DE102023132252B3 - Motor vehicle and method for at least partially automated parking of a motor vehicle - Google Patents

Abstract

In a 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 a 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), 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) are provided by applying a path criterion of the computing device (6). In a step d), a desired virtual target pose (5) is received. In a step e), a movement trajectory (13) to the desired virtual target pose (5) is calculated by interpolation between its at least two neighboring movement trajectories (11, 12) of the already determined virtual target poses (4). In a step f), the interpolated motion trajectory (13) is provided to a control device (9) of the motor vehicle (10).

Description

The invention relates to a method for at least partially automated parking of a motor vehicle. Furthermore, the invention relates to a motor vehicle that is designed to carry out the method.

Methods for at least partially automated parking are often only optimized for certain applications or are very computationally intensive. Thus, complete spatial coverage of all parking options for any virtual target poses can often not be achieved and/or methods for providing a movement trajectory to a desired virtual target pose in these parking options are not suitable for real-time use due to the computational intensity.

The US 10 732 622 B2 discloses a system having a feature whereby a user provides an input via a touchscreen of a mobile device. A vehicle can then drive autonomously to a parking space based on the input.

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

The DE 10 2021 104 290 B3 describes a method for 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 along the trajectory to the end point at least partially automatically, 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.

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

The DE 10 2006 026 092 A1 describes a method for controlling a parking process.

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

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

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

The disadvantage of the known methods is that only parking spaces determined by a system are provided. The option for a user to determine a parking space themselves, in particular a desired virtual target pose in such a parking space, is not available.

The object of the invention is to provide a motion trajectory for a virtual target pose desired by the user.

This object is achieved by the independent patent claims. Advantageous further developments are disclosed in the dependent patent claims, the following description and the figures.

The method comprises, as a step a), determining an initial state of the motor vehicle and an environment of the motor vehicle by a sensor device of the motor vehicle, and, as a step b), determining parking options from the determined environment of the motor vehicle by 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.

In other words, a sensor device of the motor vehicle can initially be used to record sensor data that describe an environment of the motor vehicle and an initial state of the motor vehicle. For example, the environment of the motor vehicle can be determined as static objects, in particular road markings and/or other vehicles, dynamic objects, in particular moving vehicles and/or pedestrians, and parking options that are in the environment of the motor vehicle. The initial state of the motor vehicle can be determined as, for example, an orientation of the motor vehicle in the environment, a steering angle and/or a speed of the motor vehicle. The sensor device can in particular have steering angle sensors, speed sensors, GPS sensors, radar sensors, laser sensors, in particular lidar sensors, ultrasonic sensors and/or camera sensors.

The parking options in the identified environment can be determined, for example, by means of an artificial neural network and/or image recognition algorithm, whereby one or at least one virtual A current target pose can be determined that the motor vehicle should adopt for parking in the respective parking space. This means that the virtual target pose includes, for example, a position and/or orientation of the motor vehicle in the respective parking space. Preferably, a plurality of parking spaces are recorded, i.e. two or more. A parking space means a possible parking position for the motor vehicle, for example a parking space or a parking space.

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

In a step d), a desired virtual target pose is received, whereby 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 this, 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.

In a step e), a movement trajectory to the desired virtual target pose is calculated by interpolation between its at least two neighboring movement trajectories of the already determined virtual target poses. In other words, a movement trajectory to the desired virtual target pose is calculated by interpolation between its n closest movement trajectories of the already determined virtual target pose. n can mean a number from 2 to 8.

In a 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 designed to steer the motor vehicle autonomously into the parking space to the desired virtual target pose using the selected movement trajectory.

The invention provides the advantage that all possible and/or achievable virtual target poses can be calculated that can be reached from a specific starting point, such as an initial state of the motor vehicle, in an environment. This can be particularly useful in scenarios in which 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 together with its movement trajectories, provided that the desired virtual target pose is achievable for the motor vehicle.

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

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, whereby 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 recorded, whereby the recorded 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 option. Preferably, only parking options whose dimensions match the motor vehicle can be pursued. This means that, for example, the dimensions of the motor vehicle can be predetermined and the artificial neural network can be used to check whether the recognized parking option at least matches the dimensions. This development has the advantage that the parking options can be recognized automatically.

A further development provides that the path criterion is designed in such a way that in step c) a configuration space can be generated from the determined sensor data by the computing device of the motor vehicle, which virtually represents the environment of the motor vehicle and in which possible movement trajectories of the motor vehicle to the respective parking options can be determined, wherein the movement trajectories are generated by means of 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 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 that are required at the corresponding positions. For this purpose, a sampling algorithm (“sampling-based algorithm”) can be used, which does not generate complete movement trajectories through the space, but rather individual movement points in the space that 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 (GPU), which enables massive parallel generation of the configuration samples. In this way, a large number of possible movements through the configuration space can be determined, in particular at least one, preferably several, for each parking option. Preferably, several sampling steps can be carried out, wherein for each configuration sample subsequent configuration samples can be determined 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 from the WO 2022/268323 A1 known.

