop point is determined when the autonomous vehicle is in the on-coming plan state.

S320: and acquiring the transverse distance from each other path to the target path.

The lateral distance is the distance perpendicular to the direction of extension of the target station. In the case of a computing device using the Frenet coordinate system, the lateral distance is the distance in the direction l in the Frenet coordinate system.

In embodiments of the present disclosure, the computing device may determine the corresponding lateral distance according to the lateral coordinates of each of the other paths and the lateral coordinates of the target path.

S330: and determining the positions of the waiting points on each other path according to the transverse distance and the position of the target stop point.

The waiting point is a position point which is positioned on other paths, ensures that the automatic driving vehicle realizes vehicle alignment after the automatic driving vehicle reaches the target path from other paths and has the minimum longitudinal distance with the target stop point. The position of the waiting point is determined based on the aforementioned lateral distance, the body structure of the autonomous vehicle and the maximum steering ability of the steerable wheels of the autonomous vehicle, and the position of the target stopping point. In the embodiment of the present disclosure, the method for determining the position of the waiting point is the same as the method in the previous embodiment, and the description thereof is not repeated here, and specific reference may be made to the foregoing description. It should be noted, however, that each of the other paths corresponds to a respective waiting point.

S340: and issuing the positions of the waiting points corresponding to the other paths.

In the case that the computing device is a vehicle-mounted machine system of an autonomous vehicle, issuing the position of each waiting point is to forward the position of the waiting point to a vehicle control module of the vehicle-mounted machine system, so that the vehicle control module determines whether to brake for waiting before the waiting point according to the position of the waiting point and the actual position of the vehicle, and then can stop at or before the waiting point.

And under the condition that the computing equipment is a remote server, an edge server or a station server, the position of the waiting point is issued, and the information of the waiting point is sent to a vehicle-mounted machine system of the automatic driving vehicle, so that the vehicle-mounted machine system realizes vehicle control according to the position of the waiting point.

In order to ensure that the autonomous vehicle can successfully switch from the other route to the target route and successfully approach, i.e., successfully achieve the alignment of the cars and stop at the target stop point, it is necessary to ensure that the autonomous vehicle switches with maximum steering capability before the extreme switch opportunity point of the other route. If the autonomous vehicle is driven before the limit lane change timing point, the autonomous vehicle can only be controlled to stop at the limit lane change timing point. The waiting point determined in this embodiment is the limit lane change opportunity point on the other path. Based on the waiting point determined by the method of the embodiment of the disclosure, the computing device can control the automatic driving vehicle to drive on other paths, so that the situation that the vehicle does not stop when driving to the waiting point is avoided, and the problem that the vehicle cannot successfully enter the station after follow-up lane changing is avoided.

It should be noted that in the embodiments of the present disclosure, the aforementioned S310-S340 may be performed only once.

In addition to performing the aforementioned S310-S340, the method provided by the embodiment of the present disclosure further includes S350-S380.

S350: and generating a plurality of candidate navigation tracks, wherein the plurality of candidate navigation tracks comprise a first navigation track.

S360: judging whether the first navigation track meets the station-entering constraint condition or not; if not, go to S370.

S370: and selecting an optimal navigation track from the plurality of navigation tracks to be selected.

S380: and issuing the optimal navigation track to realize the running track control of the automatic driving vehicle.

The specific implementation method of steps S350-S380 may be the same as the implementation method in the corresponding steps in the foregoing embodiments, and will not be repeated here, and specific reference may be made to the foregoing description.

By adopting S350-S380, the computing equipment can determine a plurality of to-be-selected navigation tracks by a path planning method under a navigation mode, select an optimal navigation track from a plurality of navigation estimates under the condition that the first navigation track does not accord with the station-entering constraint condition, and control the automatic driving vehicle to run by adopting the optimal navigation track. It should be noted that the aforementioned S350-S380 are performed periodically.

In some embodiments of the present disclosure, the computing device may perform S390 in addition to performing S350-S380 as previously described.

S390: and under the condition that the automatic driving vehicle is predicted to travel to the corresponding waiting point along another path and is not locked into the station entering track, issuing an instruction for controlling the automatic driving vehicle to stop at the waiting point or before the waiting point.

The computing device, after determining the optimal navigation trajectory for autonomous driving, also predicts a state of travel of the autonomous vehicle along the optimal navigation trajectory and a state of locked-in trajectory in the future. If the computing device predicts that the autonomous vehicle still does not lock into the inbound trajectory when traveling to the waiting point, it is determined that the autonomous vehicle is to be parked at or before the waiting point to ensure that subsequent trips to the target route from a parked state and successful inbound can be made.

It should be noted that the foregoing S390 is executed only in a case where the autonomous vehicle travels forward along the extended section of the optimal navigation trajectory in the actual situation. If the autonomous vehicle does not travel forward along the extension of the optimal voyage trajectory determined in the foregoing, the foregoing S390 need not be executed.

In an extreme case, the method for planning the arrival trajectory of the computing device in multiple cycles selects only one of the other transit trajectories except the first transit trajectory as the optimal transit trajectory once, determines the position of the waiting point corresponding to the optimal transit trajectory, and does not perform the aforementioned S390 if the first transit trajectory is taken as the optimal transit trajectory or the first transit trajectory is locked as the arrival trajectory in other cycles.

In some embodiments of the present disclosure, the computing device may perform S410 as follows, in addition to performing S310-S340 described above.

