Motor vehicle and method for at least partially automated parking of a motor vehicle

The method enhances automated parking by allowing user-defined virtual target poses and optimizing computational efficiency through sensor data analysis and pathfinding, ensuring real-time capability and comprehensive parking coverage.

DE102023132252B3Active Publication Date: 2024-11-28CARIAD SE
View PDF 11 Cites 0 Cited by

Patent Information

Application Number
DE102023132252
Authority / Receiving Office
DE · DE
Patent Type
Patents
Current Assignee / Owner
Filing Date
2023-11-20
Publication Date
2024-11-28
Estimated Expiration
2043-11-20

AI Technical Summary

Technical Problem

Existing automated parking systems often lack the ability for users to select their desired virtual target pose and are computationally intensive, leading to incomplete spatial coverage and real-time limitations.

Method used

A method utilizing a vehicle's sensor device to gather environmental data, determine parking options, and apply pathfinding algorithms to calculate movement trajectories, allowing users to set their desired virtual target pose through an input device, and using neural networks and configuration sampling to optimize computational efficiency.

Benefits of technology

Enables real-time determination of all possible virtual target poses and movement trajectories, including user-defined options, even in complex environments, reducing computational burden and ensuring timely parking maneuvers.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 00000000_0000_ABST
    Figure 00000000_0000_ABST
Patent Text Reader

Abstract

In step a), an initial state (2) of the motor vehicle (10) and an environment (16) of the motor vehicle (10) are detected by a sensor device (7) of the motor vehicle (10). In step b), parking options (8) are determined from the determined environment (16) of the motor vehicle (10) by a computing device (6) of the motor vehicle (10), whereby a virtual target pose (4) is determined for each parking option (8). In step c), several motion trajectories (11, 12) for reaching the virtual target poses (4) are provided by applying a path criterion of the computing device (6). In step d), a desired virtual target pose (5) is received. In step e), a motion trajectory (13) to the desired virtual target pose (5) is calculated by interpolation between its at least two adjacent motion trajectories (11, 12) of the already determined virtual target poses (4).In step f), the interpolated motion trajectory (13) is provided to a control device (9) of the motor vehicle (10).
Need to check novelty before this filing date? Find Prior Art

Description

[0001] The invention relates to a method for at least partially automated parking of a motor vehicle. Furthermore, the invention relates to a motor vehicle configured to carry out the method.

[0002] Methods for at least partially automated parking are often optimized only for specific use cases or are very computationally intensive. Thus, complete spatial coverage of all parking spaces for any virtual target pose cannot often be achieved, and / or methods for providing a movement trajectory to a desired virtual target pose within these parking spaces are not suitable for real-time use due to the computational intensity.

[0003] US 10 732 622 B2 discloses a system with a function that allows a user to enter an input via a touchscreen of a mobile device. A vehicle can then drive autonomously to a parking space based on the input.

[0004] US 10 906 530 B2 discloses an automatic parking system by which a vehicle can be parked autonomously at a determined parking space.

[0005] DE 10 2021 104 290 B3 describes a method for the at least partially automated parking of a motor vehicle, wherein a trajectory from a starting point to an end point is provided and stored, and in the event that the motor vehicle is in predetermined proximity to the provided trajectory, the motor vehicle is driven at least partially automatically along the trajectory to the end point, the trajectory is displayed on a display device, an overview map of an environment around the trajectory is displayed, and the trajectory is shown in the overview map.

[0006] DE 10 2005 062 084 A1 describes a method for steering a vehicle into a parking space and a parking assistance device.

[0007] DE 10 2006 026 092 A1 describes a method for controlling a parking process.

[0008] DE 10 2017 210 221 A1 describes a method for the longitudinal and lateral guidance of a motor vehicle.

[0009] DE 10 2020 126 509 A1 describes a parking assistance device, a parking assistance method and a parking assistance program.

[0010] WO 2023 / 090 001 A1 describes an information processing device, an information processing method and a program.

[0011] A disadvantage of the known methods is that only parking spaces determined by a system are provided. Users do not have the option to independently determine a parking space, especially a desired virtual target pose within such a parking space.

