CN112649012A

CN112649012A - Trajectory planning method, equipment, medium and unmanned equipment

Info

Publication number: CN112649012A
Application number: CN202011482262.8A
Authority: CN
Inventors: 林伟
Original assignee: Beijing Sankuai Online Technology Co Ltd
Current assignee: Beijing Sankuai Online Technology Co Ltd
Priority date: 2020-12-15
Filing date: 2020-12-15
Publication date: 2021-04-13

Abstract

The present specification discloses a trajectory planning method, apparatus, medium, and unmanned equipment, including: acquiring obstacle data of obstacles around a road where unmanned equipment runs; aiming at different set projection models, determining a cost parameter corresponding to the projection model according to the obstacle data of the obstacle; selecting a projection model used for the obstacle from different preset projection models according to the obtained cost parameters corresponding to the different projection models; determining projection coordinates of the obstacles projected in a road coordinate system corresponding to the driving road by using the selected projection model; and planning a driving track for the unmanned equipment according to the projection coordinates of the obstacles. Therefore, a proper projection model is selected according to the difficulty of planning the driving track for the unmanned equipment, so that the planned driving track can reasonably avoid obstacles, planning resources are saved, and the efficiency of planning the driving track for the unmanned equipment is improved.

Description

Trajectory planning method, equipment, medium and unmanned equipment

Technical Field

The specification relates to the technical field of unmanned driving, in particular to a trajectory planning method, equipment, a medium and unmanned equipment.

Background

Along with the development of artificial intelligence technology, computer technology and car networking technology, the unmanned technology comes. Unmanned vehicles, which are generated with unmanned technologies, are also receiving wide attention.

In order to guarantee the driving safety of the unmanned vehicle, it is necessary to provide a reasonable and effective driving path for the unmanned vehicle. A trajectory planning module is typically deployed in the unmanned vehicle, which is primarily used to plan local travel paths for the unmanned vehicle.

When planning a trajectory for an unmanned vehicle, obstacles around the unmanned vehicle need to be considered to ensure that the planned driving trajectory can effectively avoid the obstacles. Specifically, first, obstacles around the unmanned vehicle are determined; secondly, projecting the obstacle to a road coordinate system corresponding to a road on which the unmanned vehicle runs according to the position of the obstacle to obtain a projection coordinate of the obstacle; and finally, planning the track of the unmanned vehicle according to the projection coordinate.

The road traveled by the unmanned vehicle comprises some complicated road sections, such as: a sharp turn road, an intersection, a roundabout, and the like, and therefore, a closest point projection method is generally used to determine projection coordinates of an obstacle. However, in practical applications, it is found that, by determining the projection coordinates of the obstacle on these complex roads by using the closest point projection method, it is easy to find that the distance between the determined projection coordinates and the position coordinates of the actual position of the obstacle in the road coordinate system is long, so that the calculation resources consumed for planning the driving track for the unmanned vehicle based on the projection coordinates are large, and the planned driving track is not necessarily optimal, and even causes a serious influence on the subsequent driving of the unmanned vehicle (for example, the unmanned vehicle cannot travel in a way afterwards).

Therefore, the present application proposes a trajectory planning scheme to solve the above problems.

Disclosure of Invention

The present specification provides a trajectory planning method, a device, a medium, and an unmanned device, to partially solve the problems of the prior art.

The technical scheme adopted by the specification is as follows:

the track planning method provided by the specification comprises the following steps:

acquiring obstacle data of obstacles around a road where unmanned equipment runs;

aiming at different set projection models, determining a cost parameter corresponding to the projection model according to barrier data of the barrier, wherein the cost parameter is used for representing the difficulty of planning a driving track for the unmanned equipment by using the projection model;

selecting a projection model used for the obstacle from different preset projection models according to the obtained cost parameters corresponding to the different projection models;

determining projection coordinates of the obstacles projected in a road coordinate system corresponding to the driving road by using the selected projection model;

and planning a driving track for the unmanned equipment according to the projection coordinates of the obstacles.

Optionally, determining a cost parameter corresponding to the projection model according to the obstacle data of the obstacle specifically includes:

determining the amount of resources to be consumed for planning a driving track for the unmanned equipment by using the projection model according to the space position of the obstacle in the driving road, the shape data of the obstacle and the reference line position of a road coordinate system corresponding to the driving road, wherein the space position of the obstacle in the driving road is contained in the obstacle data;

determining a weight value of a resource amount to be consumed for planning a driving track for the unmanned equipment by using the projection model according to the type of the obstacle and the motion data of the obstacle contained in the obstacle data;

and determining a cost parameter corresponding to the projection model according to the resource amount and the weight value.