S410: and determining the position of a limit lane changing and righting point, wherein the limit lane changing and righting point is a position point which is closest to a target stop point and realizes the righting of the vehicle body of the automatic driving vehicle from the lane changing to the target path.

In the embodiment of the present disclosure, the method for determining the position of the extreme lane change rectification point in S410 may be the same as the method in S111B, and will not be repeated here, and for details, refer to the foregoing description.

As in the foregoing embodiments, the position of the extreme lane change rectification point determined in the embodiments of the present disclosure may be used to determine an available longitudinal distance, and then may determine a lane change longitudinal distance according to the available longitudinal distance, so that, in step S350, it is possible to determine a lane change termination point on each path according to the lane change longitudinal distance, and determine each to-be-selected navigation track based on the lane change termination point.

In some embodiments of the present disclosure, the computing device may also perform S320-S330.

S420: and determining a non-obstacle-avoidance starting point on the target path according to the position of the limit lane changing righting point and the widening distance.

S430: and setting the path between the non-obstacle-avoiding starting point and the target stop point as a non-obstacle-avoiding path.

The implementation method of S420 is the same as that of S211-S212 in the foregoing, and is not repeated here, and for details, reference may be made to the foregoing description. In the embodiment of the present disclosure, the function of setting the non-obstacle avoidance path is the same as that in the foregoing embodiment, and the description thereof is not repeated here, and the details thereof can be referred to the foregoing description.

In addition, when S360 is executed, the embodiment of the present disclosure may determine whether the first ferry track meets the entry constraint condition by using the determining method in the foregoing embodiment, and lock the entry track by using the method in the foregoing embodiment when the first ferry track meets the entry constraint condition.

In addition to providing the method for planning the arrival trajectory of the automatic driving vehicle, the embodiment of the disclosure also provides a device for planning the arrival trajectory of the automatic driving vehicle.

Fig. 6 is a schematic diagram of an arrival trajectory planning device of an autonomous vehicle according to an embodiment of the present disclosure. As shown in fig. 6, in some embodiments, the apparatus 600 for planning an arrival trajectory of an autonomous vehicle includes a candidate trajectory generating unit 601, an arrival constraint determining unit 602, an optimal trajectory selecting unit 603, a lateral distance obtaining unit 604, a waiting point determining unit 605, and a data issuing unit 606.

The candidate trajectory generation unit 601 is configured to generate a plurality of candidate navigation trajectories when the autonomous vehicle is in the station entry planning state, where the plurality of candidate navigation trajectories include a first navigation trajectory, an extended segment of the first navigation trajectory at least partially coincides with a target path, and the target path is a path that is parallel to the target platform and passes through a target stop point.

The inbound constraint judging unit 602 is configured to judge whether the first ferry track meets the inbound constraint condition.

The optimal trajectory selecting unit 603 is configured to select an optimal navigation trajectory from the multiple navigation trajectories to be selected when the station entry constraint judging unit 602 judges that the first navigation trajectory does not meet the station entry constraint condition.

The transverse distance obtaining unit 604 is configured to obtain a transverse distance between a track point on the optimal navigation track and the target path when the optimal navigation track is not the first navigation track.

The waiting point determining unit 605 is configured to determine the position of a waiting point according to the transverse distance and the position of the target stop point, where the waiting point is a track point that is located on the optimal transit track, ensures that the autonomous vehicle realizes vehicle alignment after changing the lane from the optimal transit track to the target path, and has the smallest longitudinal distance from the target stop point.

The data issuing unit 606 is configured to issue an optimal cruise track and a position of a waiting point to realize a travel track control of the autonomous vehicle.

In some embodiments, the inbound trajectory planner 600 further comprises a pointing direction determination unit; the pointing direction determining unit is used for generating the pointing direction of track points on each to-be-selected navigation track; correspondingly, the waiting point determining unit determines the position of the waiting point according to the transverse distance, the corresponding pointing direction and the position of the target stop point.

In some embodiments, the apparatus further comprises a parking instruction issuing unit. And the parking instruction issuing unit is used for issuing an instruction for controlling the automatic driving vehicle to park before the waiting point or the waiting point under the condition that the entering track is not locked when the automatic driving vehicle is predicted to run to the waiting point.

In some embodiments, the candidate trajectory generating unit 601 includes a start point determining subunit, a lane change longitudinal distance determining subunit, a lane change end point determining subunit, an extension determining subunit, and a candidate trajectory generating subunit.

The starting point determining subunit is used for determining a planning starting point. The lane changing longitudinal distance determining subunit is used for determining the lane changing longitudinal distance. And the lane changing end point determining subunit is used for determining a plurality of lane changing end points according to the position of the planning start point and the lane changing longitudinal distance, wherein the plurality of lane changing end points comprise position points positioned on the target path. The lane change segment determining subunit is used for determining a plurality of lane change segments according to the position of the planned starting point, the positions of all the lane change end points, the kinematic state of the automatic driving vehicle at the planned starting point and the kinematic state of the automatic driving vehicle in the alignment of all the lane change end points. The extension section determining subunit is used for determining a plurality of extension sections according to the positions of the plurality of lane changing end points, wherein the extension sections are track sections parallel to the target platform; and the candidate track generating subunit is used for connecting the multiple lane change sections with the corresponding extension sections and determining multiple candidate navigation tracks.

