DE102022123120A1 - METHOD AND DEVICE FOR MANEUVER PLANNING FOR AN AUTOMATED MOTOR VEHICLE - Google Patents

Abstract

A method for maneuver planning for an automated motor vehicle is provided. The method includes entering (S4) a planned first trajectory for a further motor vehicle (2) received by means of V2X communication on the motor vehicle (1) and a planned second trajectory for the further motor vehicle (2) determined by the motor vehicle (1). a maneuver planning module (3), and determining (S5) a trajectory planned by the further motor vehicle (2) based on the planned first trajectory received via V2X communication and the planned second trajectory determined by the motor vehicle (1) using the maneuver planning module (3 ).

Description

The present disclosure relates to a method for maneuver planning for an automated motor vehicle, a method for training a maneuver planning module for use in the method, and a data processing device configured to at least partially carry out the method. Furthermore, an automated motor vehicle with the data processing device is provided. Additionally or alternatively, a computer program is provided which includes commands which, when the program is executed by a computer, cause it to at least partially carry out the method. Additionally or alternatively, a computer-readable medium is provided which includes instructions which, when the instructions are executed by a computer, cause it to at least partially carry out the method.

The EP 3 457 382 A1 relates to a method for planning a collision avoidance maneuver that can be used in the scenarios of cooperative driving or autonomous driving. The method includes the steps of observing the surroundings of a vehicle, determining the risk of a collision if there is a risk of collision, and starting an information exchange phase for the vehicles involved. During the information exchange phase, a vehicle involved transmits its self-determined driving route to the vehicles involved. An evaluation phase begins in which a vehicle evaluates its own driving tubes and those received from the other vehicles involved. In addition, a common safe area is determined for the vehicles involved to approach in order to avoid the collision. This can be presented to the vehicles involved for checking against their own safety requirements. If the safety requirements are not met, the vehicle carries out a state change from the collision avoidance state to the collision minimization state and informs the other vehicles involved about the state change.

The US 2013/325306 A1 concerns distributed control of vehicles with coordinating vehicles that apply a cooperative control method and non-coordinating vehicles that are assumed to follow predictable dynamics. A cooperative control method can combine distributed, back-horizon control for optimization-based path planning and feedback with higher-level logic to ensure that implemented plans are collision-free. The cooperative method can be fully distributed and partially synchronous, providing time for communication and computation - characteristics required for implementation on real highways. The method can check for conflicts and calculate optimized trajectories by adjusting the parameters in the end-state constraints of an optimal control problem.

The DE 10 2018 216 082 A1 relates to a method for maneuver planning and execution of a vehicle by an in-vehicle control device, wherein the control device has a strategic planning level for carrying out route planning, a tactical planning level for providing precise trajectories to possible destination points and an operational planning level for selecting a destination point and a drivable trajectory selected target point, wherein the planning levels are executed in a cascade manner and when each planning level is executed, an exchange of information with neighboring vehicles is carried out via a communication link to determine collisions, with a maneuver coordination between the vehicles being carried out via the communication link in the event of a detected collision in at least one planning level.

Against the background of this prior art, the task of the present disclosure is to specify a device and a method, which are each suitable for enriching the prior art.

The task is solved by the features of the independent claim. The independent claims and the subclaims contain optional developments of the invention.

The task is then solved by a procedure for maneuver planning for an automated motor vehicle.

The method can be a computer-implemented method, i.e. one, several or all steps of the method can be carried out at least partially by a computer or a data processing device.

The method includes entering a planned first trajectory for a further motor vehicle, received by means of V2X communication on the motor vehicle, and a planned second trajectory for the further motor vehicle, determined by the motor vehicle, into a maneuver planning module.

V2X communication or Car2x can be understood as a data transmission technology in which (motor) vehicles communicate with their environment (“x”) and/or with each other. The data exchange between neighboring vehicles is a special case of Car2x and is called Car2Car or V2V communication. With Car2x, transmission can be possible in both directions, i.e. from the vehicle to the environment and vice versa. Car2x is intended to increase traffic safety, lead to energy savings and strengthen transport efficiency.

A trajectory can be understood as a path along which a motor vehicle moves or will move. In addition to location or position information, the trajectory can include a temporal component, i.e. when is the motor vehicle where or when will the motor vehicle be where.

A maneuver can be understood as a driving maneuver, i.e. a change and/or maintenance of a speed and/or a direction of travel.

The method includes determining a trajectory planned by the further motor vehicle based on the planned first trajectory received via V2X communication and the planned second trajectory determined by the motor vehicle using the maneuver planning module.