Optionally, determining, according to the spatial position of the obstacle in the driving road, the shape data of the obstacle, and the reference line position of the road coordinate system corresponding to the driving road, an amount of resources to be consumed for planning the driving trajectory for the unmanned aerial vehicle using the projection model, specifically including:

determining a spatial vector of the obstacle from shape data of the obstacle included in the obstacle data;

and estimating the amount of resources consumed by planning the driving track for the unmanned equipment by adopting the projection model by utilizing a preset projection model cost function according to the space vector of the obstacle, the space position of the obstacle and the reference line position of a road coordinate system corresponding to the driving road.

Optionally, estimating, by using a preset projection model cost function, an amount of resources to be consumed by using the projection model to plan a driving trajectory for the unmanned aerial vehicle, specifically including:

determining a relative position between the obstacle and a reference line of a road coordinate system corresponding to the driving road according to the space vector of the obstacle, the space position of the obstacle and the position of the reference line of the road coordinate system, wherein the relative position comprises an actual distance;

determining a predicted position between the obstacle projected by the projection model and a reference line of the road coordinate system based on the projection model, wherein the predicted position comprises a predicted distance;

and estimating the resource amount consumed by planning the driving track for the unmanned equipment by adopting the projection model according to the relative position and the predicted position by utilizing a preset projection model cost function.

Optionally, determining a projection coordinate of the obstacle projected in a road coordinate system corresponding to the driving road by using the selected projection model, specifically including:

if the projection model determined for the obstacle is a multipoint projection model, determining a projection curve obtained by projecting the obstacle into a road coordinate system corresponding to the driving road based on the multipoint projection model and position data in obstacle data of the obstacle, wherein the projection curve is used for representing the distance change from the obstacle to a reference line of the road coordinate system;

selecting a specific coordinate point from the determined projection curve as a projection coordinate of the obstacle in the road coordinate system.

Optionally, selecting a specific coordinate point from the determined projection curve as a projection coordinate of the obstacle in the road coordinate system, specifically including:

determining the distance from each coordinate point of the projection curve to a reference line of the road coordinate system;

finding out a coordinate point corresponding to the minimum distance and/or minimum distance of the reference line of the road coordinate system as a specific coordinate point;

and taking the coordinates of the specific coordinate point as the projection coordinates of the obstacle in the road coordinate system.

if the projection model determined for the obstacle is a continuous projection model, determining a projection curve obtained by projecting the obstacle into a road coordinate system corresponding to the driving road based on the continuous projection model and position data in obstacle data of the obstacle, wherein the projection curve is used for representing the distance change from the obstacle to a reference line of the road coordinate system;

and selecting coordinate points which fall into a specified area and are distributed continuously from the determined projection curve as projection coordinates of the obstacle in the road coordinate system.

Optionally, selecting, from the determined projection curve, coordinate points that fall into a specified area and are continuously distributed as projection coordinates of the obstacle in the road coordinate system, specifically including:

according to the determined distance, determining that the coordinate point with the distance smaller than the set value falls into the designated area;

and taking the coordinates corresponding to the coordinate points which fall into the specified area and are distributed continuously as the projection coordinates of the obstacle in the road coordinate system.

Optionally, planning a driving path for the unmanned aerial vehicle according to the projection coordinates of each obstacle specifically includes:

and planning a driving track capable of avoiding each obstacle for the unmanned equipment according to the projection coordinates of each obstacle and the pre-planned driving path.

An embodiment of the present specification further provides a trajectory planning apparatus, including:

the system comprises a collecting unit, a control unit and a display unit, wherein the collecting unit is used for collecting barrier data of barriers around a road where unmanned equipment runs;

the processing unit is used for determining a cost parameter corresponding to the projection model according to the barrier data of the barrier aiming at different set projection models, wherein the cost parameter is used for representing the difficulty of planning a driving track for the unmanned equipment by using the projection model; selecting a projection model used for the obstacle from different preset projection models according to the obtained cost parameters corresponding to the different projection models; determining projection coordinates of the obstacles projected in a road coordinate system corresponding to the driving road by using the selected projection model;

and the planning unit is used for planning a driving track for the unmanned equipment according to the projection coordinates of the obstacles.

The present specification provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the trajectory planning method described above.

The unmanned device provided by the present specification is equipped with a trajectory planning device, where the trajectory planning device includes a memory, a processor, and a computer program stored in the memory and running on the processor, and the processor implements the trajectory planning method described above when executing the program.