In some embodiments, the lane change longitudinal distance determining subunit includes a recommended distance determining module, an extreme lane change putting point determining module, an available longitudinal distance determining module, a smaller distance determining module, and a lane change longitudinal distance determining module.

The recommended distance determination module is used for determining a recommended longitudinal distance according to the road environment and the kinematic state of the autonomous vehicle.

The limit lane changing and righting point determining module is used for determining the position of a limit lane changing and righting point, wherein the limit lane changing and righting point is a position point which is closest to a target stop point and is used for realizing the righting of a vehicle body when the automatic driving vehicle changes the lane to the target path.

The available longitudinal distance determining module is used for determining the available longitudinal distance according to the position of the planning starting point and the position of the correction point.

The smaller distance determination module is to determine a smaller longitudinal distance of the recommended longitudinal distance and the available longitudinal distance.

The lane change longitudinal distance determination module is used for taking the smaller longitudinal distance as the lane change longitudinal distance under the condition that the smaller longitudinal distance is larger than or equal to the threshold longitudinal distance, and the threshold longitudinal distance is the longitudinal distance required by the automatic driving vehicle to change the lane from the current path to the target path by adopting the maximum steering capacity.

In some embodiments, the autonomous vehicle is a non-towing vehicle; and the limit track changing and correcting point determining module takes the position of the target stop point as the position of the limit track changing and correcting point.

In some embodiments, the autonomous vehicle is a trailer vehicle comprising a tractor and a trailer, and the limit lane change settlement point is a position point where the tractor changes lanes to a target path to achieve the vehicle body settlement; the limit lane changing and righting point determining module determines a righting driving distance according to the structure of the trailer and a typical steering included angle between the trailer and the tractor, wherein the righting driving distance is a longitudinal distance which is driven by the tractor when the trailer is changed to a target path and is completely righted; and determining the position of the limit lane changing and correcting point according to the correcting running distance and the position of the target stop point.

In some embodiments, the inbound restriction determining unit 602 includes an obstacle determining subunit, a safety restriction determining subunit, and an included angle determining subunit. The obstacle judging subunit is used for judging whether an obstacle exists on the first navigation track; the safety constraint judging subunit is used for judging whether the automatic driving vehicle runs along the first ferry track to meet the safety constraint; and the included angle judging subunit is used for judging whether the included angle between the first navigation track extension section and the target path is smaller than an included angle threshold value.

In some embodiments, the apparatus further comprises a non-obstacle avoidance path determination unit. The non-obstacle-avoidance path determining unit is used for setting a non-obstacle-avoidance path on the target path. The obstacle judging subunit is used for judging whether the first navigation track has an obstacle in a track section outside the non-obstacle-avoiding path.

In some embodiments, the non-obstacle-avoidance path determining unit includes a non-obstacle-avoidance start point determining subunit and a non-obstacle-avoidance path determining subunit. The non-obstacle-avoidance starting point determining sub-unit is used for determining a non-obstacle-avoidance starting point according to the position of the limit lane changing alignment point and the widening distance, and the non-obstacle-avoidance starting point is located on the target path; the non-obstacle-avoidance path determining subunit is used for setting a path between the non-obstacle-avoidance starting point and the target stop point as a non-obstacle-avoidance path.

In some embodiments, the apparatus further comprises a relaxation distance determining unit. The widening distance determining unit is used for determining the widening distance according to the threshold longitudinal distance or the curve characteristic of the first navigation track lane changing section and a preset numerical distance.

In some embodiments, the autonomous vehicle arrival trajectory planning apparatus 600 further includes a second navigation trajectory planning unit and an arrival trajectory locking unit. The system comprises a second navigation track acquisition unit and a station entering track locking unit. The second navigation track planning unit is used for planning a second navigation track according to the threshold longitudinal distance under the condition that the lane changing longitudinal distance determining module determines that the smaller longitudinal distance is smaller than the threshold longitudinal distance, wherein the second navigation track is a navigation track for the automatic driving vehicle to change the lane to the target path; the station entering track locking unit is used for locking the second navigation track into the station entering track.

In some embodiments, the inbound trajectory planner 600 further comprises a counting unit. The counting unit is used for adding one to the counting value of the track locking counter under the condition that the first ferry track is judged to accord with the station entering constraint condition; the entry trajectory locking unit locks the first navigation trajectory into the entry trajectory when the count value of the trajectory lock counter reaches a count threshold value.

In some embodiments, the inbound track locking unit includes a track goodness comparison subunit and an inbound track selection subunit. The track quality comparison subunit is used for judging whether the first navigation track is superior to a historical track to be selected, wherein the historical track to be selected is a previously determined navigation track which accords with the station entering constraint condition and at least partially coincides with the target path; the station entering track selecting subunit is used for locking the first navigation track as the station entering track under the condition that the first navigation track is superior to the historical track to be selected.

In some embodiments, the trajectory goodness comparison subunit includes a distance calculation module, a distance comparison module, and a trajectory goodness determination module. The distance calculation module is used for calculating a first longitudinal distance from the first navigation track lane change end point to the target stop point and calculating a second longitudinal distance from the to-be-selected historical track lane change end point to the target stop point; the distance comparison module is used for judging whether the first longitudinal distance is smaller than the second longitudinal distance; the track quality determining module is used for judging that the first navigation track is superior to the candidate historical track under the condition that whether the first longitudinal distance is smaller than the second longitudinal distance.

