Motor vehicle and method for motion planning of an autonomous motor vehicle

Abstract

The invention relates to a motor vehicle (10) and a method for motion planning of an autonomous motor vehicle (10). The method comprises determining (S1) an environment of the motor vehicle (10); determining (S2) a target position; determining (S3) configuration samples (20, 20', 20") in a configuration space (18) based on a motion model, wherein sequences of configuration samples (20, 20', 20") define paths (22, 22') to the target position; wherein the configuration space (18) comprises several grid cells (26) (S4) and a grid cell object distance (28) from a respective grid cell (26) to objects (24) is determined, wherein a motor vehicle shape (18) is modeled by means of at least one circle (30), wherein (26) a distance of the motor vehicle (10) to the object (24) is calculated by means of a difference of the grid cell object distance (28) and a radius of the circle (30).Furthermore, the possible paths (22, 22') are evaluated (S5) based on the calculated distance; and at least one possible path (22') is provided (S6) as a motion trajectory.

Description

The invention relates to a method for planning the movement of an autonomous motor vehicle. Furthermore, the invention relates to a motor vehicle which is designed to carry out the method.Several strategies for motion planning or for planning motion trajectories are known. In particular, the sampling-based algorithms (sampling-based algorithm) have proven advantageous. However, in these algorithms, the result is strongly dependent on the number of samples, wherein a large number of sample points often complicates a real-time application and therefore these algorithms are not applicable to many scenarios. Particularly in tight environments that include one or more objects, the overall coverage of all possible motion paths is often difficult and strategies are needed to determine possible paths through such an environment.DE 10 2021 120 632 B3 discloses a method for carrying out an autonomous parking process of a vehicle.DE 10 2013 2020 931 A1 discloses a method and a device for supporting the driving of a motor vehicle onto a curb. The method comprises as steps a detection of a curbstone located in the environment of the motor vehicle, and a modification of at least one operating parameter of the motor vehicle in such a way that, during the driving of at least one tire of the motor vehicle onto the curbstone, a vibration of the motor vehicle accompanying this driving-on is reduced in comparison with an analogous driving-on process without this with modification.The object of the invention is to improve a movement planning for an autonomous motor vehicle.This object is achieved by the independent patent claims. Advantageous refinements of the invention are disclosed in the dependent patent claims, in the following description and in the figures.The invention is based on the idea that an algorithm based on samples is used for motion planning, wherein a motion model of the motor vehicle is provided for this purpose and a model of a shape of the motor vehicle, wherein the generation of samples is limited by the models only to movements and distances to objects that are possible on the basis of an orientation of the motor vehicle.One aspect of the invention relates to a method for planning the movement of an autonomous motor vehicle, in particular for a parking process. The method comprises as steps a determination of an initial state of the motor vehicle and of a surrounding area of the motor vehicle by a sensor device of the motor vehicle, a determination of a target position and of a target state of the motor vehicle in the surrounding area by a computing device of the motor vehicle, and a determination of configuration samples in a configuration space by the computing device, wherein the configuration samples are generated as a function of a movement model of the motor vehicle and thus impermissible movement of the motor vehicle is excluded, wherein the configuration space represents the surrounding area of the motor vehicle and the configuration samples comprise possible positions of the motor vehicle with a respectively associated state of the motor vehicle. The configuration samples are determined using a sample-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 each sampling step are based on the state and the position of the configuration samples of the preceding sampling step, wherein respective sequences of configuration samples define possible paths of the motor vehicle through the configuration space for reaching the target position and the target state. Furthermore, the configuration space is rastered into a plurality of raster cells and a raster cell object distance from a center of a respective raster cell to an object in the environment closest to the respective raster cell is determined, wherein a motor vehicle shape of the motor vehicle in the configuration space is modeled as a motor vehicle circle model comprising a circle or a composition of a plurality of circles, wherein for a respective raster cell a distance of the motor vehicle to the object in the environment closest is calculated by means of a difference of the raster cell object distance and a radius of a circle of the motor vehicle circle model. In addition, the possible paths and / or newly generated configuration samples are evaluated after each sampling step by the computing device as a function of a path criterion, wherein at least the calculated distance of the motor vehicle from the objects in the environment is checked by the path criterion for the presence of at least one minimum distance, wherein paths and / or configuration samples are excluded for which the minimum distance is not present. Finally, at least one possible path is provided as a movement trajectory of the motor vehicle at a control device of the motor vehicle for controlling