The technical scheme adopted by the specification can achieve the following beneficial effects:

according to the track planning method provided by the specification, the obstacle data of obstacles around the road where the unmanned equipment runs are collected; aiming at different set projection models, determining a cost parameter corresponding to the projection model according to barrier data of the barrier, wherein the cost parameter is used for representing the difficulty of planning a driving track for the unmanned equipment by using the projection model; selecting a projection model used for the obstacle from different preset projection models according to the obtained cost parameters corresponding to the different projection models; determining projection coordinates of the obstacles projected in a road coordinate system corresponding to the driving road by using the selected projection model; and planning a driving track for the unmanned equipment according to the projection coordinates of the obstacles. Therefore, the projection coordinate of the barrier is not determined by singly adopting a closest point projection method, but a proper projection model is selected according to the difficulty of planning the driving track for the unmanned equipment, so that the phenomenon that the distance between the determined projection coordinate and the position coordinate, corresponding to the actual position of the barrier, in the road coordinate system is overlarge due to the space distortion of the road coordinate system can be avoided, the planned driving track can reasonably avoid the barrier, the planning resource is saved, and the efficiency of planning the driving track for the unmanned equipment is improved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the specification and are incorporated in and constitute a part of this specification, illustrate embodiments of the specification and together with the description serve to explain the specification and not to limit the specification in a non-limiting sense. In the drawings:

fig. 1 is a schematic flowchart of a trajectory planning method provided in an embodiment of the present disclosure;

fig. 2(a) is a schematic diagram of a single-point projection model provided in an embodiment of the present disclosure;

fig. 2(b) is a schematic diagram of a single-point projection model provided in an embodiment of the present disclosure;

FIG. 3(a) is a schematic diagram of a multi-point projection model provided in an embodiment of the present disclosure;

FIG. 3(b) is a schematic diagram of a multi-point projection model provided in an embodiment of the present disclosure;

FIG. 3(c) is a schematic diagram of a multi-point projection model provided in an embodiment of the present disclosure;

FIG. 4(a) is a schematic diagram of a continuous projection model provided in an embodiment of the present disclosure;

FIG. 4(b) is a schematic diagram of a continuous projection model provided in an embodiment of the present disclosure;

FIG. 4(c) is a schematic diagram of a continuous projection model provided in an embodiment of the present disclosure;

fig. 5 is a schematic structural diagram of a trajectory planning scheme provided in an embodiment of the present disclosure;

fig. 6 is a schematic structural diagram of a trajectory planning apparatus provided in an embodiment of the present disclosure;

fig. 7 is a schematic structural diagram of an unmanned aerial vehicle provided in an embodiment of the present specification.

Detailed Description

In practical application, when planning a driving track for unmanned equipment, firstly, a road coordinate system needs to be constructed. A road coordinate system (SL coordinate system) is constructed based on the center line of the traveled road, usually along the traveling direction of the unmanned aerial vehicle. The center line of the running road is taken as the S axis of the road coordinate system along the running direction of the unmanned equipment; the L-axis of the road coordinate system is constructed perpendicular to the S-axis. Secondly, the position (i.e. projection coordinates) of the obstacle in the road coordinate system is determined according to the conversion relation between the world coordinate system and the road coordinate system. And finally, planning a driving track for the unmanned equipment based on the determined projection coordinates of the obstacle.

However, due to the complexity of the road traveled by the unmanned aerial vehicle, when the road coordinate system is constructed, the road space is deformed (such as compression, stretching and tearing) along with the complexity of the road traveled, which is particularly the case in a sharp turn section and a section crossing a target path. The projection coordinates of the obstacle determined by the closest point projection method are far away from the unmanned aerial vehicle due to deformation, so that when a driving track is planned for the unmanned aerial vehicle based on the projection coordinates, not only is the planning difficulty increased and a large amount of resources consumed, but also the track planning may fail (i.e., a proper track planning result cannot be obtained) because the track planning is an accumulated process.

Based on this, the specification provides a trajectory planning method, which includes acquiring obstacle data of obstacles around a road where unmanned equipment runs; aiming at different set projection models, determining a cost parameter corresponding to the projection model according to barrier data of the barrier, wherein the cost parameter is used for representing the difficulty of planning a driving track for the unmanned equipment by using the projection model; selecting a projection model used for the obstacle from different preset projection models according to the obtained cost parameters corresponding to the different projection models; determining projection coordinates of the obstacles projected in a road coordinate system corresponding to the driving road by using the selected projection model; and planning a driving track for the unmanned equipment according to the projection coordinates of the obstacles. Therefore, the projection coordinate of the barrier is not determined by singly adopting a closest point projection method, but a proper projection model is selected according to the difficulty of planning the driving track for the unmanned equipment, so that the phenomenon that the distance between the determined projection coordinate and the position coordinate, corresponding to the actual position of the barrier, in the road coordinate system is overlarge due to the space distortion of the road coordinate system can be avoided, the planned driving track can reasonably avoid the barrier, the planning resource is saved, and the efficiency of planning the driving track for the unmanned equipment is improved.