In some embodiments, the counting unit returns the count value of the trajectory lock counter to zero in a case where it is determined that the first voyage trajectory does not meet the inbound constraint.

Fig. 7 is a schematic structural diagram of an arrival trajectory planning device of an autonomous vehicle according to another embodiment of the present disclosure. As shown in fig. 7, another apparatus 700 for planning an arrival trajectory of an autonomous vehicle includes a path selecting unit 701, a lateral distance obtaining unit 702, a waiting point determining unit 703, and a data issuing unit 704.

The path selection unit 701 is configured to determine a target path and at least one other path among the multiple candidate paths when the autonomous vehicle is in the inbound planning state, where the target path is a path that is parallel to the target platform and passes through the target stop point.

The transverse distance acquiring unit 702 is configured to acquire a transverse distance from each of the other paths to the target path.

The waiting point determining unit 703 is configured to determine positions of waiting points on each other path according to the transverse distance and the position of the target stop point, where the waiting point is a position point that ensures that the vehicle is aligned after the autonomous vehicle changes lanes from the other path to the target path and has the smallest longitudinal distance from the target stop point.

The data issuing unit 704 is configured to issue positions of waiting points corresponding to various other paths.

In some embodiments, the apparatus 700 further comprises a parking instruction issuing unit. The parking instruction issuing unit is used for issuing an instruction for controlling the automatic driving vehicle to park before the waiting point or the waiting point under the condition that the entering track is not locked when the automatic driving vehicle is predicted to travel to the corresponding waiting point along other paths.

In some embodiments, the apparatus 700 further comprises a limit lane change correction point determination unit. And the limit lane changing and righting point determining unit is used for determining the position of a limit lane changing and righting point, and the limit lane changing and righting point is a position point which is closest to a target stop point and is used for realizing the righting of the vehicle body of the automatic driving vehicle from the lane changing to the target path.

In some embodiments, the autonomous vehicle is a trailer vehicle comprising a tractor and a trailer, and the limit lane change righting point is a position point where the tractor changes lanes to a target path to achieve righting of the vehicle body; the limit lane-changing correcting point determining unit comprises a longitudinal driving distance determining subunit and a longitudinal driving distance determining subunit. The longitudinal driving distance determining subunit is used for determining a correcting driving distance according to the structure of the trailer and a typical steering included angle between the trailer and the tractor, wherein the correcting driving distance is the longitudinal distance which is driven by the tractor when the trailer is enabled to change the track to the target path and is completely corrected; and the longitudinal running distance determining subunit is used for determining the position of the limit lane changing correcting point according to the correcting running distance and the position of the target stop point.

In some embodiments, the apparatus 700 further includes a non-obstacle-avoidance starting point determining unit and a non-obstacle-avoidance path determining unit. The non-obstacle-avoidance starting point determining unit is used for determining a non-obstacle-avoidance starting point on the target path according to the position of the limit lane changing righting point and the widening distance; the non-obstacle-avoidance path determining unit is used for setting a path between the non-obstacle-avoidance starting point and the target stop point as a non-obstacle-avoidance path.

In some embodiments, the autonomous vehicle inbound trajectory planning apparatus 700 further comprises a relaxed distance determination unit. And the relaxation distance determining unit is used for determining the relaxation distance according to a threshold longitudinal distance and a preset numerical distance, wherein the threshold longitudinal distance is the longitudinal distance required by the automatic driving vehicle to change the lane from the current path to the target path by adopting the maximum steering capacity.

The embodiment of the present disclosure further provides a computing device, which includes a processor and a memory, where the memory stores a computer program, and when the computer program is executed by the processor, the text input method of any of the above embodiments may be implemented.

1. An automatic driving vehicle arrival track planning method comprises the following steps:

judging whether the first ferry track meets an arrival constraint condition or not;

under the condition that the optimal crossing track is not the first crossing track, determining the transverse distance between each track point on the optimal crossing track and the target path;

2. The method according to 1, while generating a plurality of candidate voyage trajectories, further comprising:

generating the pointing direction of track points on each navigation track to be selected;

the determining the position of the waiting point according to the transverse distance and the position of the target stop point comprises the following steps:

and determining the position of the waiting point according to the transverse distance, the corresponding pointing direction and the position of the target stop point.

3. The method of claim 1, after issuing the optimal navigation trajectory and the location of the waiting point, the method further comprising:

and under the condition that the automatic driving vehicle is predicted to run to the waiting point and the entering track is not locked, issuing an instruction for controlling the automatic driving vehicle to stop at or before the waiting point.

4. The method according to 1, wherein the generating of the plurality of candidate ferry tracks comprises:

determining a planning starting point and determining a lane changing longitudinal distance;

determining a plurality of lane changing end points according to the position of the planning starting point and the lane changing longitudinal distance, wherein the plurality of lane changing end points comprise position points positioned on the target path;

determining a plurality of lane changing segments according to the position of the planning starting point, the positions of the lane changing end points, the kinematic state of the automatic driving vehicle at the planning starting point and the kinematic state of the automatic driving vehicle in the alignment of the lane changing end points;

determining a plurality of extension sections according to the positions of the lane changing end points, wherein the extension sections are track sections parallel to the target platform;

and connecting the plurality of lane changing sections with the corresponding extension sections, and determining the plurality of navigation tracks to be selected.