the autonomous motor vehicle to the target position in the target state.In other words, sensor data are initially acquired by means of a sensor device of the motor vehicle, said sensor data comprising information about the surroundings of the motor vehicle and an initial state of the motor vehicle. The environment of the motor vehicle can include, for example, static objects, in particular roadway boundaries and / or other vehicles. As an initial state of the motor vehicle, for example, an orientation of the motor vehicle in the environment, a steering angle angle angle or a wheel position and / or a speed of the motor vehicle can be determined. The sensor device can have, in particular, steering angle sensors, speed sensors, GPS sensors, radar sensors, laser sensors, in particular LIDAR sensors, ultrasonic sensors and / or camera sensors.From the determined sensor data, a target position and a target state of the motor vehicle in the environment can be determined by a computing device of the motor vehicle, which can be provided, for example, as a vehicle computer. The target position can be a position to which the motor vehicle is intended to travel, for example a parking position, and the target state can indicate the state of vehicle parameters which are intended to be reached in the target position. For example, the target state can be used to specify an orientation of the motor vehicle in space, a speed, a wheel position and / or further vehicle parameters which the motor vehicle is intended to assume in the target position.The computing device can furthermore be configured to generate a configuration space which represents the environment of the motor vehicle virtually and can be determined in the possible positions of the motor vehicle to the target position with an associated state, wherein the positions and the associated states are generated as configuration samples or sampling values which comprise a respective configuration at the respective position. In other words, the configuration samples can comprise the respective positions in the configuration space and the associated configuration or the associated state of the motor vehicle. In particular, the state can comprise the respective steering angles which are required at the corresponding positions and the respective orientation of the motor vehicle in space.For analyzing the configuration space, a sampling algorithm (sampling-based algorithm) can be used, by means of which no complete trajectories through the space are generated, but rather individual movement points in the space, which are based in particular on the preceding sampling points, i.e. the preceding 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), by means of which massively parallel generation of the configuration samples is made possible. Thus, a plurality of possible movements for a variety of situations can be determined by the configuration space. Preferably, a plurality of scanning steps can be carried out, wherein the configuration scanning values in a respective scanning step can be based on the previously determined states and positions of the preceding scanning step. For example, such a sample-based method with a configuration space and configuration samples is known from WO 2022 / 268323 A1.In order to limit the computing effort for the scanning algorithm and to provide improved motion planning, the configuration samples can be generated by means of a motion model of the motor vehicle and thus the number of configuration samples in the configuration space can be limited. In the movement model, in particular only admissible movements of the motor vehicle can be defined and permitted, so that configuration samples which correspond to the movement model are not generated or taken into account. In particular, only configuration samples can thus be generated which can be reached at all by a steering movement of the motor vehicle, as a result of which, for example. Movements of the motor vehicle in the transverse direction of the vehicle can be excluded. The motion model can use the associated state and the position as input value on the basis of a respective configuration sample value and thus determine the configuration samples based thereon in the subsequent sampling step.A respective sequence of configuration samples can form a possible geometric path of the motor vehicle through the configuration space. In this case, the geometric path is the spatial distance to the target position, which, however, does not yet comprise a velocity profile. However, the individual configuration samples may comprise speed information which is required, for example, to pass from one configuration sample to the next, for example if a steering is necessary for such a movement when the motor vehicle is at a standstill.In order to maintain sufficient distance from objects in the environment, in particular static objects, it can furthermore be provided that the configuration space is divided into a plurality of grid cells and a grid cell object distance from a center of the respective grid cell to the next object in the environment is determined for each grid cell. This means that there is thus a value for each grid cell which provides the distance to the closest object. Furthermore, the motor vehicle shape can be assumed to be a schematic model in order to be able to perform a distance check quickly for each grid cell. Preferably, a simplified model can be provided for this purpose, by means of which a rapid calculation of the distance of the motor vehicle can be determined for each grid cell; in particular, the motor vehicle shape can be modeled as a motor vehicle circuit model. With the motor vehicle circle model, for example, the shape of the entire motor vehicle can be assumed in a simplified manner as a circle having a predefined radius. Particularly preferably, the motor vehicle shape can also be assembled as a composition of a plurality of