[0012] The object of the invention is to provide a movement trajectory for a virtual target pose desired by the user.

[0013] This problem is solved by the independent patent claims. Advantageous further developments are disclosed in the dependent patent claims, the following description, and the figures.

[0014] The method comprises, as a step a), determining an initial state of the motor vehicle and a surrounding area of ​​the motor vehicle using a sensor device of the motor vehicle, and, as a step b), determining parking options from the determined surrounding area of ​​the motor vehicle using a computing device of the motor vehicle, wherein a virtual target pose is determined for the respective parking option. The computing device can be provided, for example, as a vehicle computer.

[0015] In other words, a sensor device of the motor vehicle can initially capture sensor data that describe the surroundings of the motor vehicle and an initial state of the motor vehicle. For example, the surroundings of the motor vehicle can be defined as static objects, in particular road markings and / or other vehicles; dynamic objects, in particular moving vehicles and / or pedestrians; and parking options located in the surroundings of the motor vehicle. The initial state of the motor vehicle can be defined as, for example, an orientation of the motor vehicle in the surroundings, a steering angle, and / or a speed of the motor vehicle. The sensor device can, in particular, comprise steering angle sensors, speed sensors, GPS sensors, radar sensors, laser sensors, in particular lidar sensors, ultrasonic sensors, and / or camera sensors.

[0016] The parking options in the identified surroundings can be determined, for example, using an artificial neural network and / or image recognition algorithm. For each parking option, one or at least one virtual target pose can be determined, which the motor vehicle should assume to park in the respective parking option. This means that the virtual target pose includes, for example, a position and / or orientation of the motor vehicle in the respective parking option. Preferably, a plurality of parking options is detected, i.e., two or more. A parking option refers to a possible parking position for the motor vehicle, for example, a parking space or a parking space.

[0017] In step c), multiple motion trajectories for reaching the virtual target poses are provided to the computing device by applying a path criterion. The path criterion can be implemented, for example, as an A* algorithm and / or a rapidly exploring random tree algorithm. In other words, multiple paths for reaching the virtual target poses can be provided using a pathfinding algorithm.

[0018] In step d), a desired virtual target pose is received, wherein the desired virtual target pose does not match any of the already determined virtual target poses. In other words, a user can, for example, specify a virtual target pose themselves via an input device of the computing device. This means that the user creates a new virtual target pose that has not yet been determined. To do so, the user can, for example, use an input device of the computing device to move and / or rotate a rectangle that at least represents the size of the motor vehicle and / or at least corresponds to its dimensions to a desired location in order to show where the motor vehicle should be parked.

[0019] In step e), a motion trajectory to the desired virtual target pose is calculated by interpolating between at least two neighboring motion trajectories of the already determined virtual target poses. In other words, a motion trajectory to the desired virtual target pose is calculated by interpolating between its n nearest motion trajectories of the already determined virtual target pose. n can be a number from 2 to 8.

[0020] In step f), the interpolated movement trajectory is provided to a control device of the motor vehicle for moving the motor vehicle to the selected desired virtual target pose. The control device can be configured to autonomously steer the motor vehicle into the parking space at the desired virtual target pose using the selected movement trajectory.

[0021] The invention provides the advantage that all possible and / or achievable virtual target poses that can be reached from a specific starting point, such as an initial state of the motor vehicle, in an environment can be calculated. This can be particularly useful in scenarios where the environment is unknown, dynamic, or complex. Furthermore, a virtual target pose desired by the user, which was not automatically determined by the artificial neural network due to an error, for example, can be provided along with its movement trajectories, provided that the desired virtual target pose is achievable for the motor vehicle.

[0022] The invention also includes further developments which result in additional advantages.

[0023] A further development provides that the parking options in the determined surroundings of the motor vehicle are determined by an artificial neural network, in particular by a convolutional neural network that is trained to determine parking options for such a motor vehicle, wherein only parking options that match a predetermined dimension of the motor vehicle are provided. In other words, the sensor device can have at least one camera through which the surroundings are detected, wherein the detected surroundings can be checked for available parking options using the artificial neural network. For example, road markings and / or street signs and / or gaps between parked vehicles can indicate the presence of a parking space. Preferably, only parking options whose dimensions match the motor vehicle can be pursued.This means, for example, that the dimensions of the vehicle can be specified, and the artificial neural network can be used to check whether the detected parking space at least matches the dimensions. This development offers the advantage of automatically detecting parking spaces.