5. The method of 4, the determining a lane change longitudinal distance, comprising:

determining a recommended longitudinal distance based on a road environment and a kinematic state of the autonomous vehicle;

determining the position of a limit lane changing and righting point, wherein the limit lane changing and righting point is a position point which is closest to the target stop point and realizes the righting of the vehicle body when the automatic driving vehicle changes the lane to the target path;

determining an available longitudinal distance according to the position of the planning starting point and the position of the correcting point;

determining a smaller longitudinal distance of the recommended longitudinal distance and the available longitudinal distance;

and when the smaller longitudinal distance is larger than or equal to a threshold longitudinal distance, taking the smaller longitudinal distance as the lane changing longitudinal distance, wherein the threshold longitudinal distance is the longitudinal distance required by the automatic driving vehicle to change the lane from the current position to the target path by adopting the maximum steering capacity.

6. The method of 5, the autonomous vehicle being a non-towing vehicle;

the determining the position of the extreme lane-changing righting point comprises the following steps: and taking the position of the target stop point as the position of the limit lane changing and correcting point.

7. The method of 5, wherein the autonomous vehicle is a trailer vehicle comprising a tractor and a trailer, and the limit lane-changing putting point is a position point where the tractor changes lanes to the target path to realize the body putting;

the determining the position of the extreme lane-changing righting point comprises the following steps:

determining a correcting running distance according to the structure of the trailer and a typical steering included angle between the trailer and the tractor, wherein the correcting running distance is a longitudinal distance which is run by the tractor when the trailer is made to change the track to the target path and is completely corrected;

and determining the position of the limit lane changing and correcting point according to the correcting running distance and the position of the target stop point.

8. The method according to any one of claims 5-7, wherein the determining whether the first ferry track meets the inbound constraint includes: judging whether an obstacle exists on the first navigation track; and/or the presence of a gas in the gas,

judging whether the automatic driving vehicle runs along the first navigation track to meet safety constraints or not; and/or the presence of a gas in the gas,

and judging whether the included angle between the first navigation track extension section and the target path is smaller than the included angle threshold value.

9. The method of 8, prior to determining whether there is an obstacle on the first ferry track, further comprising: setting a non-obstacle avoidance path on the target path;

the judging whether the first navigation path has the obstacle or not comprises the following steps: and judging whether the track section of the first navigation track outside the non-obstacle-avoidance path has an obstacle or not.

10. The method according to 9, setting a non-obstacle avoidance path on the target path, including:

determining a non-obstacle-avoidance starting point according to the position of the limit lane-changing righting point and the widening distance, wherein the non-obstacle-avoidance starting point is positioned on the target path;

and setting the path between the non-obstacle-avoidance starting point and the target stop point as the non-obstacle-avoidance path.

11. The method according to claim 10, before determining a non-obstacle-avoidance starting point according to the position of the extreme lane-changing righting point and the widening distance, the method further includes:

and determining the relaxation distance according to the threshold longitudinal distance or the curve characteristic of the first navigation track lane change section and a preset numerical distance.

12. The method of any of claims 5-7, where the smaller longitudinal distance is less than the threshold longitudinal distance, the method further comprising:

planning a second navigation track according to the threshold longitudinal distance, wherein the second navigation track is a navigation track for enabling the automatic driving vehicle to change the channel to the target path;

and locking the second ferry track as a station entering track.

13. The method of any of claims 1-7, further comprising: under the condition that the first ferry track is judged to accord with the station-entering constraint condition, adding one to the count value of a track locking counter;

and locking the first navigation track as an inbound track when the count value of the track locking counter reaches a count threshold.

14. The method of 13, locking the first ferry track to an inbound track, comprising:

judging whether the first navigation track is superior to a history track to be selected, wherein the history track to be selected is a previously determined navigation track which accords with the station-entering constraint condition and has an extension section at least partially overlapped with a target path;

if yes, the first navigation track is locked as the station entering track.

15. The method according to 14, wherein the determining whether the first ferry track is better than the candidate historical track includes:

calculating a first longitudinal distance from the first navigation track lane change end point to the target stop point, and calculating a second longitudinal distance from the to-be-selected historical track lane change end point to the target stop point;

judging whether the first longitudinal distance is smaller than the second longitudinal distance;

and if so, judging that the first navigation track is superior to the historical track to be selected.

16. The method of claim 13, further comprising:

and under the condition that the first navigation track is judged not to accord with the station-entering constraint condition, the counting value of the track locking counter is reset to zero.

17. An approach path planning method for an automatic driving vehicle comprises the following steps:

determining the transverse distance from each of the other paths to the target path;

determining the positions of waiting points on the other paths according to the transverse distance and the position of the target stop point, wherein the waiting points are position points which realize vehicle alignment after changing lanes from the other paths to the target path and have the minimum longitudinal distance with the target stop point;

18. According to the method of 17, the positions of the waiting points corresponding to the other paths are issued, and the method further includes: and under the condition that the station entering track is not locked when the automatic driving vehicle is predicted to travel to the corresponding waiting point along the other path, issuing an instruction for controlling the automatic driving vehicle to stop at the waiting point or before the waiting point.

19. The method of any of claims 17-18, further comprising:

and determining the position of a limit lane changing and righting point, wherein the limit lane changing and righting point is a position point which is closest to the target stop point and realizes the righting of the vehicle body when the automatic driving vehicle changes the lane to the target path.