circles, which can have different radii, for example. Here, the accuracy can be increased with an increase in further circles in the circle model of the motor vehicle.With the aid of the grid cell object distance and the motor vehicle circle model, the distance of the motor vehicle from the objects can then be calculated once for each grid cell. Thus, for each configuration sample reaching this cell, the distance to the objects can be estimated, which provides a time advantage in sampling the entire configuration space. In particular, for each grid cell, a distance of the motor vehicle from the respective object can be calculated by means of a difference of the grid cell object distance and a radius of a circle of the motor vehicle circle model. That is, the grid cell object distance may be determined by where min(distance_Objekt) is the respective minimum distance to the respective objects in the environment, and the distance of the motor vehicle to the objects may be calculated by.After the possible paths and / or the configuration samples have been generated in a respective sampling step, the paths can be evaluated as a function of a path criterion. The path criterion can be, for example, a condition and / or a rule that the respective path and / or the respective configuration sample should or should meet. The path criterion can query at least the calculated distance of the motor vehicle from the objects in the environment for the presence of at least one minimum distance, wherein paths and / or configuration samples for which the minimum distance is not present can be excluded. This means that the corresponding configuration samples can be discarded and not followed further, so that subsequent configuration samples that would be based on these configuration samples are not generated at all, which results in a time advantage in the calculation.The path criterion can preferably query additional conditions, e.g. the paths can be additionally evaluated as a function of a route, a number of required steering movements or changes in direction, in order to generate a cost function and to determine the best paths. It is thus particularly preferable for the configuration samples to be determined and for the paths resulting therefrom to be subsequently evaluated in each sampling step, it being possible in particular for the best-evaluated paths to be followed iteratively. This can be carried out until the paths lead to the target position.After the possible paths to the target position have been created, a path can be selected from all possible paths, preferably the best evaluated path, on the basis of the evaluation. This can be determined in particular by a loss function ("loss function").After the path has been selected, a movement trajectory can be created from this using a speed profile. In other words, the movement trajectory represents the geometric path through the space including an associated speed on the path. This movement trajectory can subsequently be provided to a control device of the motor vehicle which is designed to control the motor vehicle autonomously into the parking position.The invention has the advantage that the static environment can be displayed in an improved manner, so that a minimum distance from static objects can be observed during a trajectory calculation and at the same time any available space is used, which can be necessary in particular in tight environments. This allows a runtime to be optimized and an improved collision check to be provided, which provides a movement planning in a quick and real-time-capable manner.The invention also comprises developments, by means of which additional advantages result.A further development provides that paths whose distance to objects are below a predetermined safety distance value are evaluated worse by the path criterion than paths above the safety distance value. The safety distance value can be greater than the minimum distance queried by the path criterion. However, the safety distance value can provide a safety distance which is to be taken into account, for example, on the basis of inaccuracies in the movement planning. For example, a distance of at least 50 cm can be defined for the safety distance value. If it is determined that the distance of the motor vehicle from objects is below the safety distance value, an allowed path may nevertheless be present, wherein said path receives a poorer evaluation than other paths for which the safety distance value is present. Thus, the probability for these paths is reduced that they are ultimately selected as a movement trajectory. This results in the advantage that the determination of the movement trajectory used can be improved.A further refinement provides that a speed of the motor vehicle is defined in the movement trajectory as a function of a distance of the motor vehicle from respective objects. That is, in planning the velocity profile on the selected path, the velocity used may be provided at any position as a function of distance. It is preferably provided that a speed can be reduced as the distance decreases. This development results in the advantage that a safety during the movement planning can be improved.A further refinement provides that the respective state of the motor vehicle comprises at least one orientation of the motor vehicle in a surrounding area and one steering angle angle angle, wherein configuration sample values which are excluded by the orientation of the motor vehicle and the steering angle angle angle angle angle angle are not generated by the movement model. However, multiple trains in the forward and reverse direction, in changes of direction at any desired points in the environment and also a change of steering angle in a standstill of the motor vehicle can be taken into account. In particular, it is thus possible to prevent a plurality of configuration samples which are built up one on top of the other and