[0024] A further development provides that the path criterion is designed such that, in step c), a configuration space can be generated from the determined sensor data by the computing device of the motor vehicle. This configuration space virtually represents the surroundings of the motor vehicle and in which possible movement trajectories of the motor vehicle to the respective parking options can be determined. The movement trajectories are generated using configuration samples that include a respective position of the motor vehicle in the configuration space and an associated state. This means that the configuration samples can include the respective position in the configuration space and the associated configuration or the associated state of the motor vehicle. In particular, the state includes the respective steering angles required at the corresponding positions.For this purpose, a sampling-based algorithm can be used, which does not generate complete movement trajectories through space, but rather individual movement points in space, which are based in particular on the previous sampling points, i.e., the previous states and positions of the motor vehicle. This generation of configuration samples is preferably carried out by means of a graphics processing unit, in particular one or more graphics processors (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 at least one, preferably several, for each parking option.Preferably, multiple sampling steps can be performed, whereby subsequent configuration samples can be determined for each configuration sample depending on the previously determined state of the motor vehicle and the position. For example, such a sampling-based method with a configuration space and configuration samples is known from WO 2022 / 268323 A1.

[0025] To limit the computational effort for the sampling algorithm and provide improved motion planning, the configuration samples can be generated using a motion model of the motor vehicle, thus limiting the number of configuration samples in the configuration space. In particular, only permissible movements of the motor vehicle can be defined and permitted in the motion model, so that configuration samples that contradict the motion model are not generated or considered. In particular, only configuration samples that are actually achievable by a steering movement of the motor vehicle can be generated, thus excluding, for example, movements of the motor vehicle in the transverse direction of the vehicle.The motion model can use the previous state and position as input variables and thus determine the configuration samples based on them in the subsequent sampling step.

[0026] A respective sequence of configuration samples forms a possible movement trajectory or a geometric path of the motor vehicle through the configuration space. The configuration samples for the respective virtual target pose of each parking space, and thus all possible movement trajectories for each parking space, are determined simultaneously. The movement trajectory refers to the respective spatial distance to the parking spaces.

[0027] The individual configuration samples can include speed information, which is required, for example, to move from one configuration sample to the next, for example, if such a movement requires steering while the vehicle is stationary. The simultaneous determination of the configuration samples or the possible movement trajectories to the respective parking spaces means that the movement trajectories for all parking spaces are determined in a single calculation sequence of sampling steps, rather than in separate individual calculations for each parking space.Since the configuration samples determine all possible movements through the configuration space and the configuration samples are based on the state of the previous sampling step, computational intensity and / or computation time can be reduced because movements through the configuration space to different parking options can at least partially use the same configuration samples, which thus do not have to be generated again.

[0028] Since the determination of the movement trajectories for each parking space is based on the same or simultaneous calculation, which maps all permissible movements of the vehicle in space, the computational effort can be reduced compared to separate calculations of movement planning, i.e., for each parking space individually, enabling real-time capability. This means that the method can determine a desired virtual target pose and a movement trajectory to this desired virtual target pose without any perceptible delay.

[0029] A further development provides that the respective state of the motor vehicle comprises at least an orientation of the motor vehicle in the environment and a steering angle, wherein the motion model does not generate configuration samples that are excluded by the orientation of the motor vehicle and the steering angle. However, multiple movements in the forward and reverse directions, a change of direction at any point in the environment, and even a change in the steering angle while the motor vehicle is stationary can be taken into account. In particular, this prevents the generation of multiple, successive configuration samples that provide movement trajectories that are completely impossible due to the orientation and the current steering angle of the motor vehicle.The configuration samples, comprising the state, can build on one another, in particular in several consecutive sampling steps, whereby it can thus be determined which configuration samples are possible based on the previous configuration sample. The respective previous state thus forms the basis for a new exploration. The first state is the initially determined state of the motor vehicle, and the subsequent states are determined using the configuration samples. Preferably, the respective configuration sample and / or state can also include a possible speed of the motor vehicle, a distance or a position relative to previous configuration samples, and / or a steering angle rate or a steering angle change rate, by means of which it can be determined whether a deceleration and / or a change in direction of the motor vehicle's movement is necessary.For example, it can be determined whether steering while the vehicle is stationary is necessary for the generation of subsequent configuration samples by the motion model.