In order to make the objects, technical solutions and advantages of the present disclosure more clear, the technical solutions of the present disclosure will be clearly and completely described below with reference to the specific embodiments of the present disclosure and the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present disclosure, and not all embodiments. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments in the present specification without any creative effort belong to the protection scope of the present specification.

The technical solutions provided by the embodiments of the present description are described in detail below with reference to the accompanying drawings.

Fig. 1 is a schematic flow chart of a trajectory planning method provided in an embodiment of the present specification. The method may be as follows.

Step 101: obstacle data of obstacles around a road on which the unmanned aerial vehicle is driven are collected.

In the embodiments provided in this specification, the unmanned device collects obstacle data of obstacles around a road on which the unmanned device is traveling in real time during traveling. Obstacle data here includes, but is not limited to: the position, shape, type, state of motion, etc. of the obstacle. The position here is understood to be a position in the world coordinate system, and a space vector of the obstacle can be obtained by calculation using the position and shape of the obstacle.

Step 103: and aiming at different set projection models, determining a cost parameter corresponding to the projection model according to the obstacle data of the obstacle.

The cost parameter is used for representing the difficulty of planning the driving track for the unmanned equipment by using the projection model.

In the embodiment provided in this specification, since the road actually traveled by the unmanned aerial vehicle is complex, when the road coordinate system is constructed, the complex road may be spatially deformed (for example, distorted, stretched, etc.), and then, in order to avoid a problem that a distance between the determined projection coordinates of the obstacle and the position coordinates of the actual position of the obstacle in the road coordinate system is too large due to such spatial deformation, a plurality of different projection models are established in advance, where the projection models include, but are not limited to, a single-point projection model, a multi-point projection model, a continuous projection model, and so on. That is, the projection coordinates of the obstacle are not determined by using the closest point projection method singly, but an appropriate projection model is selected from a plurality of different projection models, so that the projection coordinates of the obstacle are determined by selecting the appropriate projection model, and the problem mentioned above is solved.

Specifically, determining a projection model, and determining a cost parameter corresponding to the projection model according to the obstacle data of the obstacle; and selecting a proper projection model for the obstacle according to the obtained cost parameter.

How to determine the cost parameter corresponding to the projection model is described in detail below.

Specifically, in the first step, the amount of resources to be consumed for planning the driving trajectory for the unmanned aerial vehicle using the projection model is determined according to the spatial position of the obstacle in the driving road, the shape data of the obstacle, and the reference line position of the road coordinate system corresponding to the driving road, which are included in the obstacle data.

The resource amount described here can be understood as a hardware resource, a software resource, a time period used, and the like used in calculating the travel locus of the unmanned aerial vehicle. The greater the amount of resources consumed here indicates the greater the difficulty of planning a travel trajectory for the unmanned aerial vehicle, and conversely, the lesser the difficulty of planning a travel trajectory for the unmanned aerial vehicle.

Specifically, first, a space vector of the obstacle is determined from shape data of the obstacle included in the obstacle data.

For example: the unmanned equipment acquires obstacle data of an obstacle through a vision sensor, the obstacle data can be picture data, shape data of the obstacle is obtained from the picture data by analyzing the picture data, and a space vector of the obstacle can be obtained through calculation by combining a space position positioned by the unmanned equipment.

And secondly, estimating the amount of resources consumed by planning the driving track for the unmanned equipment by adopting the projection model by utilizing a preset projection model cost function according to the space vector of the obstacle, the space position of the obstacle and the reference line position of a road coordinate system corresponding to the driving road.

The spatial position of the obstacle mentioned herein may be understood as a position determined by a world coordinate system, i.e., a position coordinate of a position where the obstacle is located in the world coordinate system;

the position of the reference line in the road coordinate system corresponding to the road to be traveled described herein may be understood as a position determined by a world coordinate system, that is, a position coordinate of a reference line in the road coordinate system corresponding to the road to be traveled in the world coordinate system, the position coordinate including an abscissa, an ordinate, an angle between a tangent line at a reference point closest to the obstacle on the reference line and the reference line, and a curvature corresponding to the reference line.

Specifically, determining a relative position between the obstacle and a reference line of a road coordinate system corresponding to the driving road according to the space vector of the obstacle, the space position of the obstacle and the position of the reference line of the road coordinate system, wherein the relative position comprises an actual distance; determining a predicted position between the obstacle projected by the projection model and a reference line of the road coordinate system based on the projection model, wherein the predicted position comprises a predicted distance; and estimating the resource amount consumed by planning the driving track for the unmanned equipment by adopting the projection model according to the relative position and the predicted position by utilizing a preset projection model cost function.

