Motor vehicle and method for motion planning of an autonomous motor vehicle for a parking maneuver

Abstract

The invention relates to a motor vehicle and a method for motion planning of an autonomous motor vehicle (10) for a parking maneuver. The method comprises determining (S1) an initial state and environment of the motor vehicle (10) by a sensor device (12); determining (S2) configuration samples (20, 20', 20") in a configuration space (18) by a computing device (14), wherein the configuration space (18) represents the environment of the motor vehicle (10) and the configuration samples (20, 20', 20") comprise possible positions with a respective corresponding state of the motor vehicle (10), wherein respective sequences of configuration samples (20, 20', 20") define paths (22, 22'), wherein the configuration samples (20, 20', 20") are limited depending on a motion model; an evaluation (S3) of the paths (22, 22') depending on a path criterion;a selection (S4) of a path (22') based on the evaluation, wherein a movement trajectory to the parking position is generated from the selected path (22') (S5); and a provision (S6) of the movement trajectory to a control device (16).;

Description

[0001] The invention relates to a method for planning the motion of an autonomous motor vehicle for a parking maneuver. Furthermore, the invention relates to a motor vehicle configured to perform the method.

[0002] In autonomous vehicles, parking maneuvers are often optimized only for specific use cases or are very computationally intensive. Therefore, complete spatial coverage of all possible parking maneuvers for any situation is often unattainable, and / or methods for planning the movement of a parking process are not suitable for real-time operation due to their computational intensity.

[0003] From US 9 969 386 B1, a method and a system for automated parking are known, wherein, using a geometry of the vehicle and a map of a parking space, a collision-free geometric path is determined that connects an initial state of the vehicle with a target state of the parked vehicle via a set of waypoints.

[0004] An automatic parking method is known from EP 3 971 047 A1. The method comprises determining node distribution information for an area to be parked during automatic parking, wherein the node distribution information contains a plurality of nodes through which a vehicle can pass; determining an intermediate node based on the node distribution information; obtaining a plurality of neighbor nodes by searching for neighbor nodes based on the intermediate node; determining cost information of candidate routes, each corresponding to the plurality of neighbor nodes, wherein the candidate routes are each a route from a starting node to the intermediate nodes via a neighbor node; and determining a destination neighbor node based on the cost information.

[0005] The object of the invention is to improve motion planning for a parking maneuver.

[0006] This problem is solved by the independent patent claims. Advantageous developments are disclosed in the dependent patent claims, the following description, and the figures.

[0007] The invention is based on the idea that a sample-based algorithm is used for motion planning, whereby a motion model of the motor vehicle is provided for this purpose, which limits the generation of sample values ​​only to movements that are possible starting from an initial orientation of the motor vehicle.

[0008] One aspect of the invention relates to a method for motion planning of an autonomous motor vehicle for a parking maneuver. The method comprises, as steps: determining an initial state of the motor vehicle and its environment, which includes a predetermined parking position, by a sensor device of the motor vehicle; determining configuration samples in a configuration space by a computing device of the motor vehicle, wherein the configuration samples are generated as a function of a motion model of the motor vehicle and thus impermissible movements of the motor vehicle are excluded; wherein the configuration samples are determined using a sampling-based algorithm in predefined sampling steps, wherein in each sampling step a plurality of configuration samples are determined in parallel using at least one graphics processing unit of the computing device.wherein the configuration samples generated in a sampling step are based on the state and position of the configuration samples of the preceding sampling step, wherein the configuration space represents the environment of the motor vehicle and the configuration samples comprise possible positions of the motor vehicle with a respective corresponding state of the motor vehicle, wherein respective sequences of configuration samples define possible paths of the motor vehicle through the configuration space to the parking position.

[0009] Furthermore, the method comprises evaluating the possible paths of the vehicle by the computing device depending on a path criterion, selecting a path from the possible paths to the parking position based on the evaluation by the computing device, generating a motion trajectory of the vehicle, including a speed profile of the vehicle, to the parking position from the selected path, and providing the motion trajectory to a control unit of the vehicle for moving the autonomous vehicle to the parking position. Preferably, the vehicle can then be controlled to the parking position by the control unit using the provided motion trajectory.