which provide paths which cannot be carried out at all by the orientation and the current steering angle angle angle angle angle of the motor vehicle. The configuration samples comprising the state can be based on one another, in particular in a plurality of successive sampling steps, it being possible to determine which configuration samples are possible on the basis of the preceding configuration sample. Thus, the respective previous state 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 comprise a possible speed of the motor vehicle, a distance or a position from the preceding 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 in this way whether steering at standstill of the motor vehicle is necessary for the generation of subsequent configuration samples by the movement model. A single-track model can preferably be used as the movement model. The toe-in model provides a model of the motor vehicle for lateral dynamics, by means of which movements of the motor vehicle can be described. This development results in the advantage that computing capacities can be saved, which contributes to improved real-time capability.A further development provides that objects in the environment are classified according to low and high objects, wherein the presence of the minimum distance is checked for high objects, wherein the configuration space is divided into a height profile grid with inclination information for low objects, wherein a wheel position of the motor vehicle is determined from the state of the respective configuration samples in relation to the low object for configuration samples which are situated in the vicinity of a low object, wherein a lateral distance of the respective wheel from the low object is determined depending on the wheel position, wherein the possible path and / or the configuration sample for which the lateral distance is below a wheel distance threshold value is excluded. In other words, the objects in the environment of the motor vehicle can be divided into high and low objects. For this purpose, for example, a determined height of the respective object can be used, wherein for example objects below twenty centimeters can be classified as low objects, and above twenty centimeters as high objects. If a tall object is present in the environment, the minimum distance can be checked by the path criterion described above, as a result of which the configuration sample can be excluded if the minimum distance is too small. However, if a low object is present, it can be checked, on the one hand, whether a transition via this low object is possible and, on the other hand, whether a risk exists for the motor vehicle, in particular for rims of the motor vehicle, by this object. Low objects may include curbstones, wheel stoppers, and ground bumps, for example. In order to check whether a transition over the low object is possible and / or whether a wheel rim can be damaged by the low object, the configuration space can be divided into a height profile grid, as a result of which, for example, inclination information of the low objects can also be provided. By a height profile grid is meant that the configuration space can be divided into several units, for example squares, each unit of the grid can have a value that can indicate the height of the object at that position. The inclination information can be provided from values or a course of adjacent raster fields. With the aid of the height profile grid, it can then be checked at least whether there is a risk for a wheel, in particular a rim of the motor vehicle, by firstly reading out a wheel position or an orientation of the wheels from the state of the configuration samples. A lateral distance of the respective wheel from the low object can then be determined. Lateral distance means the distance which runs in the direction of a surface normal of the wheel laterally to the object. If it is determined that the lateral distance is below a wheel distance threshold value and thus, for example, the rim can strip the low object, the configuration sample and / or the associated path can be excluded from the movement planning. This results in the advantage that a movement planning can be further improved.Preferably, it is provided that a crossing of the low object is checked on the basis of the height profile grid, wherein a crossing of the low object is permitted if a height and / or inclination of the low object below a height threshold value is determined from the height profile grids and if an angle of the wheel position to the low object lies in a predefined angle range. This means that, during the movement planning, it is also possible to plan the passage over low objects, in particular if the value of a field of the height profile grid is below an height threshold value and / or if at least one sequence of adjacent fields of the height profile grid is below the height threshold value. As a further condition, for a transition over low objects, provision can be made that a wheel position is also suitable for the transition, wherein only transitions over low objects are allowed, in which the wheel position is located in a predefined angle range to the low object. In other words, the passage can only be allowed if the wheel substantially just hits the low object. This results in the advantage that further movements are made possible during the movement planning.Preferably, it is provided that for the generation of a movement trajectory of the motor vehicle, a speed is adjusted to a predefined speed value when passing low objects. In particular, the speed can be reduced when passing low objects. Safety for the motor vehicle can thereby be increased.Furthermore, it can be provided that those paths are preferred in which no passing of low objects is provided. In other words, a respective path can be evaluated by the path criterion, paths which provide a transition over low objects being evaluated worse