The "determination of the relative position between the obstacle and the reference line of the road coordinate system" described herein may be obtained by calculating the distance between the obstacle and the center line of the road on which the vehicle travels in a world coordinate system. If the obstacle has a large volume and the corresponding spatial position is more than one, the relative position obtained by calculation may be an average value of a plurality of distances, that is, the distance between each spatial position coordinate and the center line of the road on which the vehicle is traveling is calculated, and then the plurality of distances obtained by calculation are averaged to obtain the relative position between the obstacle and the reference line of the road coordinate system.

The "determining the predicted position between the obstacle projected by using the projection model and the reference line of the road coordinate system" described herein may predict a deformation amount of the reference line of the road coordinate system based on a degree of curvature (corresponding to a curvature) of a road to be traveled, and further determine the predicted position between the obstacle projected by using the projection model and the reference line of the road coordinate system based on the deformation amount, that is, the larger the deformation amount, the larger the change in distance between the obstacle projected by using the projection model and the reference line of the road coordinate system; on the contrary, the change of the distance between the projected obstacle and the reference line of the road coordinate system is smaller.

And estimating the amount of resources consumed by planning the driving track for the unmanned equipment by adopting the projection model based on the difference value and a preset projection model cost function by comparing the difference value between the relative position and the predicted position. Specifically, the larger the difference value is, the more the resource amount consumed for planning the driving track for the unmanned aerial vehicle by using the projection model is; on the contrary, the smaller the resource amount consumed for planning the driving track for the unmanned equipment by adopting the projection model is.

Optionally, the spatial position of the obstacle in the driving road, the shape data of the obstacle, and the position of the reference line of the road coordinate system corresponding to the driving road, which are included in the obstacle data, are input into a preset projection model cost prediction model, the preset projection model cost prediction model performs calculation according to the input data, and the amount of resources consumed for planning the driving trajectory for the unmanned aerial vehicle by using the projection model is output.

The preset projection model cost prediction model may be obtained by training a neural network model based on data such as resource consumption consumed by planning a driving track for the unmanned aerial vehicle by using each projection model generated historically.

For example: COST ═ f_single f_multi f_conti]＝[cost_single cost_multi cost_conti](ii) a Wherein COST represents a preset projection model COST function; the preset cost function of the projection model comprises cost functions corresponding to different projection models. For example: here, COST includes a COST function corresponding to a single-point (single) projection model, a COST function corresponding to a multi-point (multi) projection model, and a COST function corresponding to a continuous (conti) projection model.

Optionally, the cost function in the preset projection model cost function includes f-functions corresponding to different projection models:

wherein obs_g,c＝[[x,y,l,w,classes]]；refline_g(i)＝[[x,y,θ,κ]](ii) a dis represents the distance between a point on the obstacle and one reference point of a reference line of the road sign coordinates; delta theta representing coordinates of obstacle and road signThe included angle of the reference line at a certain reference point.

Note that obs is_g,c＝[[x,y,l,w,classes]]Indicating obstacle properties, such as: coordinates (x, y), length and width parameters (l, w), type parameters (classes) in the world coordinate system; refline_g(i)＝[[x,y,θ,κ]]The coordinate attribute of the ith reference point in the reference line representing the coordinates of the road marker, for example: (x, y) represents the coordinates of the ith reference point, theta represents the angle between the tangent line at the ith reference point and the reference line, and kappa represents the curvature corresponding to the reference line of the road sign coordinates at the ith reference point.

And secondly, determining a weight value of the resource quantity to be consumed for planning the driving track for the unmanned equipment by using the projection model according to the type of the obstacle and the motion data of the obstacle contained in the obstacle data.

For example: w ═ f_W(obs_k,c)＝[w_single,w_multi,w_conti]Wherein W represents a weight.

And thirdly, determining a cost parameter corresponding to the projection model according to the resource amount and the weight value.

Specifically, a product between the resource amount and the weight value is calculated, and an obtained product value may be regarded as a cost parameter corresponding to the projection model.

Step 105: and selecting the projection model used for the obstacle from different preset projection models according to the obtained cost parameters corresponding to the different projection models.

In an embodiment provided in this specification, cost parameters corresponding to different projection models are compared, a projection model corresponding to a minimum cost parameter is selected, and a projection model to be used is selected for the obstacle.

Step 107: and determining the projection coordinates of the obstacles projected in a road coordinate system corresponding to the driving road by using the selected projection model.