[0010] In other words, a vehicle's sensor system first acquires sensor data that describes the vehicle's environment and its initial state. The vehicle's environment can include, for example, static objects such as lane markings and / or other vehicles, dynamic objects such as moving vehicles and / or pedestrians, and a parking position, which may be predetermined or predefined. The vehicle's initial state can include, for example, its orientation within the environment, its steering angle, and / or its speed. The sensor system can include, in particular, steering angle sensors, speed sensors, GPS sensors, radar sensors, laser sensors (especially LiDAR sensors), ultrasonic sensors, and / or camera sensors.

[0011] From the acquired sensor data, a vehicle's computing unit, such as the vehicle's computer, can then generate a configuration space that virtually represents the vehicle's surroundings. This space allows for the determination of possible positions of the vehicle relative to its parking position, along with their corresponding states represented as configuration samples. These configuration samples can encompass the respective positions within the configuration space and the corresponding configuration or state of the vehicle. Specifically, the state includes the steering angles required at each position.For this purpose, a sampling-based algorithm can be used, which does not generate complete trajectories through space, but rather individual movement points in space, based in particular on the preceding sampling points, i.e., the previous states and positions of the vehicle. This generation of configuration samples is preferably carried out by means of a graphics processing unit, in particular one or more graphics processing units (GPUs), which enables massively parallel generation of the configuration samples. Thus, a multitude of possible movements through the configuration space can be determined. In particular, this allows for improved determination of the parking process for a wide variety of situations.Preferably, several sampling steps can be performed, whereby for each configuration sample value, subsequent configuration samples can be determined depending on the previously determined state of the motor vehicle and its position. For example, such a sampling-based method with a configuration space and configuration samples is known from WO 2022 / 268323 A1.

[0012] To limit the computational effort of the sampling algorithm and provide improved motion planning, configuration samples can be generated using a motion model of the vehicle, thus limiting the number of configuration samples in the configuration space. Specifically, only permissible vehicle movements can be defined and allowed within the motion model, preventing the generation or consideration of configuration samples that contradict the motion model. In particular, this ensures that only configuration samples achievable through steering movements of the vehicle are generated, thereby excluding, for example, lateral movements.The motion model can use the preceding state and position as input and thus determine the configuration sample values ​​based on it in the subsequent sampling step.

[0013] Each sequence of configuration samples represents a possible geometric path of the vehicle through the configuration space, specifically to its parking position. Here, "geometric path" refers to the spatial distance to the parking position, which does not yet include a speed profile. However, the individual configuration samples can contain speed information, which is needed, for example, to move from one configuration sample to the next, such as when steering is required while the vehicle is stationary.

[0014] After all possible paths of the vehicle have been determined in a given sampling step, the paths can be evaluated based on a path criterion. This path criterion can be, for example, a condition and / or requirement that the respective path should or must fulfill. For instance, the paths can be evaluated based on a distance traveled, a number of required steering movements or changes of direction, and / or a maintained distance to static and / or dynamic objects. Paths that do not meet the path criterion can preferably be truncated or not followed further. It is particularly preferred that the configuration sampling values ​​are determined and the resulting paths are subsequently evaluated in each sampling step, with the best-rated paths being iteratively pursued.This can be done until the paths lead to the parking position.

[0015] Once the possible paths to the parking position have been determined, one path can be selected from all possible paths based on an evaluation, preferably the highest-rated path. This can be determined in particular using a loss function (or cost function).

[0016] Once the path, which simply comprises the vehicle's route and its associated state (especially steering angle) to the parking position, has been selected, a motion trajectory can be created using a velocity profile. In other words, the motion trajectory represents the geometric path through space, including the corresponding velocity at each position along the path. This motion trajectory can then be provided to a vehicle control system designed to autonomously steer the vehicle into the parking position.

[0017] The invention offers the advantage that, for general parking operations without a predefined scenario, a motion plan to the parking position can be provided quickly and in real time, thereby improving the parking process for autonomous vehicles.

[0018] The invention also includes further developments that result in additional advantages.