In order to limit the computational effort for the sampling algorithm and to 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 taken into account. In particular, only configuration samples can be generated that can actually be reached by a steering movement of the motor vehicle, which excludes, 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 an input variable and thus determine the configuration samples based on them in the subsequent sampling step.

A respective sequence of configuration samples forms a possible movement trajectory or a geometric path of the motor vehicle through the configuration space, whereby the configuration samples for the respective virtual target pose of each parking option and thus all possible movement trajectories for each parking option are determined simultaneously. The movement trajectory here means the respective spatial route to the parking options.

The individual configuration samples can include speed information that is required, for example, to get from one configuration sample to the next, for example if steering is necessary for such a movement when the motor vehicle is stationary. The simultaneous determination of the configuration samples or the possible movement trajectories to the respective parking options means that the movement trajectories for all parking options are determined in a single calculation sequence of sampling steps and not for each parking option in separate individual calculations. 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 computing time can be reduced, since movements through the configuration space to different parking options can at least partially use the same configuration samples, which therefore do not have to be generated again.

Since the determination of the movement trajectories for each parking option is based on the same or a simultaneous calculation, which maps all permissible movements of the motor vehicle in space, the computational effort can be reduced compared to separate calculations of the movement planning, i.e. for each parking option individually, which enables real-time suitability. 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.

A further development provides that the respective state of the motor vehicle includes at least an orientation of the motor vehicle in the environment and a steering angle, whereby the movement model does not generate configuration samples that are excluded by the orientation of the motor vehicle and the steering angle. However, multiple moves in the forward and backward direction, a change of direction at any point in the environment and also a change in the steering angle when the motor vehicle is at a standstill can be taken into account. In particular, this can prevent several configurations that build on each other. configuration samples are generated that provide movement trajectories that are not feasible at all due to the orientation and the current steering angle of the motor vehicle. The configuration samples, including 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 initial determined state of the motor vehicle and the subsequent states are determined by 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 to previous configuration samples and/or a steering angle rate or a steering angle change speed, by means of which it can be determined whether a deceleration and/or a change in direction of the movement of the motor vehicle is necessary. For example, it can be determined whether steering while the vehicle is at a standstill is necessary for the motion model to generate subsequent configuration samples.

This further development has the advantage that computing capacity can be saved, which contributes to (improved) real-time capability.

A further development provides that after step d) feedback regarding the selected virtual target pose is output by means of 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 about whether and/or how his desired virtual target pose can be achieved.

A further development provides that the motor vehicle is driven to the selected virtual target pose by interaction with the voice dialog system. If the user wants the motor vehicle to drive to the selected virtual target pose at least partially autonomously, he can do this, for example, by making a voice input via the voice dialog system. This makes it convenient and/or easy for the user to operate. Instead of going through complex menus on a display or using physical controls, the user can give a voice instruction to drive the motor vehicle autonomously to the desired virtual target pose.

• In einem Schritt e. 1) wird eine erste Bewegungstrajektorie, die vom initialen Zustand des Kraftfahrzeugs zu der ersten der zumindest zwei benachbarten virtuellen Zielposen führt, in eine Mehrzahl von Fahrschritten aufgeteilt. In einem Schritt e.2) wird eine zweite Bewegungstrajektorie, die vom initialen Zustand des Kraftfahrzeugs zu der zweiten der zumindest zwei benachbarten virtuellen Zielposen führt, in eine Mehrzahl von Fahrschritten aufgeteilt. Entsprechend kann derselbe Schritt für weitere Bewegungstrajektorien je nach Anzahl der in zu Betracht ziehenden benachbarten virtuellen Zielposen durchgeführt werden. Die Anzahl der Fahrschritte der zumindest zweiten Bewegungstrajektorie entspricht dabei der Anzahl der Fahrschritte der ersten Bewegungstrajektorie. Mit anderen Worten haben alle Bewegungstrajektorien der in Betracht gezogenen benachbarten virtuellen Zielposen am Ende dieselbe Anzahl an Fahrschritten. In einem Schritt e.3) werden Durchschnittswerte zwischen jeweils korrespondierenden Fahrschritten der zumindest zwei Bewegungstrajektorien ermittelt. In einem Schritt e.4) werden die ermittelten Durchschnittswerte der korrespondierenden Fahrschritte zum Generieren der dritten Bewegungstrajektorie zusammengeführt.

Further training requires that step e) includes the following steps:

• In a step e.1), a first movement trajectory that 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 that 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 adjacent virtual target poses taken into account have the same number of driving steps at the end. In a step e.3), average values between corresponding driving steps of the at least two movement trajectories are determined. In a step e.4), the determined average values of the corresponding driving steps are combined to generate the third movement trajectory.