than paths which do not have a transition.A further development provides that regions around objects, in particular tall objects, are divided into at least three distance regions, a near region up to a first predefined distance from the object, a middle region, starting from the first predefined distance to a second predefined distance from the object, wherein the second distance is greater than the first distance, and a far region, starting from the second predefined distance to a third predefined distance from the object, wherein the third distance is greater than the second distance, wherein after the provision of the movement trajectory a validity of the movement trajectory is checked cyclically, and when the environment changes the movement trajectory is recalculated. The recalculation can depend on the following criteria:If the motor vehicle is located in the far range during the recalculation, a path and / or a movement trajectory which runs in the far range can preferably be determined. If entry into the mid-range is unavoidable, a path and / or a movement trajectory can be determined which leads back into the far range after entry into the mid-range. Alternatively or additionally, a speed can be reduced as a function of the distance.If the motor vehicle is in the mid-range during the re-calculation, a path and / or a movement trajectory can be determined which is remote from the object and / or which leads into the long-range. If no path that is remote from the object can be determined, the motor vehicle can preferably be stopped.If the motor vehicle is in the near range during the recalculation, a stopping of the motor vehicle can preferably be initiated. In other words, an originally calculated movement trajectory or an originally calculated path may no longer be valid after a change in the environment. Therefore, a cyclical check can take place as to whether the planned path is still valid and a re-calculation can be carried out if this is not the case. If the path continues to be valid, it can be used further. During a recalculation, it is preferably provided that as little change as possible in the previous path is made and that dead end situations are avoided. This development results in the advantage that a further improvement in the movement planning can be provided.For use cases or application situations which can arise in the method and which are not explicitly described here, provision can be made for an error message and / or a request for inputting a user feedback to be output and / or for a default setting and / or a predetermined initial state to be set according to the method.A further aspect of the invention relates to a motor vehicle comprising at least one computing device, wherein the computing device is designed to carry out an aforementioned method. This results in the same advantages and possible variations as in the method. 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.The invention also includes a control device for the motor vehicle. The control device can have a data processing device or a processor device which 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 (graphic processing unit) or an NPU (neural processing unit) can be used as the microprocessor in each case. Furthermore, the processor device can have program code which 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 on at least one circuit board and / or on at least one SoC (system on chip), for example.As a further solution, the invention also comprises a computer-readable storage medium comprising program code which, when executed by a computer or a computer cluster, causes the latter to execute an embodiment of the method according to the invention. The storage medium may 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 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 developments of the motor vehicle according to the invention, which have features as have already been described in connection with the developments of the method according to the invention. For this reason, the corresponding developments of the motor vehicle according to the invention are not described again here.The invention also includes the combinations of the features of the described embodiments. The invention therefore also comprises implementations which each have a combination of the features of a plurality of the described embodiments, provided that the embodiments have not been described as mutually exclusive.Exemplary embodiments of the invention are described below. The following shows: FIG. 1 shows a schematically illustrated motor vehicle according to an exemplary embodiment; FIG. 2 is a schematic process diagram according to an example embodiment; FIG. 3 shows a configuration space with configuration samples for an example motion planning; FIG. 4 shows a configuration space with grid cells that include a grid cell object distance; FIG. 5 shows a schematic illustration of a pass of a low object; FIG. 6 shows an illustration of distance ranges around an object.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 are to be considered independently of one another and that also develop the invention independently of one another. Therefore, the disclosure is intended to include combinations of the features of the embodiments other than those illustrated. Furthermore, the described embodiments can also be supplemented by further features of the invention that have already been described.In the figures, identical reference numerals designate functionally identical elements.FIG. 1 shows a schematically illustrated motor vehicle 10, which can be designed, for example, as a motor vehicle. The motor vehicle 10 may be an autonomous motor vehicle which is designed to carry out a movement planning to a target position, in particular for a parking process, and to drive autonomously to the target position on the basis of the movement planning. For this purpose, the motor vehicle 