[0019] A further development stipulates that the respective state of the vehicle includes at least its orientation within its surroundings and a steering angle. The motion model does not generate configuration samples that are excluded by the vehicle's orientation and steering angle. However, multiple movements in forward and reverse directions, changes of direction at any point in the environment, and even steering angle changes while the vehicle is stationary can be taken into account. In particular, this prevents the generation of multiple successive configuration samples that would provide paths that are not feasible due to the vehicle's orientation and current steering angle.The configuration samples encompassing the state can build upon one another, particularly in several successive sampling steps, thereby determining which configuration samples are possible based on the preceding configuration sample. Thus, each preceding state forms the basis for a new exploration. The first state is the initial, determined state of the vehicle, and the subsequent states are determined by the configuration samples. Preferably, each configuration sample and / or state can also include a possible speed of the vehicle, a distance or position relative to previous configuration samples, and / or a steering angle rate or steering angle change rate, which can be used to determine whether a deceleration and / or a change of direction of the vehicle's movement is necessary.For example, this can determine whether steering while the vehicle is stationary is necessary for the generation of subsequent configuration samples by the motion model. This further development offers the advantage of saving computing resources, which contributes to improved real-time capability.

[0020] A further development proposes that the motion model be a single-track model. The single-track model provides a model of a motor vehicle for lateral dynamics, which can be used to describe the vehicle's movements. This allows for a preferred design of a motion model.

[0021] Preferably, the single-track model incorporates front axle control of the motor vehicle in a forward and / or reverse direction. This means that movements of the motor vehicle, whose front axle is movable, are permitted for the provision of configuration sample values, and thus forward and / or reverse movements can be determined using the single-track model.

[0022] A further advantageous improvement involves incorporating rear axle control into the single-track model in addition to front axle control. This means that the single-track model can account for the movement of both the front and rear axles. Preferably, the single-track model can simulate both forward and reverse movements. This allows for the consideration and limitation of other movements of appropriately equipped motor vehicles.

[0023] A further development involves a vehicle with a trailer, where the motion model does not generate configuration samples if the yaw angle between the vehicle and the trailer exceeds a threshold. The yaw angle can be defined, in particular, as the angle between the longitudinal axis of the vehicle and the longitudinal axis of the trailer. For example, if the longitudinal axes of the vehicle and the trailer are aligned, the yaw angle may be zero, and its magnitude may increase during steering maneuvers of the vehicle. If the yaw angle becomes too large and exceeds a threshold, indicating that the vehicle and trailer are tilting, this movement can be prevented by the motion model.The threshold can be predefined, particularly depending on the vehicle, the coupling used for the trailer, and the trailer itself. This further development offers the advantage that parking maneuvers for vehicles with trailers can also be planned and executed.

[0024] Further training stipulates that the evaluation of potential paths using the path criterion is based on the distance of the respective path to objects in the surroundings, and / or on the number of steering maneuvers required on the respective path, and / or on the number of required changes of direction, and / or on the length of the respective path, and / or on the number of steering maneuvers while the vehicle is stationary. In other words, paths with a large distance to objects in the surroundings may be rated higher than paths with a small distance. Alternatively or additionally, paths requiring many steering maneuvers may be rated lower than paths requiring few steering maneuvers, and / or a short path length may be rated higher than a long path length.Alternatively or additionally, an increasing number of required changes of direction and / or an increasing number of steering maneuvers while the vehicle is stationary can negatively affect the rating. This means that paths with a high number of changes of direction and / or steering maneuvers while stationary are rated lower than those with a low number. The advantage of this is that a trajectory is only created for the best-rated path, thus improving the parking process.

[0025] A further development proposes that for configuration samples generated in successive sampling steps and lying on the same path, intermediate values ​​are determined using the motion model. From these intermediate values, further configuration samples, and thus paths, are generated. In other words, intermediate values ​​can be created on the path between two adjacent configuration samples, which can serve as starting points for further configuration samples. These intermediate values ​​can have their own positions and states in the configuration space. In particular, these intermediate values ​​can be derived from the motion model, since the initial state, the final state, and the motion of the vehicle provided by the motion model are known.For example, the motion model can reveal the curvature and / or distance of the path between two adjacent configuration samples, allowing intermediate values ​​to be determined at each position along the path. Since these intermediate values ​​are not freely generated in the configuration space but are based on the path and the respective states between the adjacent configuration samples, they are preferably not considered classical configuration samples.