In other words, both the trajectories exchanged with V2X and internally predicted trajectories for other road users are taken into account in order to be able to make a more reliable maneuver selection based on this. Having both trajectories as inputs to a maneuver planner and a selector results in more redundancy and reliability compared to the traditional approaches.

Possible further developments of the above method are explained in detail below.

The method may include determining a target trajectory for the motor vehicle based on the planned trajectory of the further motor vehicle determined using the maneuver planning module. This can be done using the maneuver planning module.

The method can include controlling a longitudinal and/or transverse guidance of the motor vehicle so that the motor vehicle automatically follows the target trajectory.

The maneuver planning module can have an algorithm based on artificial intelligence for determining the planned trajectory of the further motor vehicle and/or for determining the trajectory of the motor vehicle. A machine learning algorithm is conceivable. The algorithm may include one or more artificial neural networks.

The method may include receiving the planned first trajectory for the further motor vehicle using V2X communication on the motor vehicle. Additionally or alternatively, the method may include determining the planned second trajectory based on sensor data detected by a sensor system of the motor vehicle.

The method described above offers a number of advantages since both inputs, i.e. the trajectory determined internally by the motor vehicle for another motor vehicle and the trajectory received from the further motor vehicle, are used by the maneuver planning module to make a decision. The maneuver planning module, which can also be referred to as the decision-making module, can therefore rely on one or both inputs or information sources (prediction and cooperation) to make an appropriate decision that ensures safety and comfort.

Furthermore, the disclosure relates to a method for training an artificial intelligence-based algorithm of a maneuver planning module for a motor vehicle, which can also be referred to as a training method. The algorithm is designed to determine a trajectory planned by a further motor vehicle based on a planned first trajectory for the further motor vehicle received via V2X communication and a planned second trajectory for the further motor vehicle determined by the motor vehicle. The method is characterized in that the training is carried out using a training data set which comprises a plurality of planned first trajectories for the further motor vehicle and associated several planned second trajectories for the further motor vehicle.

In other words, the proposed machine learning model can be trained with both inputs to be used in the method described above.

What was described above with reference to the maneuver planning procedure also applies analogously to the training procedure and vice versa.

Furthermore, a computer program comprising instructions which, when the program is executed by a computer, causes it to carry out at least one of the methods described above to be carried out or carried out at least partially.

A program code of the computer program can be in any code, in particular in a code that is suitable for motor vehicle controls.

What has been described above with reference to the procedures also applies analogously to the computer program and vice versa.

Furthermore, a data processing device, for example a control device, is provided for an automated motor vehicle, wherein the data processing device or the control device is set up to at least partially implement or carry out at least one of the methods described above.

The data processing device can be part of or represent a driving assistance system. The data processing device can be, for example, an electronic control unit (ECU = electronic control unit). The electronic control unit can be an intelligent processor-controlled unit that can communicate with other modules, for example via a central gateway (CGW) and, if necessary, via field buses such as the CAN bus, LIN bus, MOST bus and FlexRay or via automotive Ethernet, for example together with telematics control devices and/or environmental sensors, can form the vehicle on-board network. It is conceivable that the control unit controls functions relevant to the driving behavior of the motor vehicle, such as the engine control, the power transmission, the braking system and/or the tire pressure monitoring system. In addition, driver assistance systems, such as a parking assistant, an adapted cruise control (ACC), a lane keeping assistant, a lane change assistant, traffic sign recognition, light signal recognition, a starting assistant, a night vision assistant and/or an intersection assistant, can be controlled by the control unit .

What has been described above with reference to the methods and the computer program also applies analogously to the data processing device and vice versa.

Furthermore, a motor vehicle comprising the data processing device described above is provided.

The motor vehicle can be a passenger car, in particular an automobile, a motorized two- or three-wheeler, or a commercial vehicle, such as a truck.

The motor vehicle can be automated. The motor vehicle can be designed to at least partially and/or at least temporarily take over longitudinal guidance and/or transverse guidance during automated driving of the motor vehicle.

Automated driving can be carried out in such a way that the movement of the motor vehicle is (largely) autonomous. The automated driving can be controlled at least partially and/or temporarily by the data processing device.

The motor vehicle can be a motor vehicle with autonomy level 1, i.e. have certain driver assistance systems that support the driver in operating the vehicle, such as adaptive cruise control (ACC).

The motor vehicle can be a motor vehicle with autonomy level 2, i.e. be partially automated so that functions such as automatic parking, lane keeping or lateral guidance, general longitudinal guidance (especially starting off), acceleration and/or braking can be taken over by driver assistance systems.