10 can have a sensor device 12, a computing device 14 and a control device 16.The sensor device 12 can comprise one or more sensors which can capture 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 which can determine a current steering angle angle angle, a speed and / or an orientation of the motor vehicle 10 in the environment.The computing device 14 and the control device 16 can be provided as vehicle computers of the motor vehicle 10, wherein these can be provided as a unit in a common device or as a common vehicle computer, or as separate devices. The computing device 14 can be configured at least to perform a movement planning to a target position in the environment of the motor vehicle 10 determined by the sensor device 12, wherein the movement planning can be based on a sampling-based algorithm in which a plurality of sample values can be determined which result in a geometric path to the target position as a respective sequence. In particular, the computing device 14 can comprise a graphics processing unit 15 by means of which a fast parallel processing of a plurality of sample values is made possible.The control device 16 can be configured to control the motor vehicle 10 by means of the movement planning provided by the computing device 14, in particular by means of a provided movement trajectory, in such a way that the motor vehicle 10 drives autonomously to the target position. In this case, in particular a plurality of steering trains with changes in direction, comprising small and large steering interventions, and also steering interventions in a standstill of the motor vehicle 10, can be taken into account by the movement trajectory.FIG. 2 shows a schematic method diagram for the movement planning of an autonomous motor vehicle 10 according to an exemplary embodiment, wherein the movement planning can be carried out by means of the sensor device 12, the computing device 14 and the control device 16.In a step S 1, an initial state of the motor vehicle 10 and a surrounding area of the motor vehicle 10, which surrounding area comprises a predetermined parking position, can be determined by the sensor device 12 of the motor vehicle 10. The environment can include static and dynamic objects in the environment of the motor vehicle 10. The initial state can provide an initial configuration or an initial state of the motor vehicle 10, on the basis of which the movement planning is carried out. For example, the initial state may include a current speed, a current steering angle angle angle angle angle and / or a current orientation in the room or the environment.In a step S 2, a target position of the motor vehicle can be determined by the computing device 14, which target position can additionally comprise a target state. The target position may be the position to which the motor vehicle 10 is to travel and the target state may include the orientation and / or velocity that the motor vehicle 10 is to assume at the target position. The target position can be known, for example, on the basis of a predetermined route, for example by means of GPS route planning, and / or the target position can be a parking position which the motor vehicle has ascertained in the environment.In a step S 3, a virtual configuration space 18 can be generated by the computing device 14 from the environment ascertained by the sensor device 12, said virtual configuration space representing the environment of the motor vehicle 10. Such a configuration space 18 is illustrated by way of example and strongly schematically in FIG. 3. The computing device 14 can then calculate configuration samples 20, 20', 20" in the configuration space 18 using a sample-based algorithm, preferably using at least one graphics processing unit 15, which comprise possible positions of the motor vehicle 10 with a respectively associated state of the motor vehicle 10. The configuration samples 20, 20', 20" (samples) can have as state at least one respective steering angle angle angle angle required for the position and an orientation of the motor vehicle at this position. In particular, the configuration samples 20, 20', 20" can be generated in a plurality of sampling steps which are based on one another. For example, in a first sampling step, the configuration samples 20 can be determined, in a subsequent second step, the configuration samples 20' which are based on the first configuration samples 20, in particular on the state provided in the configuration samples 20, and correspondingly in a third sampling step, further configuration samples 20". In this case, the number of scanning steps is shown only by way of example, and a multiplicity of further scanning steps up to a last scanning step in which the motor vehicle 10 reaches the target position can be carried out.In order to limit the number of configuration samples in the respective sampling step and thus provide a real-time capability of the movement planning, it can furthermore be provided that generation of the configuration samples 20, 20', 20" in the configuration space 18 is carried out by a movement model and thus impermissible movements of the motor vehicle are excluded. In particular, the movement model can provide that positions and / or states of the motor vehicle 10 in the configuration space 18 are not generated, for which a movement of the motor vehicle is excluded, wherein all other possible movements of the motor vehicle are generated, preferably also under the assumption of a steering movement when the motor vehicle is at a standstill.Particularly preferably, a meshing model can be used as the movement model, by means of which steering angle angles and a movement and orientation of the motor vehicle 10 in space resulting therefrom can be determined in a simple manner. In the case of the toe-in model, it may preferably be provided that a front axle control of the motor vehicle 10 is assumed and movements in the forward and / or