[0026] Furthermore, determining these intermediate values ​​is easier and less computationally intensive, since the target configuration sample value of the path has already been determined as a permissible movement, and thus the intermediate values ​​along the path also represent permissible movements of the vehicle. A distance between the respective intermediate values ​​can be specified, which is particularly advantageous. For example, the distance can be equidistant or increase or decrease exponentially. This refinement offers the advantage that further paths with different lengths can be generated between two adjacent configuration samples, and the entire configuration space can be covered with all possible movements. This allows for the rapid finding of an alternative route to the parking position, especially if the environment changes.

[0027] A further development provides that, if the sensor system detects a change in the environment, the method generates a new motion trajectory. This new trajectory is then evaluated against the previous one and is only used if a switching condition is met. This means that the method can initially create a motion trajectory used to guide the vehicle to the parking position. However, the environment can change during this process, for example, due to dynamic objects, which the sensor system can detect.Preferably, an updated motion trajectory can then be determined again using the motion planning method, whereby the new motion trajectory can then be compared with the previously valid motion trajectory to decide whether the new or the previously valid motion trajectory should be used. In particular, it can be provided that the new motion trajectory is only used if a switching condition exists, for example, because the previously valid motion trajectory is no longer possible due to the changed environment, as it is blocked by an object. This offers the advantage that it is possible to react quickly to changes in the environment.

[0028] Another aspect of the invention relates to a motor vehicle comprising a sensor device, a computing device, and a control device. The control device is configured to determine an initial state of the motor vehicle and its environment, which includes a predetermined parking position. The computing device is configured to determine configuration samples in a configuration space and to generate these configuration samples based on a motion model of the motor vehicle, thereby preventing impermissible movements of the motor vehicle. The configuration space represents the environment of the motor vehicle, and the configuration samples comprise possible positions of the motor vehicle with a corresponding state. The computing device includes at least one graphics processing unit and a sampling-based algorithm configured to...to determine the configuration samples in predefined sampling steps and to determine a plurality of configuration samples in parallel in each sampling step using the at least one graphics processing unit, wherein the configuration samples generated in a sampling step are based on the state and position of the preceding sampling step, wherein respective sequences of configuration samples define possible paths of the motor vehicle, in particular to the parking position, wherein the computing device is further configured to evaluate the possible paths of the motor vehicle depending on a path criterion, to select a path from the possible paths to the parking position based on the evaluation, and to generate a motion trajectory of the motor vehicle from the selected path, comprising a speed profile of the motor vehicle.to generate the parking position and provide the motion trajectory to the control unit. The control unit is designed to autonomously steer the vehicle into the parking position based on the provided motion trajectory. In other words, the vehicle is designed to perform the aforementioned procedure. This offers the same advantages and variations as the previous procedure.

[0029] For use cases or application situations that may arise during the method and which are not explicitly described here, it may be provided that, in accordance with the method, an error message and / or a request to enter user feedback is issued and / or a default setting and / or a predetermined initial state is set.

[0030] The invention also includes the control device for the motor vehicle. The control device can comprise a data processing device or a processor unit configured to carry out an embodiment of the method according to the invention. For this purpose, the processor unit can comprise at least one microprocessor and / or at least one microcontroller and / or at least one FPGA (Field Programmable Gate Array) and / or at least one DSP (Digital Signal Processor). Furthermore, the processor unit can comprise program code configured to carry out the embodiment of the method according to the invention when executed by the processor unit. The program code can be stored in a data memory of the processor unit. The processor unit can, for example, be based on at least one circuit board and / or on at least one SoC (System on Chip).

[0031] The invention also includes further developments of the motor vehicle according to the invention, which have features already described in connection with the further developments of the method according to the invention. For this reason, the corresponding further developments of the motor vehicle according to the invention are not described again here.