The motor vehicle can be a motor vehicle of autonomy level 3, i.e. conditionally automated so that the driver does not have to continuously monitor the vehicle system. The motor vehicle independently carries out functions such as triggering the turn signal, changing lanes and/or keeping in lane. The driver can turn his attention to other things, but if necessary the system will ask him to take over within a warning period.

The motor vehicle can be a motor vehicle with autonomy level 4, i.e. so highly automated that control of the vehicle is permanently taken over by the vehicle system. If the system can no longer handle the driving tasks, the driver can be asked to take over the lead.

The motor vehicle can be a motor vehicle with autonomy level 5, i.e. so fully automated that the driver is not required to fulfill the driving task. No human intervention is required other than setting the target and starting the system. The motor vehicle can do without a steering wheel and pedals.

What has been described above with reference to the method, the data processing device and the computer program also applies analogously to the motor vehicle and vice versa.

Furthermore, a computer-readable medium, in particular a computer-readable storage medium, is provided. The computer-readable medium includes instructions that, when executed by a computer, cause the computer to at least partially carry out the method described above.

That is, a computer-readable medium may be provided that includes a computer program as defined above. The computer-readable medium can be any digital data storage device, such as a USB flash drive, hard drive, CD-ROM, SD card, or SSD card.

The computer program does not necessarily have to be stored on such a computer-readable storage medium in order to be made available to the motor vehicle, but can also be obtained externally via the Internet or otherwise.

What has been described above with reference to the method, the data processing device, the computer program and the motor vehicle also applies analogously to the computer-readable medium and vice versa.

• 1 zeigt schematisch ein Ablaufdiagramm des Verfahrens zur Manöverplanung mit vorgelagertem Verfahren zum Trainieren eines Algorithmus, der in dem Verfahren zur Manöverplanung verwendet wird, und
• 2 zeigt schematisch ein das Verfahren zur Manöverplanung ausführendes Kraftfahrzeug.

An embodiment is described below with reference to 1 described.

• 1 schematically shows a flowchart of the maneuver planning method with an upstream method for training an algorithm that is used in the maneuver planning method, and
• 2 shows schematically a motor vehicle carrying out the maneuver planning procedure.

How out 1 results, the procedure for maneuver planning has five steps S2 - S7 with an upstream step S1, in which an artificial intelligence-based algorithm used in the procedure for maneuver planning is trained.

In the first step S1, the algorithm is trained using a training data set, which includes several planned first trajectories for another motor vehicle received via V2X communication and several corresponding planned second trajectories for the further motor vehicle, each determined by a motor vehicle. It is conceivable that supervised learning could be used. Supervised learning is a branch of machine learning. Learning refers to the ability of an artificial intelligence to reproduce regularities. The results are known through natural laws or expert knowledge and are used to train the system. A learning algorithm can be used that finds a hypothesis that makes predictions that are as accurate as possible. Hypothesis is a mapping that assigns the assumed output value to each input value. After the first step S1, the algorithm is suitable for determining a trajectory planned by a further motor vehicle based on a planned first trajectory for the further motor vehicle received via V2X communication and a planned second trajectory for the further motor vehicle determined by the motor vehicle. Furthermore, the algorithm is suitable for determining a target trajectory for a motor vehicle based on the planned trajectory of the other motor vehicle determined by the maneuver planning module. This will also be discussed in detail below with reference to 2 described.

In the in 2 In the driving situation shown in the bird's eye view, the automated motor vehicle 1 is in a drive-on lane 4 and another motor vehicle 2 is located to the side of the motor vehicle 1 in a lane 5 to which the motor vehicle 1 is to change. In order to determine how, ie when and where, the lane change should take place, the motor vehicle 1 includes a maneuver planning module 3 comprising the algorithm trained in step S1 described above and carries out the procedure for maneuver planning for an automated motor vehicle described in detail below.

In a first step S2 of the method, the motor vehicle 1 receives a planned first trajectory for the further motor vehicle 2 from the further motor vehicle 2 by means of V2X communication.

In a second step S3 of the method, the motor vehicle 2 determines a planned second trajectory for the further motor vehicle based on sensor data detected by a sensor system 6 of the motor vehicle 1.

In a third step S4, the planned first trajectory for the further motor vehicle 2 received by means of V2X communication on the motor vehicle 1 and the planned second trajectory for the further motor vehicle 2 determined by the motor vehicle 1 are entered into the maneuver planning module 3.