In an embodiment provided in this specification, if the projection model determined for the obstacle is a single-point projection model, the obstacle is projected onto a road coordinate system corresponding to the travel road, distances from the obstacle to reference lines in the road coordinate system are calculated, a minimum value is selected from the calculated distances, and a coordinate point corresponding to the minimum distance is determined as a projection coordinate of the obstacle projected onto the road coordinate system corresponding to the travel road.

Fig. 2(a) and fig. 2(b) are schematic diagrams of a single-point projection model provided in an embodiment of the present disclosure. As can be seen from fig. 2(a), on a road where the unmanned aerial vehicle travels, the curvature of the road corresponding to the position where the obstacle appears is not large, that is, the road complexity is relatively small, and it is determined to use the single-point projection model by calculating the cost parameter. As can be seen from fig. 2(b), the distance projected to the point s1 is the smallest when the obstacle is projected onto the road coordinate system corresponding to the driving road, and therefore, the corresponding coordinate at s1 is determined as the projection coordinate of the obstacle projected onto the road coordinate system corresponding to the driving road.

If the projection model determined for the obstacle is a multipoint projection model, determining a projection curve obtained by projecting the obstacle into a road coordinate system corresponding to the driving road based on the multipoint projection model and position data in obstacle data of the obstacle, wherein the projection curve is used for representing the distance change from the obstacle to a reference line of the road coordinate system; selecting a specific coordinate point from the determined projection curve as a projection coordinate of the obstacle in the road coordinate system.

Specifically, the distance from each coordinate point on the projection curve to a reference line of the road coordinate system is determined; finding out a coordinate point corresponding to the minimum distance and/or minimum distance of the reference line of the road coordinate system as a specific coordinate point; and taking the coordinates of the specific coordinate point as the projection coordinates of the obstacle in the road coordinate system.

Fig. 3(a), fig. 3(b), and fig. 3(c) are schematic diagrams of a multi-point projection model provided in an embodiment of the present disclosure. As can be seen from fig. 3(a), on the road where the unmanned aerial vehicle travels, the position where the obstacle appears is at the intersection of the road, and belongs to a complex road scene, and it is determined to adopt the multipoint projection model by calculating the cost parameter. As can be seen from fig. 3(b), the distance between each coordinate point on the projection curve and the reference line is different, so that the projection curve is obtained by projecting the obstacle onto the road coordinate system corresponding to the driving road through the multipoint projection model. The distance minimum point (s2) and/or minimum point (s1) to the reference line of the road coordinate system can be determined by analysis. As can be seen from fig. 3(c), coordinate points corresponding to the distance minimum point (s2) and/or the minimum point (s1) to the reference line of the road coordinate system are determined as the projection coordinates of the obstacle in the road coordinate system.

Specifically, the distance from each coordinate point of the projection curve to a reference line of the road coordinate system is determined; according to the determined distance, determining that the coordinate point with the distance smaller than the set value falls into the designated area; and taking the coordinates corresponding to the coordinate points which fall into the specified area and are distributed continuously as the projection coordinates of the obstacle in the road coordinate system.

Fig. 4(a), fig. 4(b), and fig. 4(c) are schematic diagrams of a continuous projection model provided in an embodiment of the present disclosure. As can be seen from fig. 4(a), on the road where the unmanned aerial vehicle travels, the position where the obstacle appears is a sharp turn of the road, and belongs to a complex road scene, and it is determined to adopt the continuous projection model by calculating the cost parameter. As can be seen from fig. 4(b), the distances from the coordinate points on the projection curve to the reference line are different, and the projection curve is obtained by projecting the obstacle onto the road coordinate system corresponding to the driving road by the continuous projection model. A plurality of coordinate points whose distances to the reference line of the road coordinate system are smaller than a set value can be determined by analysis. As can be seen from fig. 4(c), a plurality of coordinate points (from s1 to s2) whose distances to the reference line of the road coordinate system are smaller than a set value are determined as the projection coordinates of the obstacle in the road coordinate system.

Step 109: and planning a driving track for the unmanned equipment according to the projection coordinates of the obstacles.

In the embodiments provided in the present specification, a travel trajectory capable of avoiding each obstacle is planned for the unmanned aerial vehicle based on the projection coordinates of each obstacle and a previously planned travel path.

According to the embodiment provided by the specification, the obstacle data of the obstacles around the road where the unmanned equipment runs are collected; aiming at different set projection models, determining a cost parameter corresponding to the projection model according to barrier data of the barrier, wherein the cost parameter is used for representing the difficulty of planning a driving track for the unmanned equipment by using the projection model; selecting a projection model used for the obstacle from different preset projection models according to the obtained cost parameters corresponding to the different projection models; determining projection coordinates of the obstacles projected in a road coordinate system corresponding to the driving road by using the selected projection model; and planning a driving track for the unmanned equipment according to the projection coordinates of the obstacles.