[0030] This further development has the advantage of saving computing capacity, which contributes to (improved) real-time capability.

[0031] A further development provides that, after step d), feedback regarding the selected virtual target pose is output via a voice dialog system of the computing device, wherein the feedback describes the accessibility of this target pose. In other words, the user receives information or feedback regarding whether and / or how their desired virtual target pose can be achieved.

[0032] A further development provides for the motor vehicle to be driven to the selected virtual target pose through interaction with the voice dialog system. If the user wishes the motor vehicle to drive to the selected virtual target pose at least partially autonomously, they can initiate this, for example, through a voice input via the voice dialog system. This allows for convenient and / or simple operation for the user. Instead of navigating complex menus on a display or using physical controls, the user can give a voice command to steer the motor vehicle autonomously to the desired virtual target pose.

[0033] Further training requires that step e) includes the following steps: In a step e.1), a first movement trajectory, which leads from the initial state of the motor vehicle to the first of the at least two adjacent virtual target poses, is divided into a plurality of driving steps. In a step e.2), a second movement trajectory, which leads from the initial state of the motor vehicle to the second of the at least two adjacent virtual target poses, is divided into a plurality of driving steps. Accordingly, the same step can be carried out for further movement trajectories depending on the number of adjacent virtual target poses to be considered. The number of driving steps of the at least second movement trajectory corresponds to the number of driving steps of the first movement trajectory. In other words, all movement trajectories of the considered adjacent virtual target poses ultimately have the same number of driving steps. In a step e.3) Average values ​​between corresponding travel steps of at least two movement trajectories are determined. In step e.4), the determined average values ​​of the corresponding travel steps are combined to generate the third movement trajectory.

[0034] A further development provides that the motion model is a single-track model. The single-track model provides a model of a motor vehicle for lateral dynamics, by means of which movements of the motor vehicle can be described. Preferably, the single-track model takes into account a front axle control or steering of the motor vehicle in a forward and / or reverse direction. This means that, for the provision of the configuration sample values, movements of the motor vehicle whose front axle is movable are permitted, and thus movements in the forward and / or reverse directions can be determined based on the single-track model. This makes it possible to provide a preferred embodiment of a motion model.

[0035] A further development provides for the virtual target poses to be stored in a lookup table, with the lookup table assigning a respective movement trajectory from the initial state of the motor vehicle to the respective virtual target pose. The lookup table can additionally store determined desired virtual target poses along with their movement trajectories. This allows for at least partially automated parking of the motor vehicle to be realized in real time.

[0036] A single calculation of the set of achievable virtual target poses is required, which are then stored in the lookup table along with their respective motion trajectories. For this purpose, it can be configured, for example, to only provide the shortest motion trajectory for reaching a given virtual target pose.

[0037] 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.

[0038] The invention also includes a control device for the motor vehicle. The control device can have a data processing device or a processor device that is configured to carry out an embodiment of the method according to the invention. For this purpose, the processor device can have 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). In particular, a CPU (Central Processing Unit), a GPU (Graphical Processing Unit), or an NPU (Neural Processing Unit) can be used as the microprocessor. Furthermore, the processor device can have program code that is configured to carry out the embodiment of the method according to the invention when executed by the processor device. The program code can be stored in a data memory of the processor device.The processor device can be based, for example, on at least one circuit board and / or on at least one SoC (System on Chip).

[0039] The invention also includes further developments of the motor vehicle according to the invention that 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 method according to the invention are not described again here.

[0040] 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.