20. The method of 19, wherein the autonomous vehicle is a trailer vehicle comprising a tractor and a trailer, and the limit lane-change putting point is a position point where the tractor changes lanes to the target path to put the vehicle body in place;

the determining the position of the extreme lane-changing righting point comprises the following steps: determining a correcting running distance according to the structure of the trailer and a typical steering included angle between the trailer and the tractor, wherein the correcting running distance is a longitudinal distance which is run by the tractor when the trailer is made to change the track to the target path and is completely corrected;

21. The method of 20, further comprising: determining a non-obstacle-avoidance starting point on the target path according to the position of the limit lane-changing righting point and the widening distance;

22. The method according to 21, determining a non-obstacle-avoidance starting point located on the target path according to the position of the extreme lane-changing putting point and the widening distance, further comprising: and determining the relaxation distance according to a threshold longitudinal distance and a preset numerical distance, wherein the threshold longitudinal distance is a longitudinal distance required by the automatic driving vehicle to change the lane from the current path to the target path by adopting the maximum steering capacity.

23. An automatic driving vehicle approach path planning device comprises:

a transverse distance obtaining unit, configured to obtain a transverse distance between each track point on the optimal ferry track and the target path when the optimal ferry track is not the first ferry track;

and the data issuing unit is used for issuing the optimal navigation track and the position of the waiting point so as to realize the running track control of the automatic driving vehicle.

24. The apparatus of 23, the apparatus further comprising:

the pointing direction determining unit is used for generating the pointing direction of track points on each to-be-selected navigation track;

and the waiting point determining unit determines the position of the waiting point according to the transverse distance, the corresponding pointing direction and the position of the target stop point.

25. The apparatus of 23, the apparatus further comprising: and the parking instruction issuing unit is used for issuing an instruction for controlling the automatic driving vehicle to park at the waiting point or before the waiting point under the condition that the station entering track is not locked when the automatic driving vehicle is predicted to run to the waiting point.

26. According to the apparatus of 23, the candidate trajectory generating unit includes: a starting point determining subunit, configured to determine a planning starting point;

the lane changing longitudinal distance determining subunit is used for determining a lane changing longitudinal distance;

a lane change end point determining subunit, configured to determine a plurality of lane change end points according to the position of the planned starting point and the lane change longitudinal distance, where the plurality of lane change end points include position points located on the target path;

a lane change section determining subunit, configured to determine multiple lane change sections according to the position of the planned starting point, the positions of the lane change end points, the kinematic state of the autonomous vehicle at the planned starting point, and the kinematic state of the autonomous vehicle when the autonomous vehicle is in alignment at the lane change end points;

the extension section determining subunit is used for determining a plurality of extension sections according to the positions of the plurality of lane changing end points, wherein the extension sections are track sections parallel to the target platform;

and the candidate track generating subunit is used for connecting the plurality of lane changing sections with the corresponding extension sections and determining the plurality of candidate navigation tracks.

27. The apparatus of 226, said lane-change longitudinal distance determining subunit comprising: a recommended distance determination module for determining a recommended longitudinal distance based on a road environment and a kinematic state of the autonomous vehicle;

the limit lane changing and righting point determining module is used for determining the position of a limit lane changing and righting point, wherein the limit lane changing and righting point is a position point which is closest to the target stop point and is used for realizing the righting of the vehicle body of the automatic driving vehicle when the automatic driving vehicle changes the lane to the target path;

an available longitudinal distance determining module, configured to determine an available longitudinal distance according to the position of the planning start point and the position of the correction point;

a smaller distance determination module to determine a smaller longitudinal distance of the recommended longitudinal distance and the available longitudinal distance;

and the lane changing longitudinal distance determining module is used for taking the smaller longitudinal distance as the lane changing longitudinal distance under the condition that the smaller longitudinal distance is greater than or equal to a threshold longitudinal distance, wherein the threshold longitudinal distance is the longitudinal distance required by the automatic driving vehicle to change the lane from the current path to the target path by adopting the maximum steering capacity.

28. The apparatus of 27, the autonomous vehicle being a non-towing vehicle;

and the limit lane changing and righting point determining module takes the position of the target stop point as the position of the limit lane changing and righting point.

29. The apparatus of 27, wherein the autonomous vehicle is a trailer vehicle comprising a tractor and a trailer, and the limit lane change settlement point is a position point where the tractor changes lanes to the target path to achieve body settlement;

the limit lane changing and righting point determining module determines a righting driving distance according to the structure of the trailer and a typical steering included angle between the trailer and the tractor, wherein the righting driving distance is a longitudinal distance which is driven by the tractor when the trailer is changed to the target path and is completely righted; and determining the position of the limit lane changing and correcting point according to the correcting running distance and the position of the target stop point.

30. The apparatus according to any one of claims 27 to 30, wherein the inbound restriction judging unit includes: the obstacle judging subunit is used for judging whether an obstacle exists on the first navigation track; and/or the presence of a gas in the gas,

a safety constraint judging subunit, configured to judge whether or not the autonomous vehicle travels along the first ferry track to meet a safety constraint; and/or the presence of a gas in the gas,

and the included angle judging subunit is used for judging whether the included angle between the first navigation track extension section and the target path is smaller than an included angle threshold value.

31. The apparatus of 30, further comprising: the non-obstacle-avoidance path determining unit is used for setting a non-obstacle-avoidance path on the target path;

the obstacle judging subunit is configured to judge whether an obstacle exists in a track segment of the first navigation track outside the obstacle avoidance free path.