[0032] The motor vehicle according to the invention is preferably designed as a motor vehicle, in particular as a passenger car or truck, or as a passenger bus or motorcycle.

[0033] As a further solution, the invention also includes a computer-readable storage medium comprising program code which, when executed by a computer or a computer network, causes it to execute an embodiment of the method according to the invention. The storage medium can be provided at least partially as a non-volatile data storage medium (e.g., as flash memory and / or as an SSD - solid state drive) and / or at least partially as a volatile data storage medium (e.g., as RAM - random access memory). The storage medium can be located within the computer or computer network. However, the storage medium can also be operated, for example, as an app store server and / or cloud server on the internet. The computer or computer network can provide a processor circuit with, for example, at least one microprocessor.The program code can be provided as binary code and / or as assembly code and / or as source code of a programming language (e.g. C) and / or as a program script (e.g. Python).

[0034] The invention also includes combinations of the features of the described embodiments. The invention therefore also includes realizations that each exhibit a combination of the features of several of the described embodiments, provided that the embodiments have not been described as mutually exclusive.

[0035] The following are exemplary embodiments of the invention described. This is illustrated by: Fig. 1 a schematically represented motor vehicle according to an exemplary embodiment; Fig. 2 a schematic process diagram according to an exemplary embodiment; Fig. 3 a configuration space with configuration sample values ​​for an exemplary motion planning; Fig. 4 An exemplary representation of the generation of configuration sample values ​​using the motion model.

[0036] The exemplary embodiments described below are preferred embodiments of the invention. In these exemplary embodiments, the described components each represent individual features of the invention, which can be considered independently of one another and each further develops the invention independently. Therefore, the disclosure is intended to include combinations of features of the embodiments other than those shown. Furthermore, the described embodiments can also be supplemented by further features of the invention already described.

[0037] In the figures, identical reference symbols denote functionally equivalent elements.

[0038] In Fig. Figure 1 shows a schematic representation of a motor vehicle 10, which may, for example, be designed as a car. The motor vehicle 10 can be an autonomous vehicle that is designed to perform motion planning for a parking maneuver and to drive autonomously into a parking position based on this motion plan. For this purpose, the motor vehicle 10 may have a sensor device 12, a computing device 14, and a control device 16.

[0039] The sensor device 12 can comprise one or more sensors capable of acquiring data from the environment of the motor vehicle 10 and / or data from the motor vehicle 10 itself. For example, the sensor device 12 can comprise optical sensors, in particular camera sensors and / or laser sensors, radar sensors and / or ultrasonic sensors, with which the environment of the motor vehicle can be recorded. Furthermore, the sensor device 12 can comprise sensors capable of determining the current steering angle, speed and / or orientation of the motor vehicle 10 in its environment.

[0040] The computing unit 14 and the control unit 16 can be provided as the vehicle computer of the motor vehicle 10, either as a unit in a common device or as separate devices. The computing unit 14 can be configured at least to perform motion planning to a predetermined parking position in the environment of the motor vehicle 10 as determined by the sensor device 12. The motion planning can be based on a sampling-based algorithm in which a plurality of samples can be determined which, as a sequence, together form a geometric path to the predetermined parking position. In particular, the computing unit 14 can include a graphics processing unit (not shown) that enables fast parallel processing of multiple samples.

[0041] The control unit 16 can be configured to control the motor vehicle 10 by means of the motion planning provided by the computer unit 14, in particular by means of a provided motion trajectory, such that the motor vehicle 10 autonomously drives into the parking position. In this process, several steering maneuvers with changes of direction, including small and large steering inputs, as well as steering inputs while the motor vehicle 10 is stationary, can be taken into account by the motion trajectory.

[0042] In Fig. Figure 2 shows a schematic process diagram for the motion planning of an autonomous motor vehicle 10 for a parking operation according to an exemplary embodiment, wherein the motion planning can be carried out by means of the sensor device 12, the computing device 14 and the control device 16.