rearward direction are taken into account. Thus, for example, multiple trains with changes of direction can also be planned at any desired locations.Geometric paths 22, 22' of motor vehicle 10 can be determined from sequences of generated configuration samples 20, 20', 20", which preferably lead to the target position after the last sampling step.In a step S 4, the configuration space can be divided into a plurality of grid cells 26 in order to determine a distance to objects 24 in the environment for each grid cell 26 and to determine a distance of the motor vehicle 10 to the at least one object 24 at this position. The step S 4 can preferably take place in parallel with the step S 3. This means that the grid cells 26 which comprise the distance to the respective objects 24 in the environment can already be generated when creating the configuration space 18 in order to take into account the distance when creating the configuration samples ( 20, 20', 20"). This is illustrated, for example, in FIG. 4.In FIG. 4, configuration space 18 is shown, which is rastered into multiple raster cells 26 to provide a raster cell object distance 28 to objects 24 in the environment. Here, for clarity, only the determination of the grid cell object distances 28 for a grid cell 26 is shown, wherein this determination can be carried out for each grid cell 26. Preferably, the grid cell object distance 28 from a center of the grid cell 26 to a respective object 24, in particular a point of the object 24 closest to the grid cell 26, can be determined. Furthermore, a motor vehicle shape of the motor vehicle 10 in the configuration space 18 can be modeled as a motor vehicle circle model, wherein the motor vehicle shape is modeled by means of two circles 30 in this example. Thus, for each configuration sample 20 scheduled for the grid cell 26, it may be checked whether the grid cell object distance 28 provides sufficient distance to the objects 24 by subtracting the grid cell object distance 28 with the radius of at least one circle 30 of the motor vehicle circle model. If the distance thus calculated is below a minimum distance, for example, a corresponding path 22 and / or a configuration sample 20 can be excluded for the movement planning. In particular, no further samples can then be generated on the basis of this configuration sample 20, as a result of which a computing effort can be minimized.Particularly preferably, in step S 4, the objects 24 can additionally be classified according to low and high objects 24, wherein the above-described distance of the motor vehicle can be checked for the presence of the minimum distance for high objects. For low objects 24, on the other hand, it is possible to check whether a crossing is possible and / or whether a lateral distance of wheels 32 from these low objects 24 is observed in order to avoid damage to motor vehicle rims. In particular, the configuration space 18 can additionally provide a height profile grid, wherein height information can be provided in the respective cells of the height profile grid. Thus, a sequence of cells of the height profile grid can preferably also provide inclination information for the low objects in order to check whether a transition is possible.In order to check whether a lateral distance of a wheel 32 from the low object 24 is observed, the planned wheel position at the respective position can be determined from the respective configuration samples. A lateral or lateral distance of the wheel 32 from the low object 24, which can be a sidewalk, for example, can then be determined from the wheel position, wherein the corresponding configuration sample and / or the associated path after the sampling step can be excluded from the movement planning if the lateral distance is below a wheel distance threshold value, for example, below 10 cm.For checking whether a transition over a low object 24 is possible, it can be checked by means of the height profile grid whether a height and / or inclination of the low object 24 is below a height threshold value and preferably whether a wheel position, which can be read out from the configuration samples ( 20, 20', 20"), is present in a predefined angle range with respect to the low object 24. For the purpose of illustration, FIG. 5 shows a schematic illustration of a pass over a low object 24. In this case, a crossing of the low object 24 can be checked on the basis of the previously determined height profile grid, it being possible to allow the crossing if a height and / or inclination of the low object 24 is below a height threshold value. Furthermore, it can be checked whether the angle δ at which the at least one wheel 32 strikes the object 24 is within a predefined permitted angle range. Thus, in particular, the passage of the low object 24 can only be permitted if the wheel 32 with a running surface substantially just meets the low object 24, wherein the predefined angle range can additionally permit angles of + / - 45 degrees for a passage, for example.In a step S5, the possible paths 22, 22' and / or the newly generated configuration samples (20, 20', 20") can be evaluated after each sampling step as a function of a path criterion, wherein at least the calculated distance of the motor vehicle 10 from respective objects in the environment can be checked by the path criterion for the presence of a minimum distance. The minimum distance may comprise a distance which the motor vehicle 10 is at least intended to have to the respective objects, for example 20 cm. In addition, the path criterion can also be used, for example, to evaluate a number of required steering maneuvers on the respective path and / or a number of required changes in direction and / or a path length and / or a path duration of the respective path and / or steering maneuvers when the motor vehicle is at a standstill. Preferably, only paths that adhere to the minimum distance can be tracked in this