[0041] As a further solution, the invention also encompasses a computer-readable storage medium comprising program code which, when executed by a computer or computer network, causes the computer to carry out an embodiment of the method according to the invention. The storage medium can be provided at least partially as a non-volatile data memory (e.g. as a flash memory and / or as an SSD - solid state drive) and / or at least partially as a volatile data memory (e.g. as a RAM - random access memory). The storage medium can be arranged in the computer or computer network. However, the storage medium can also be operated on the Internet, for example, as a so-called app store server and / or cloud server. The computer or computer network can provide a processor circuit with, for example, at least one microprocessor.The program code may 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).

[0042] The invention also includes combinations of features from the described embodiments. Thus, the invention also encompasses implementations that each comprise a combination of features from several of the described embodiments, provided that these embodiments are not described as incompatible with one another.

[0043] Exemplary embodiments of the invention are described below. Shown are: Fig. 1 a schematic representation of an embodiment of the method according to the invention; Fig. 2 a flowchart of an embodiment of the method according to the invention; and Fig. 3 a diagram of an embodiment of the method according to the invention.

[0044] The exemplary embodiments explained below are preferred embodiments of the invention. In the exemplary embodiments, the described components of the embodiments each represent individual features of the invention that can be considered independently of one another, each of which also develops the invention independently of one another. Therefore, the disclosure is intended to encompass combinations of the features of the embodiments other than those shown. Furthermore, the described embodiments can also be supplemented by further features of the invention already described.

[0045] In the figures, the same reference symbols designate elements with the same function.

[0046] Fig. Figure 1 shows a schematic representation of an embodiment of the concept. It shows a motor vehicle 10, having a sensor device 7 and a computing device 6, wherein the computing device 6 includes an artificial neural network 1. Also shown are an obstacle 3, parking spaces 8, virtual target poses 4, a desired virtual target pose 5, a first movement trajectory 11, a second movement trajectory 12, and an interpolated movement trajectory 13, wherein the movement trajectories 11, 12 are each divided into three travel steps 20', 20'', 20'', 21'', 21'', 21''. Average values ​​22', 22'', 22'' can then be calculated from the travel steps 20', 20'', 20'', 21'', 21'', 21''' to generate the interpolated movement trajectory 13.

[0047] In a step a), an initial state 2 of the motor vehicle 10 and an environment 16 of the motor vehicle 10 can be detected by a sensor device 7 of the motor vehicle 10. In a step b), parking options 8 can be determined from the determined environment 16 of the motor vehicle 10 by a computing device 6 of the motor vehicle 10, wherein a virtual target pose 4 is determined for the respective parking option 8. In a step c), several movement trajectories 11, 12 for reaching the virtual target poses 4 can be provided by applying a path criterion to the computing device 6. In a step d), a desired virtual target pose 5 can be received, wherein the desired virtual target pose 5 does not match any of the already determined virtual target poses 4.In a step e), a movement trajectory 13 to the desired virtual target pose 5 can be calculated by interpolation between its at least two adjacent movement trajectories 11, 12 of the already determined virtual target poses 4. In a step f), the interpolated movement trajectory 13 can be provided to a control device 9 of the motor vehicle 10 for moving the motor vehicle 10 to the selected desired virtual target pose 5.

[0048] The selection of a desired virtual target pose 5 can be carried out regardless of whether the desired virtual target pose 5 is located in a parking space 8. It can therefore happen that, for example, for technical reasons, not all actual parking spaces 8 are determined, a virtual target pose 5 desired by a user 17 was not automatically determined, but is nevertheless reachable and / or available for the motor vehicle 10. Furthermore, it can happen that the user 17 prefers a different virtual target pose 5 than an already determined one in a parking space 8, so that a movement trajectory 13 to the desired virtual target pose 5 in the parking space 8 is calculated.