[0043] In step S1, the sensor device 12 of the vehicle 10 can determine an initial state of the vehicle 10 and its environment, which includes a predetermined parking position. The environment can include static and dynamic objects in the vicinity of the vehicle 10. The initial state can provide an initial configuration or starting state of the vehicle 10 from which the motion planning is carried out. For example, the initial state can include a current speed, a current steering angle, and / or a current orientation in space or the environment.

[0044] In step S2, a virtual configuration space 18, representing the environment of the motor vehicle 10, can be generated by the computing unit 14 from the environment determined by the sensor device 12. Such a configuration space 18 is shown in an exemplary and highly schematic form in Fig. Figure 3 illustrates this. The computing device 14 can then calculate configuration samples 20, 20', 20" in the configuration space 18 using a sampling-based algorithm, preferably using at least one graphics processing unit. These configuration samples comprise possible positions of the motor vehicle 10 with a corresponding state of the motor vehicle 10. The configuration samples 20, 20', 20" (samples) have as their state at least one steering angle required for the position and an orientation of the motor vehicle at that position. In particular, the configuration samples 20, 20', 20" can be generated in several successive sampling steps.For example, in a first sampling step, the configuration samples 20 can be determined, in a subsequent second step the configuration samples 20', which build on the first configuration samples 20, in particular on the state provided in the configuration samples 20, and similarly in a third sampling step further configuration samples 20". Here, the number of sampling steps is only shown as an example and a large number of further sampling steps can be carried out up to a final sampling step in which the vehicle 10 is in a parked position.

[0045] To limit the number of configuration samples in each sampling step and thus provide real-time capability for motion planning, it can further be provided that the generation of configuration samples 20, 20', 20" in configuration space 18 is carried out by a motion model, thereby excluding impermissible movements of the vehicle. In particular, the motion model can be configured so that positions and / or states of the vehicle 10 are not generated in configuration space 18 for which movement of the vehicle is excluded, while all other possible movements of the vehicle are generated, preferably also assuming a steering movement while the vehicle is stationary.

[0046] The generation of the configuration sample values ​​20, 20' using the motion model is exemplified by the following: Fig.Figure 4 illustrates this. It shows configuration sample values ​​20' that can be provided based on the configuration sample value 20 generated in a previous sampling step. The number of possible configuration sample values ​​20' is shown only as an example and is limited for clarity. The motion model can generate all possible movements of the vehicle 10 starting from the configuration sample value 20. The direction d represents the possible distance at which the configuration sample values ​​20' can be reached from the configuration sample value 20. Here, direction d is shown as a forward direction, but corresponding movements can also be provided in the reverse direction.In this example, at configuration sample value 20, a previous steering angle and orientation state can exist, allowing the upper two configuration sample values ​​20' to be reached after a short distance, as only minor adjustments to the steering angle and thus the orientation may be necessary to achieve these configuration sample values ​​20'. In contrast, reaching the lower two configuration sample values ​​20' may require, for example, significant steering angle changes, necessitating a longer distance to be covered for the steering angle change to be effective.In addition, the motion model can also be used to plan a steering angle change while the vehicle 10 is stationary, which changes the initial steering angle at configuration sampling value 20 and thus makes the lowest configuration sampling value 20', which is represented by a dashed line, achievable.

[0047] After generating the configuration samples 20', intermediate values ​​21 can preferably also be determined, which lie on the path 22 between the successive configuration samples 20, 20'. These intermediate values ​​21 can be determined, in particular, by means of the movement known from the motion model to reach the configuration sample 20', whereby further configuration samples can be generated from these intermediate values ​​in order to determine further movements in the configuration space 18.

[0048] A single-track model can be used as a particularly preferred motion model, through which steering angle inputs and the resulting movement and orientation of the motor vehicle 10 in space can be determined in a simple way.