Therefore, the projection coordinate of the barrier is not determined by singly adopting a closest point projection method, but a proper projection model is selected according to the difficulty of planning the driving track for the unmanned equipment, so that the phenomenon that the distance between the determined projection coordinate and the position coordinate, corresponding to the actual position of the barrier, in the road coordinate system is overlarge due to the space distortion of the road coordinate system can be avoided, the planned driving track can reasonably avoid the barrier, the planning resource is saved, and the efficiency of planning the driving track for the unmanned equipment is improved.

Fig. 5 is a schematic structural diagram of a trajectory planning scheme provided in an embodiment of the present specification. As can be seen from fig. 5, in the trajectory planning scheme, a driving path (i.e., a target path) of the unmanned aerial vehicle is first determined through a map, and a sensing module senses surrounding obstacles in the driving process of the unmanned aerial vehicle; secondly, determining a projection model for each obstacle by using the scheme shown in fig. 1, and determining projection coordinates corresponding to each obstacle based on the determined projection model; and finally, planning a driving track for the unmanned equipment based on the projection coordinates of the obstacles and a preset target path.

The trajectory planning method provided by the specification can be applied to a remote driving system connected with the unmanned vehicle and can also be applied to various application scenes of unmanned vehicle driving. The unmanned vehicle may be an unmanned delivery vehicle. The unmanned delivery vehicle can be applied to the field of delivery by using the unmanned delivery vehicle, such as delivery scenes of express delivery, takeaway and the like by using the unmanned delivery vehicle.

The term "unmanned vehicle" or "unmanned vehicle" as used herein includes vehicles traveling on the ground (e.g., cars, trucks, buses, etc.), but may also include vehicles traveling in the air (e.g., drones, airplanes, helicopters, etc.), vehicles traveling on water (e.g., boats, submarines, etc.). One or more "vehicles" discussed herein may or may not accommodate one or more passengers therein.

Based on the same idea, the trajectory planning method provided by the embodiment of the present specification further provides corresponding devices, storage media, and electronic devices.

Fig. 6 is a schematic structural diagram of a trajectory planning apparatus provided in an embodiment of the present specification. The trajectory planning device includes: an acquisition unit 601, a processing unit 602 and a planning unit 603, wherein:

the acquisition unit 601 is used for acquiring obstacle data of obstacles around a road where the unmanned equipment runs;

a processing unit 602, configured to determine, for different set projection models, a cost parameter corresponding to the projection model according to obstacle data of the obstacle, where the cost parameter is used to represent a difficulty level for planning a driving trajectory for the unmanned aerial vehicle using the projection model; selecting a projection model used for the obstacle from different preset projection models according to the obtained cost parameters corresponding to the different projection models; determining projection coordinates of the obstacles projected in a road coordinate system corresponding to the driving road by using the selected projection model;

and a planning unit 603, configured to plan a driving trajectory for the unmanned aerial vehicle according to the projection coordinates of the obstacle.

In another embodiment provided in this specification, the determining, by the processing unit 602, a cost parameter corresponding to the projection model according to the obstacle data of the obstacle specifically includes:

In another embodiment provided in the present specification, the determining, by the processing unit 602, an amount of resources to be consumed for planning a driving trajectory for the unmanned aerial vehicle by using the projection model according to a spatial position of the obstacle in the driving road, shape data of the obstacle, and a reference line position of a road coordinate system corresponding to the driving road, which are included in the obstacle data, specifically includes:

In another embodiment provided in this specification, the estimating, by the processing unit 602, an amount of resources to be consumed by using the projection model to plan a driving trajectory for the unmanned aerial vehicle by using a preset projection model cost function specifically includes:

In another embodiment provided in the present specification, the processing unit 602 determines, by using the selected projection model, projection coordinates of the obstacle projected in a road coordinate system corresponding to the driving road, and specifically includes:

In another embodiment provided by the present specification, the processing unit 602 selects a specific coordinate point from the determined projection curve as a projection coordinate of the obstacle in the road coordinate system, and specifically includes:

In another embodiment provided in the present specification, the processing unit 602 selects, from the determined projection curve, coordinate points that fall into a specified area and are continuously distributed as projection coordinates of the obstacle in the road coordinate system, and specifically includes:

In another embodiment provided in this specification, the planning unit 603 plans a driving path for the unmanned aerial vehicle according to the projection coordinates of each obstacle, specifically including:

It should be noted that the trajectory planning device provided in the embodiment of the present specification may be implemented in a hardware manner, or may be implemented in a software manner, where the implementation manner is not specifically limited. The trajectory planning equipment acquires the barrier data of barriers around the road where the unmanned equipment runs; aiming at different set projection models, determining a cost parameter corresponding to the projection model according to barrier data of the barrier, wherein the cost parameter is used for representing the difficulty of planning a driving track for the unmanned equipment by using the projection model; selecting a projection model used for the obstacle from different preset projection models according to the obtained cost parameters corresponding to the different projection models; determining projection coordinates of the obstacles projected in a road coordinate system corresponding to the driving road by using the selected projection model; and planning a driving track for the unmanned equipment according to the projection coordinates of the obstacles.