32. The apparatus of 31, the non-obstacle avoidance path determining unit comprising: the obstacle avoidance starting point determining subunit is used for determining an obstacle avoidance starting point according to the position of the limit lane changing righting point and the widening distance, and the obstacle avoidance starting point is located on the target path;

and the non-obstacle-avoidance path determining subunit is used for setting a path between the non-obstacle-avoidance starting point and the target stop point as the non-obstacle-avoidance path.

33. The apparatus of 31, further comprising: and the widening distance determining unit is used for determining the widening distance according to the threshold longitudinal distance or the curve characteristic of the first navigation track lane change section and a preset numerical distance.

34. The apparatus of any of claims 27-30, in a case where the lane-change longitudinal distance determination module determines that the smaller longitudinal distance is less than the threshold longitudinal distance, the apparatus further comprising:

a second navigation track planning unit, configured to plan a second navigation track according to the threshold longitudinal distance, where the second navigation track is a navigation track for the autonomous vehicle to change the lane to the target path;

and the station entering track locking unit is used for locking the second navigation track into the station entering track.

35. The apparatus of any of claims 23-29, further comprising:

the counting unit is used for increasing the count value of the track locking counter by one under the condition that the first navigation track is judged to accord with the station entering constraint condition;

the entry trajectory locking unit locks the first ferry trajectory to an entry trajectory when a count value of the trajectory lock counter reaches a count threshold value.

36. The apparatus of claim 25, the inbound track lock unit comprising:

the track quality comparison subunit is used for judging whether the first navigation track is superior to a historical track to be selected, wherein the historical track to be selected is a previously determined navigation track which accords with the station entering constraint condition and at least partially coincides with the target path in an extension section;

and the station entering track selecting subunit is used for locking the first navigation track as the station entering track under the condition that the first navigation track is superior to the history track to be selected.

37. The apparatus of 36, wherein the trajectory goodness comparison subunit comprises:

the distance calculation module is used for calculating a first longitudinal distance from the first navigation track lane change end point to the target stop point and calculating a second longitudinal distance from the to-be-selected historical track lane change end point to the target stop point;

the distance comparison module is used for judging whether the first longitudinal distance is smaller than the second longitudinal distance;

and the track quality determining module is used for judging that the first navigation track is superior to the candidate historical track under the condition that whether the first longitudinal distance is smaller than the second longitudinal distance.

38. The apparatus of 35, further comprising: the counting unit resets the count value of the track locking counter to zero when the first navigation track is judged not to meet the station entering constraint condition.

39. An arrival trajectory planning device for an autonomous vehicle, comprising: the route selection unit is used for determining a target route and at least one other route in a plurality of routes to be selected when the automatic driving vehicle is in a station entering planning state, wherein the target route is a route which is parallel to a target platform and passes through a target stop point;

a transverse distance acquiring unit, configured to acquire a transverse distance from each of the other paths to the target path;

40. The apparatus of 39, further comprising: and the parking instruction issuing unit is used for issuing an instruction for controlling the automatic driving vehicle to park at the waiting point or before the waiting point under the condition that the automatic driving vehicle is predicted to drive to the corresponding waiting point along the other path and the parking track is not locked.

41. The apparatus of any of claims 39-40, further comprising: and the limit lane changing and righting point determining unit is used for determining the position of a limit lane changing and righting point, wherein the limit lane changing and righting point is a position point which is closest to the target stop point and realizes the righting of the vehicle body of the automatic driving vehicle from the lane changing to the target path.

42. The apparatus of 41, the autonomous vehicle being a trailer vehicle comprising a tractor and a trailer, the extreme lane change true point being a point at which the tractor changes lanes to the target path to achieve body true; the limit lane changing and correcting point determining unit comprises:

a longitudinal driving distance determining subunit, configured to determine a swing driving distance according to a structure of the trailer and a typical steering included angle between the trailer and the tractor, where the swing driving distance is a longitudinal distance traveled by the tractor when the trailer is made to change lanes to the target path and is completely swung;

and the limit lane changing and correcting point determining subunit is used for determining the position of the limit lane changing and correcting point according to the correcting running distance and the position of the target stop point.

43. The apparatus of 42, further comprising: the obstacle avoidance starting point determining unit is used for determining an obstacle avoidance starting point on the target path according to the position of the limit lane changing righting point and the widening distance;

and the non-obstacle-avoidance path determining unit is used for setting the path between the non-obstacle-avoidance starting point and the target stop point as a non-obstacle-avoidance path.

44. The apparatus of 43, further comprising: and the relaxation distance determining unit is used for determining the relaxation distance according to a threshold longitudinal distance and a preset numerical distance, wherein the threshold longitudinal distance is a longitudinal distance required by the automatic driving vehicle to change the lane from the current path to the target path by adopting the maximum steering capacity.

Fig. 8 is a schematic structural diagram of a computing device provided by some embodiments of the present disclosure. Referring now in particular to FIG. 8, a block diagram of a computing device 800 suitable for use in implementing embodiments of the present disclosure is shown. The computing device illustrated in fig. 8 is only one example and should not impose any limitations on the functionality or scope of use of embodiments of the disclosure.