[0049] In the single-track model, it is preferably possible to assume front axle control of the vehicle 10 and to consider movements in forward and / or reverse directions. This allows, for example, the planning of multiple trains with changes of direction at any point. Additionally, the single-track model can include rear axle control alongside the front axle control, enabling further movements and thus additional configuration sample values ​​20, 20', 20". Alternatively or additionally, the use of a trailer (not shown) can be planned for generating configuration sample values ​​20, 20', 20" in configuration space 18, whereby configuration sample values ​​20, 20', 20" can be excluded where the vehicle 10 might be wedged against the trailer.For this purpose, for example, a yaw angle, which may be provided between a longitudinal axis of the motor vehicle 10 and a longitudinal axis of the trailer, can be checked to see if it lies outside a specified range, whereby no configuration sample values ​​are generated for yaw angles that lie outside the specified range.

[0050] From sequences of the generated configuration sample values ​​20, 20', 20" geometric paths 22, 22' of the motor vehicle 10 can be determined, which preferably lead to the parking position after the last sampling step.

[0051] In step S3, the possible paths 22, 22' can be evaluated based on a path criterion. This criterion evaluates the possible paths 22, 22' based on their distance to objects in the environment, the number of steering maneuvers required on each path, the number of required changes of direction, the path length, the path duration, and / or steering maneuvers while the vehicle is stationary. Preferably, only collision-free paths are considered, while paths with a collision are excluded and cannot be pursued further. Thus, the evaluation can be performed iteratively after each sampling step, and paths can be excluded if necessary, until the paths leading to the parking position are selected in a final sampling step.

[0052] In step S4, one of the evaluated paths 22, 22' to the parking position can be selected, in particular the best-evaluated path 22', for which a speed profile can be determined in step S5. Thus, a motion trajectory of the motor vehicle 10 to the parking position can be generated from the geometric path.

[0053] In step S6, the generated motion trajectory can then be provided by the computing unit 14 to the control unit 16 in order to autonomously steer the vehicle 10 into the parking position. This means that the control unit 16 can autonomously drive the vehicle 10 into the parking position using the provided motion trajectory.

[0054] Preferably, in step S7, the environment is further monitored by the sensor device 12. If the sensor device 12 detects a change in the environment, for example, due to another road user, a new movement trajectory can be determined using the method and compared with the previous movement trajectory. If, for example, it is determined that the new movement trajectory deviates only minimally from the previous movement trajectory and / or the previous movement trajectory is not affected by the changed environment, the previous movement trajectory can continue to be used; otherwise, the new movement trajectory is used for movement planning.

[0055] Overall, the examples show how a strategy for motion planning for universal parking maneuvers can be provided. QUOTES INCLUDED IN THE DESCRIPTION

[0000] This list of documents cited by the applicant was automatically generated and is included solely for the reader's convenience. The list is not part of the German patent or utility model application. The DPMA accepts no liability for any errors or omissions. Cited patent literature

[0000] US 9 969 386 B1

[0003] EP 3 971 047 A1

[0004] WO 2022 / 268323 A1

[0011]