[0049] Fig. 2 shows a flowchart of an embodiment of the idea. In a step S1, as already described, virtual target poses 4 can be determined. In a step S2, the user 17 can enter the desired virtual target pose 5. In S3, it can be calculated whether the desired virtual target pose 5 is reachable and / or how far the desired virtual target pose 5 is away. The n nearest already determined target poses 4 can be used to interpolate the movement trajectory 13 and the desired virtual target pose 3. In S4, depending on the possible accessibility of the desired virtual target pose 5, appropriate feedback, e.g., in the form of a voice output, e.g., via a voice dialog system of the computing device 6, can be reproduced to the user 17. In S5, the environment 16 can be updated using the sensor device 7 of the motor vehicle 10, for example, toto determine one or more obstacles 3 and / or additional motor vehicles. The update can be performed at predetermined or fixed intervals. Based on the updated environment 3, new or additional or different parking options 8 and / or virtual target poses 4 can be determined in S6. The parking options 8 and / or virtual target poses 4 can therefore also be updated. Steps S3 and S4 can then be continued.

[0050] Fig.3 shows a diagram of an embodiment according to the idea. As already mentioned, in a step S10, parking spaces 8 and / or virtual target poses 4 in the parking spaces 8 and / or, for example, a drivable area can be determined by means of the sensor device 7 and / or the computing device 6 of the motor vehicle 10. In particular, image data can be determined here, wherein this image data represents or comprises a view from above, i.e., a so-called top-view perspective. The image data can be displayed or reproduced in an input device 19 of the computing device 6 in a step S11. In S12, the input device 19 can enable the user 17 to manually shift the drivable area and / or the parking spaces 8 and / or an obstacle 3.The user 17 can then enter a desired virtual target pose 5 in S13 and / or move one or more obstacles 3 and / or a detected drivable area and / or parking spaces 8 themselves. This has the advantage that the image data can be manually "updated" or adjusted by the user 17 if there is at least a partially incorrect detection of the environment 3 and / or an obstacle 3 and / or a detected drivable area and / or the parking spaces 8.

[0051] In S14, the manual shift and / or a received desired virtual target pose 5 can be routed to a parking module 30. The parking module 30, which may include the control device 9 and / or the computing device 6, can calculate in S15 whether the desired virtual target pose 5 is reachable. In S16, the accessibility of the desired virtual target pose 5 can then be checked. If the desired virtual target pose 5 is inaccessible or not reachable for the motor vehicle 10, this can be provided to the user 17 in the form of feedback in S17. The user 17 can enter a different desired virtual target pose 5 and / or perform another manual shift in S18.

[0052] In S19, the accessibility of the desired virtual target pose 5 can then be checked again and provided as information to the user 17 in the form of feedback. If the desired virtual target pose 5 is then accessible, a control or maneuver to the desired virtual target pose 5 can be checked in S20 and / or initiated in S21. The start of the control can then be reproduced in real time on the input device 19 in S22. At the same time, in S23, the parking module 30 can start or activate the control to the desired virtual target pose 5 and carry it out in S24 using the sensor device 7 and / or at least one actuator.

[0053] Overall, the examples show how a selection of an assisted driving and / or parking maneuver can be provided. List of reference symbols 1 artificial neural network 2 initial state 3 Obstacle 4 virtual target pose 5 desired virtual target pose 6 Computing device 7 Sensor device 8 parking spaces 9 Control device 10 motor vehicle 11 first movement trajectory 12 second movement trajectory 13 interpolated motion trajectory 16 Surroundings 19 Input device 30 parking modules 20', 20'', 20''' driving steps of the first movement trajectory 21'' 21'', 21''' Driving steps of second movement trajectory 22', 22'', 22''' Average values