Therefore, when the driving track is planned for the unmanned equipment, the projection coordinate of the obstacle is not determined by singly adopting a closest point projection method, but a proper projection model is selected according to the difficulty of planning the driving track for the unmanned equipment, so that the overlarge distance between the determined projection coordinate and the position coordinate, corresponding to the actual position of the obstacle, in the road coordinate system due to the space distortion of the road coordinate system can be avoided, the planned driving track can be ensured to reasonably avoid the obstacle, the planning resource is saved, and the efficiency of planning the driving track for the unmanned equipment is improved.

The present specification also provides a computer readable storage medium having stored thereon a computer program, which when executed by a processor is operable to perform the trajectory planning method provided in fig. 1 above.

Based on the trajectory planning method shown in fig. 1, the embodiment of the present specification further provides a schematic structural diagram of the unmanned device shown in fig. 7. As shown in fig. 7, on the hardware level, the unmanned aerial vehicle is installed with a trajectory planning device, which includes a processor, an internal bus, a network interface, a memory, and a non-volatile memory, and may also include hardware required by other services. The processor reads a corresponding computer program from the non-volatile memory into the memory and then runs the computer program to implement the trajectory planning method described in fig. 1 above. The method comprises the steps of acquiring obstacle data of obstacles around a road where unmanned equipment runs; aiming at different set projection models, determining a cost parameter corresponding to the projection model according to barrier data of the barrier, wherein the cost parameter is used for representing the difficulty of planning a driving track for the unmanned equipment by using the projection model; selecting a projection model used for the obstacle from different preset projection models according to the obtained cost parameters corresponding to the different projection models; determining projection coordinates of the obstacles projected in a road coordinate system corresponding to the driving road by using the selected projection model; and planning a driving track for the unmanned equipment according to the projection coordinates of the obstacles.

Of course, besides the software implementation, the present specification does not exclude other implementations, such as logic devices or a combination of software and hardware, and the like, that is, the execution subject of the following processing flow is not limited to each logic unit, and may be hardware or logic devices.

In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the various elements may be implemented in the same one or more software and/or hardware implementations of the present description.

As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The description has been presented with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the description. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or Flash memory (Flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that 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 phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

This description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only an example of the present specification, and is not intended to limit the present specification. Various modifications and alterations to this description will become apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present specification should be included in the scope of the claims of the present specification.

Claims

1. A trajectory planning method, characterized in that the method comprises:

2. The method of claim 1, wherein determining a cost parameter corresponding to the projection model according to the obstacle data of the obstacle comprises:

3. The method of claim 2, wherein determining the amount of resources to be consumed for planning the driving trajectory for the unmanned aerial device using the projection model according to the spatial position of the obstacle in the driving road, the shape data of the obstacle, and the reference line position of the road coordinate system corresponding to the driving road, included in the obstacle data, comprises:

4. The method of claim 3, wherein estimating an amount of resources to be consumed for planning a travel path for the unmanned aerial device using the projection model using a predetermined projection model cost function comprises:

5. The method according to claim 1, wherein determining projection coordinates of the obstacle projected in a road coordinate system corresponding to the driving road using the selected projection model comprises:

6. The method of claim 5, wherein selecting a specific coordinate point from the determined projection curve as the projection coordinate of the obstacle in the road coordinate system comprises:

7. The method according to claim 1, wherein determining projection coordinates of the obstacle projected in a road coordinate system corresponding to the driving road using the selected projection model comprises:

8. The method according to claim 7, wherein selecting, from the determined projection curves, coordinate points that fall within a specified area and are continuously distributed as projection coordinates of the obstacle in the road coordinate system, specifically comprises:

9. The method of claim 1, wherein planning a travel path for the drone according to the projected coordinates of each obstacle, comprises:

10. A trajectory planning device, characterized in that,

11. A computer-readable storage medium, characterized in that the storage medium stores a computer program which, when being executed by a processor, implements the trajectory planning method according to any one of the preceding claims 1 to 9.

12. An unmanned aerial device comprising a memory, a processor and a computer program stored on the memory and running on the processor, wherein the processor when executing the program implements the trajectory planning method of any of claims 1 to 9.