Claims

[1] Method for planning the movement of an autonomous motor vehicle (10) for a parking operation, the method comprising the following steps: - determining (S1) an initial state of the motor vehicle (10) and an environment of the motor vehicle (10), which includes a predetermined parking position, by a sensor device (12) of the motor vehicle (10); - Determining (S2) configuration sample values ​​(20, 20', 20") in a configuration space (18) by a computing device (14) of the motor vehicle (10), wherein the configuration sample values ​​(20, 20', 20") are generated as a function of a movement model of the motor vehicle (10) and thus inadmissible movements of the motor vehicle (10) are excluded, wherein the configuration space (18) represents the surroundings of the motor vehicle (10) and the configuration sample values ​​(20, 20', 20") comprise possible positions of the motor vehicle (10) with a respective associated state of the motor vehicle (10), wherein the configuration sample values ​​(20, 20', 20") are determined using a sampling-based algorithm in predefined sampling steps, wherein in each sampling step a plurality of configuration sample values ​​(20, 20', 20") are processed in parallel using at least one graphics processing unit of the computing device (14),wherein the configuration samples (20, 20', 20") generated in a sampling step are based on the state and position of the configuration samples (20, 20', 20") of the previous sampling step, wherein respective sequences of configuration samples (20, 20', 20") define possible paths (22, 22') of the motor vehicle (10) through the configuration space (18);, - evaluating (S3) the possible paths (22, 22') of the motor vehicle (10) by the computing device (14) as a function of a path criterion; - selecting (S4) a path (22') from the possible paths (22, 22') to the parking position based on the evaluation by the computing device (14), wherein a movement trajectory of the motor vehicle (10), comprising a speed profile of the motor vehicle (10), to the parking position is generated from the selected path (22') (S5); and - Providing (S6) the movement trajectory to a control device (16) of the motor vehicle (10) for moving the autonomous motor vehicle (10) into the parking position. [2] Method according to claim 1, wherein the respective state of the motor vehicle (10) comprises at least an orientation of the motor vehicle (10) in the environment and a steering angle, wherein configuration samples (20, 20', 20") which are excluded by the orientation of the motor vehicle (10) and the steering angle are not generated by the movement model. [3] Method according to one of the preceding claims, wherein the motion model is a single-track model. [4] Method according to claim 3, wherein a front axle control of the motor vehicle (10) in a forward direction and / or reverse direction is taken into account in the single-track model. [5] Method according to claim 4, wherein in the single-track model, a rear axle control is taken into account in addition to the front axle control. [6] Method according to one of the preceding claims, wherein the motor vehicle (10) has a trailer, wherein the motion model does not generate configuration samples (20, 20', 20") in which an amount of a yaw angle between the motor vehicle (10) and the trailer is above a threshold value. [7] Method according to one of the preceding claims, wherein the evaluation of the possible paths (22, 22') by the path criterion is carried out on the basis of a distance of the respective path (22, 22') to objects in the environment and / or on the basis of a number of required steering maneuvers on the respective path (22, 22') and / or on the basis of a number of required changes of direction and / or on the basis of a path length of the respective path (22, 22') and / or on the basis of steering maneuvers when the motor vehicle (10) is stationary. [8] Method according to one of the preceding claims, wherein intermediate values ​​(21) are determined by means of the motion model for configuration samples (20, 20', 20") which are generated in successive sampling steps and which lie on the same path, wherein, starting from the intermediate values ​​(21), further configuration samples and thus paths are generated. [9] Method according to one of the preceding claims, wherein, if a change in the environment is detected by the sensor device (12) (S7), a new movement trajectory is provided by means of the method, wherein an evaluation of the new movement trajectory is carried out compared to the previous movement trajectory and the new movement trajectory is only used if a change condition exists. [10] Motor vehicle (10) comprising a sensor device (12), a computing device (14) and a control device (16), - wherein the sensor device (12) is designed to determine an initial state of the motor vehicle (10) and an environment of the motor vehicle (10) which includes a predetermined parking position; - wherein the computing device (14) is designed to determine configuration sample values ​​(20, 20', 20") in a configuration space (18) and to generate the configuration sample values ​​(20, 20', 20") as a function of a movement model of the motor vehicle (10) and thus to exclude impermissible movements of the motor vehicle (10), wherein the configuration space (18) represents the surroundings of the motor vehicle (10) and the configuration sample values ​​(20, 20', 20") comprise possible positions of the motor vehicle (10) with a respective associated state of the motor vehicle (10), wherein the computing device (14) has at least one graphics processing unit and a sampling-based algorithm which is designed to determine the configuration sample values ​​(20, 20', 20") in predefined sampling steps and to generate a plurality of configuration sample values ​​(20, 20',20") in parallel using the at least one graphics processing unit, wherein the configuration samples (20, 20', 20") generated in a sampling step are based on the state and position of the previous sampling step, wherein respective sequences of configuration samples (20, 20', 20") define possible paths (22, 22') of the motor vehicle (10), wherein the computing device (14) is further configured to evaluate the possible paths (22, 22') of the motor vehicle (10) depending on a path criterion, to select a path (22') from the possible paths (22, 22') to the parking position based on the evaluation, to generate a movement trajectory of the motor vehicle (10), comprising a speed profile of the motor vehicle (10), to the parking position from the selected path (22'), and to provide the movement trajectory to the control device (16); - wherein the control device (16) is designed to autonomously control the motor vehicle (10) into the parking position based on the provided movement trajectory.

Images