Claims

[1] Method for at least partially automated parking of a motor vehicle (10), comprising the steps: a) detecting an initial state (2) of the motor vehicle (10) and an environment (16) of the motor vehicle (10) by a sensor device (7) of the motor vehicle (10), b) determining parking possibilities (8) from the determined surroundings (16) of the motor vehicle (10) by a computing device (6) of the motor vehicle (10), wherein a virtual target pose (4) is determined for the respective parking possibility (8), c) providing a plurality of movement trajectories (11, 12) for reaching the virtual target poses (4) by applying a path criterion of the computing device (6), characterized by , d) receiving a desired virtual target pose (5), wherein the desired virtual target pose (5) does not match any of the already determined virtual target poses (4), e) calculating a movement trajectory (13) to the desired virtual target pose (5) by interpolation between its at least two adjacent movement trajectories (11, 12) of the already determined virtual target poses (4), f) providing the interpolated movement trajectory (13) to a control device (9) of the motor vehicle (10) for moving the motor vehicle (10) to the selected desired virtual target pose (5). [2] Method according to claim 1, wherein the parking possibilities (8) in the determined environment (16) of the motor vehicle (10) are determined by at least one artificial neural network (1) of the computing device (6), wherein only parking possibilities (8) are provided which match a predetermined dimension of the motor vehicle (10). [3] Method according to one of the preceding claims, wherein step c) comprises: determining configuration samples in a configuration space by the computing device (6), wherein the configuration samples are generated as a function of a movement model of the motor vehicle (10) and thus impermissible movements of the motor vehicle (10) are excluded, wherein the configuration space represents the environment (16) of the motor vehicle (10) and the configuration samples comprise possible positions of the motor vehicle (10) with a respective associated state of the motor vehicle (10), 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 (6),wherein the configuration samples generated in each sampling step are based on the state and position of the configuration samples of the previous sampling step, wherein respective sequences of configuration samples define possible movement trajectories (11, 12) of the motor vehicle (10) through the configuration space to the respective parking spaces (8) for reaching the respective virtual target pose (4), wherein the possible movement trajectories (11, 12) for the respective parking spaces (8) are determined simultaneously by the computing device (6). [4] Method according to one of the preceding claims, wherein the respective state of the motor vehicle (10) comprises at least an orientation of the motor vehicle (10) in the environment (16) and a steering angle, wherein the movement model does not generate configuration samples which are excluded by the orientation of the motor vehicle (10) and the steering angle. [5] Method according to one of the preceding claims, wherein after step d) a feedback regarding the virtual target pose (4) is output by means of a speech dialogue system of the computing device (6), wherein the feedback describes an accessibility of this virtual target pose. [6] A method according to any one of the preceding claims, wherein step e) comprises: e.1 )Dividing a first movement trajectory (11), which leads from the initial state (2) of the motor vehicle (10) to the first of the at least two adjacent virtual target poses (4), into a plurality of driving steps (20', 20'', 20''), e.2) Dividing at least one second movement trajectory (12), which leads from the initial state (2) of the motor vehicle (10) to the at least second of the two adjacent virtual target poses (4), into a plurality of driving steps (21', 21'', 21 "'), wherein the number of driving steps (21', 21", 21''`) of the at least second movement trajectory (12) corresponds to the number of driving steps (20', 20'', 20''') of the first movement trajectory (11), e.3) determining average values ​​(22', 22'', 22''') between corresponding travel steps (20', 20'', 20''', 21', 21'', 21''') of the first and at least the second movement trajectory (11, 12), e.4) Combining the determined average values ​​(22', 22'', 22'') of the corresponding travel steps (20', 20'', 20''', 21', 21'', 21''') to generate the movement trajectory (13). [7] Method according to one of the preceding claims, wherein the motion model is a single-track model. [8] Method according to one of the preceding claims, wherein control of the motor vehicle (10) to the selected virtual target pose (4) is initiated by interaction with the speech dialogue system. [9] Method according to one of the preceding claims, wherein the virtual target poses (4, 5) are stored in a lookup table, wherein the lookup table assigns a respective movement trajectory (11, 12, 13) from the initial state (2) of the motor vehicle (10) to the respective virtual target pose (4, 5). [10] Control device (9) comprising a processor device comprising program instructions which, when executed by the processor device, cause it to carry out a method according to any one of the preceding claims. [11] Motor vehicle (10) comprising a control device (9) according to claim 10.

Citation Information

Patent Citations

  • Method for steering a vehicle into a parking space and parking aid device

    DE102005062084A1

  • method for controlling a parking process

    DE102006026092A1

  • Method for longitudinal and lateral guidance of a motor vehicle

    DE102017210221A1

  • Parking assistance device, parking assistance procedure and parking assistance program

    DE102020126509A1

  • Method for at least partially automated parking of a motor vehicle, driver assistance system and motor vehicle

    DE102021104290B3