As shown in fig. 8, computing device 800 may include a processing means 801 (e.g., a central processing unit, a graphics processor, etc.) that may perform various appropriate actions and processes in accordance with a program stored in a read only memory ROM802 or a program loaded from a storage means 808 into a random access memory RAM 803. In the RAM803, various programs and data necessary for the operation of the computing device 800 are also stored. The processing apparatus 801, the ROM802, and the RAM803 are connected to each other by a bus 804. An input/output I/O interface 805 is also connected to bus 804.

Generally, the following devices may be connected to the I/O interface 805: input devices 806 including accelerometers, gyroscopes, and the like; output devices 807 including, for example, a Liquid Crystal Display (LCD), speakers, vibrators, or the like; storage 808 including, for example, magnetic tape, hard disk, etc.; and a communication device 809. Communications means 809 may allow computing device 800 to communicate wirelessly or by wire with other devices to exchange data. While fig. 8 illustrates a computing device 800 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program carried on a non-transitory computer readable medium, the computer program containing program code for performing the method illustrated by the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication means 809, or installed from the storage means 808, or installed from the ROM 802. The computer program, when executed by the processing apparatus 801, performs the above-described functions defined in the methods of the embodiments of the present disclosure.

It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.

The computer readable medium may be embodied in the computing device; or may exist separately and not be assembled into the computing device.

The computer readable medium carries one or more programs which, when executed by the computing device, cause the computing device to: generating a plurality of to-be-selected navigation tracks under the station entering planning state of the automatic driving vehicle, wherein the plurality of to-be-selected navigation tracks comprise a first navigation track, the extension section of the first navigation track is at least partially overlapped with a target path, and the target path is a path which is parallel to the target platform and passes through a target stop point; judging whether the first navigation track meets the station-entering constraint condition or not; if not, selecting an optimal navigation track from the plurality of navigation tracks to be selected; determining the transverse distance between the optimal navigation track point and the target path under the condition that the optimal navigation track is not the first navigation track; determining the position of a waiting point according to the transverse distance and the position of a target stop point, wherein the waiting point is a track point which is positioned on the extension section of the optimal navigation track, ensures that the automatic driving vehicle realizes vehicle alignment after changing the channel from the optimal navigation track to the target path, and has the minimum longitudinal distance with the target stop point; and issuing the optimal navigation track and the position of the waiting point to realize the running track control of the automatic driving vehicle.

Computer program code for carrying out operations for the present disclosure may be written in any combination of one or more programming languages, including but not limited to an object oriented programming language such as Java, smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units described in the embodiments of the present disclosure may be implemented by software or hardware. Where the name of an element does not in some cases constitute a limitation on the element itself.

The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems on a chip (SOCs), complex Programmable Logic Devices (CPLDs), and the like.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection according to one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The embodiments of the present disclosure further provide a computer-readable storage medium, where a computer program is stored in the storage medium, and when the computer program is executed by a processor, the method of any of the above method embodiments can be implemented, and the execution manner and the beneficial effect are similar, and are not described herein again.

In addition, in a fifth aspect, an embodiment of the present disclosure provides a vehicle, including an on-board control chip and a plurality of interactive display screens, where the on-board control chip is configured to execute the foregoing text input method and control at least two of the interactive display screens to independently display a text input interface. The vehicle-mounted control chip may be a central control chip in a vehicle, an entertainment system control chip independent of the central control chip, or other chips, and the embodiment of the present disclosure is not particularly limited; preferably, the vehicle-mounted control chip is a control chip specially used for controlling each interactive display screen in the vehicle intelligent cabin system.

It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a component of' 8230; \8230;" does not exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.

The foregoing are merely exemplary embodiments of the present disclosure, which enable those skilled in the art to understand or practice the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for planning an arrival track of an automatically driven vehicle is characterized by comprising the following steps:

generating a plurality of navigation tracks to be selected when the automatic driving vehicle is in a station entering planning state, wherein the navigation tracks to be selected comprise first navigation tracks, the extension sections of the first navigation tracks are at least partially overlapped with a target path, and the target path is a path which is parallel to a target station and passes through a target stop point;

if not, selecting an optimal navigation track from the plurality of navigation tracks to be selected;

under the condition that the optimal ferry track is not the first ferry track, acquiring the transverse distance between each track point on the optimal ferry track and the target path;

2. The method of claim 1, wherein, while generating the plurality of candidate voyage trajectories, the method further comprises:

generating the pointing direction of track points on each to-be-selected navigation track;

3. The method of claim 1, wherein after issuing the optimal voyage trajectory and the location of the waiting point, the method further comprises:

4. The method of claim 1, wherein the generating a plurality of candidate voyage trajectories comprises:

5. A method for planning an arrival track of an automatic driving vehicle is characterized by comprising the following steps:

acquiring the transverse distance from each other path to the target path;

6. An apparatus for planning an arrival trajectory of an autonomous vehicle, comprising:

7. An apparatus for planning an arrival trajectory of an autonomous vehicle, comprising:

8. A computing device comprising a processor and a memory, the memory for storing a computer program;

the computer program, when loaded by the processor, causes the processor to perform the method of planning an inbound trajectory for an autonomous vehicle as recited in any of claims 1-5.

9. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when executed by a processor, causes the processor to carry out the method of planning an arrival trajectory of an autonomous vehicle as claimed in any one of claims 1 to 5.

10. An autonomous vehicle comprising an on-board control chip for performing the method of planning an inbound trajectory for an autonomous vehicle as claimed in any one of claims 1 to 5.