In a fourth step S5, a trajectory planned by the further motor vehicle 2 is determined based on the planned first trajectory received by means of V2X communication and that determined by the motor vehicle 1 th planned second trajectory using the maneuver planning module 3.

In a fifth step S6, a target trajectory for the motor vehicle 1 is determined based on the planned trajectory of the further motor vehicle 2 determined by means of the maneuver planning module 3 in the fourth step S5. These two steps S5, S6 are not separate Steps should be considered in the sense that after the fourth step S5 there is an intermediate product which is then further processed in the fifth step S6. Rather, the maneuver planning module 3 can determine the target trajectory of the motor vehicle 1 directly from the two input trajectories, without the planned trajectory of the other motor vehicle 2 being explicitly determined.

In concrete terms, this can mean in the present case that the first and second planned trajectories for the other motor vehicle 2 are evaluated by the maneuver planning module 3 in order to decide which maneuver is best suited for the motor vehicle 1, i.e., for example, keep in the approach lane, wait until that the rear or other motor vehicle has passed and then change, or to cut in front of the other motor vehicle 2.

In a sixth step S7, a longitudinal and/or transverse guidance of the motor vehicle 1 is controlled, so that the motor vehicle 1 automatically follows the target trajectory. This can be done by the maneuver planning module 3 or by another control unit of the motor vehicle 1 that is set up for this purpose.

Reference symbol list

1

automated motor vehicle

2

another motor vehicle

3

Maneuver planning module

4

access lane

5

lane

6

Sensor system

S1 - S7

Procedural steps

QUOTES INCLUDED IN THE DESCRIPTION

This list of documents listed by the applicant was generated automatically and is included solely for the better information of the reader. The list is not part of the German patent or utility model application. The DPMA assumes no liability for any errors or omissions.

Cited patent literature

• EP 3457382 A1 [0002]
• US 2013325306 A1 [0003]
• DE 102018216082 A1 [0004]

Claims (10)

Method for maneuver planning for an automated motor vehicle (1), characterized in that the method comprises: - Entering (S4) a planned first trajectory for another motor vehicle (2) received via V2X communication on the motor vehicle (1) and one of the Motor vehicle (1) determined planned second trajectory for the further motor vehicle (2) in a maneuver planning module (3), and - determining (S5) a trajectory planned by the further motor vehicle (2) based on the planned first trajectory received via V2X communication and the planned second trajectory determined by the motor vehicle (1) using the maneuver planning module (3). Procedure according to Claim 1 , characterized in that the method includes determining (S6) a target trajectory for the motor vehicle (1) based on the planned trajectory of the further motor vehicle (2) determined by the maneuver planning module (3). Procedure according to Claim 2 , characterized in that the method includes controlling (S7) a longitudinal and/or transverse guidance of the motor vehicle (1), so that the motor vehicle (1) automatically follows the target trajectory. Procedure according to one of the Claims 1 until 3 , characterized in that the maneuver planning module (3) for determining the planned trajectory of the other motor vehicle (2) and, as far as Claim 2 related back, for determining the trajectory of the motor vehicle (1) has an algorithm based on artificial intelligence. Procedure according to one of the Claims 1 until 4 , characterized in that the method comprises: - receiving (S2) the planned first trajectory for the further motor vehicle (2) by means of V2X communication on the motor vehicle (1), and / or - determining (S3) the planned second trajectory based on sensor data detected by a sensor system (6) of the motor vehicle (1). Method for training (S1) an algorithm based on artificial intelligence of a maneuver planning module (3) for a motor vehicle (1), which is designed to implement a trajectory planned by another motor vehicle (2) based on a planned first trajectory received via V2X communication for the further motor vehicle (2) and a planned second trajectory for the further motor vehicle (2) determined by the motor vehicle (1), characterized in that the training is carried out using a training data set which contains several planned first trajectories for the further motor vehicle ( 2) and each associated several planned second trajectories for the further motor vehicle (2). Data processing device (3) for a motor vehicle (1), characterized in that the data processing device (3) is designed to carry out the method according to one of Claims 1 until 6 to carry out. Motor vehicle (1), characterized in that the motor vehicle uses the data processing device Claim 7 includes. Computer program, characterized in that the computer program comprises commands which, when the program is executed by a computer, cause it to carry out the method according to one of the Claims 1 until 6 to carry out. Computer-readable medium, characterized in that the computer-readable medium comprises instructions which, when the instructions are executed by a computer, cause it to carry out the method according to one of the Claims 1 until 6 to carry out.

Images