A further development provides that the movement 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. It is preferably provided that a front axle control or steering of the motor vehicle in a forward direction and/or backward direction is taken into account in the single-track model. This means that movements of the motor vehicle whose front axle is movable are permitted for the provision of the configuration samples, and thus movements in the forward direction and/or backward direction can be determined using the single-track model. This makes it possible to provide a preferred embodiment of a movement model.

A further development provides that the virtual target poses are stored in a lookup table, whereby the lookup table assigns a respective movement trajectory from the initial state of the motor vehicle to the respective virtual target pose. The lookup table can also store determined desired virtual target poses together with their movement trajectories. This enables at least partially automated parking of the motor vehicle to be implemented in real time.

A one-time calculation of the set of achievable virtual target poses is required, which are then stored in the lookup table together with their respective movement trajectories. For this purpose, it can be set so that, for example, only the shortest movement trajectory is provided to reach a respective virtual target pose.

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.

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 set up 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 set up 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).

The invention also includes further developments of the motor vehicle according to the invention, which have features as have already been 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.

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.

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 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, for example, as a so-called 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 assembler code and/or as source code of a programming language (e.g. C) and/or as a program script (e.g. Python).

The invention also includes combinations of the features from the described embodiments. Thus, the invention also includes implementations that each have a mixture of the features of several of the described embodiments, provided that these embodiments have not been described as incompatible with one another.

• 1 eine schematische Darstellung einer Ausführungsform des erfindungsgemäßen Verfahrens;
• 2 ein Flussdiagram einer Ausführungsform des erfindungsgemäßen Verfahrens; und
• 3 ein Diagramm einer Ausführungsform des erfindungsgemäßen Verfahrens.

Embodiments of the invention are described below.

• 1 a schematic representation of an embodiment of the method according to the invention;
• 2 a flowchart of an embodiment of the method according to the invention; and
• 3 a diagram of an embodiment of the method according to the invention.

The exemplary embodiments explained below are preferred embodiments of the invention. In the exemplary embodiments, the components of the embodiments described each represent individual features of the invention that are to be considered independently of one another and which also develop the invention independently of one another. Therefore, the disclosure should also include combinations of the features of the embodiments other than those shown. Furthermore, the described embodiments can also be supplemented by other features of the invention already described.

In the figures, identical reference symbols designate functionally identical elements.

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

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 of 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.

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 virtual target pose 5 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.

2 shows a flow chart 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 can be reached and/or how far away the desired virtual target pose 5 is. The n next target poses 4 already determined 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 verbal output, e.g. via a voice dialog system of the computing device 6, can be reproduced to the user 17. In S5, an update of the environment 16 can be carried out by means of the sensor device 7 of the motor vehicle 10, for example to determine one or more obstacles 3 and/or other motor vehicles. The update can be carried out 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.

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 by means of the computing device 6 of the motor vehicle 10. In particular, image data can be determined here, whereby this image data represents or has 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 move the drivable area and/or the parking spaces 8 and/or an obstacle 3. The user 17 can then enter a virtual target pose 5 desired by him in S13 and/or move one or more obstacles 3 and/or a detected drivable area and/or parking spaces 8 himself. 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 options 8.

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 can have 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 in S17 as information for the user 17 in the form of feedback. The user 17 can enter a different desired virtual target pose 5 in S18 and/or carry out another manual shift.

In S19, the accessibility of the desired virtual target pose 5 can then be checked again and reproduced as information for the user 17 in the form of feedback. If the desired virtual target pose 5 can then be reached, a control or maneuver to the desired virtual target pose 5 can be checked in S20 and/or initiated in S21. A start of the control can then be reproduced in real time on the input device 19 in S22. At the same time, the control to the desired virtual target pose 5 can be started or activated in S23 of the parking module 30 and carried out in S24 by means of the sensor device 7 and/or at least one actuator.

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

9

control device

10

motor vehicle

11

first movement trajectory

12

second movement trajectory

13

interpolated motion trajectory

16

Vicinity

19

input device

30

parking module

20', 20'', 20'''

driving steps of the first movement trajectory

21'' 21'', 21'''

driving steps of the second movement trajectory

22', 22'', 22'''

average values

Claims (11)

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 options (8) 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), 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). procedure according to claim 1 , wherein the parking options (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 options (8) are provided which match a predetermined dimension of the motor vehicle (10). Method according to one of the preceding claims, wherein step c) comprises: determining of 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 preceding sampling step, wherein respective sequences of configuration samples represent possible movement trajectories (11, 12) of the motor vehicle (10) through the Define a configuration space for the respective parking options (8) to reach the respective virtual target pose (4), wherein the possible movement trajectories (11, 12) for the respective parking options (8) are determined simultaneously by the computing device (6). 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 motion model does not generate configuration samples that are excluded by the orientation of the motor vehicle (10) and the steering angle. 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. Method according to 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). Method according to one of the preceding claims, wherein the motion model is a single-track model. 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. 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). Control device (9) comprising a processor device having program instructions which, when executed by the processor device, cause it to carry out a method according to one of the preceding claims. Motor vehicle (10), comprising a control device (9) according to claim 10 .

Images