case, wherein paths and / or configuration samples below the minimum distance can be excluded and cannot be tracked. Consequently, the assessment can be carried out iteratively after each scanning step and paths can possibly be excluded until the paths lead to the target position in a last scanning step.In a step S6, at least one of the calculated paths ( 22, 22') can then be provided to the control device 16 as a movement trajectory of the motor vehicle 10. Consequently, the control device 16 can control the motor vehicle 10 autonomously to the target position by means of the movement trajectory.Preferably, for this purpose, a path 22', in particular the best-valued path 22', for which a speed profile can be determined, can be selected from the valued paths 22, 22' to the target position. A movement trajectory of the motor vehicle 10 to the target position can thus be generated from the geometric path.In a step S 7, after the movement trajectory has been provided for controlling the motor vehicle 10, a validity of the movement trajectory can be checked repeatedly, in particular whether it continues to be valid after a change in the environment. If this is no longer valid, new recalculation can preferably take place depending on a present distance from objects 24.FIG. 6 shows distance ranges A 1, A 2, A 3 around an object 24, by means of which criteria for a recalculation of the movement trajectory can be provided if a previously determined movement trajectory becomes invalid by changing an environment. In particular, a near area A 1, a middle area A 2 and a far area A 3 are shown.If the motor vehicle is located in the far range A 3 during the recalculation, it can preferably be provided that a new path and / or a new movement trajectory is determined, which is likewise located in the far range A 3 or even further away from the object 24. However, if entry into the center area A 2 cannot be avoided during the recalculation, it can be provided as a new path and / or new movement trajectory that it leads from the center area A 2 back into the far area A 3. It can be provided particularly preferably in this case that the closer the motor vehicle 10 approaches the object, the further a speed can be reduced.If the motor vehicle is located in the center area A 2 when the new calculation takes place, it can be provided that a new path and / or a new movement trajectory is provided, which is remote from the object 24 and which preferably leads into the remote area A 3. If no such path is present, it can preferably be provided that a speed of the motor vehicle 10 is reduced until it stops.If the motor vehicle 10 is in the near range A 1 during the recalculation, it can be provided that the motor vehicle is stopped. Preferably, a request for manual control of the motor vehicle 10 can then be made.Overall, the examples show how a strategy for motion planning can be provided in tight environments.References included in the specificationThis list of documents cited by the applicant has been produced in an automated manner and is only included for the better information of the reader. The list is not part of the German patent application or utility model application. The DPMA does not take any adhesion for any faults or omissions.Patent Literature citedDE 10 2021 120 632 B3

[0003] DE 10 2013 2020 931 A1

[0004] WO 2022 / 268323 A1

[0012]

Claims

Method for planning the movement of an autonomous motor vehicle (10), wherein the method comprises the following steps: - determining (S1), by a sensor device (12) of the motor vehicle (10), an initial state of the motor vehicle (10) and a surrounding area of the motor vehicle (10); - determining (S2) by a computing device (14) of the motor vehicle (10) a target position and a target state of the motor vehicle (10) in the surrounding area; - determining (S3), by the computing device (14), configuration samples (20, 20', 20") in a configuration space (18), wherein the configuration samples (20, 20', 20") 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 (18) represents the surrounding area of the motor vehicle (10) and the configuration samples (20, 20', 20"), 20', 20") comprise possible positions of the motor vehicle (10) with a respective associated state of the motor vehicle (10), wherein the configuration samples (20, 20', 20") are determined in predefined sampling steps using a sample-based algorithm, wherein in each sampling step a plurality of configuration samples (20, 20', 20") are determined in parallel using at least one graphics processing unit (15) of the computing device (14), wherein the configuration samples (20, 20', 20") generated in each sampling step are based on the state and the position of the configuration samples (20, 20', 20") of the preceding 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) for reaching the target position and the target state; wherein the configuration space (18) is rastered (S4) into a plurality of raster cells (26) and a raster cell object distance (28) is determined from a center of a respective raster cell (26) to an object (24) in the environment closest to the respective raster cell (26), wherein a motor vehicle shape of the motor vehicle (10) in the configuration space (18) is modeled as a motor vehicle circle model comprising a circle (30) or a composition of a plurality of circles, wherein for a respective raster cell (26) a distance of the motor vehicle (10) to the object (24) in the environment closest is calculated by means of a difference of the raster cell object distance (28) and a radius of a circle (30) of the motor vehicle circle model, - evaluating (S5) the possible paths (22, 22') and / or newly generated configuration samples (20, 20', 20") after each scanning step by the computing device (14) as a function of a path criterion, wherein at least the calculated distance of the motor vehicle (10) from the objects (24) in the environment is checked by the path criterion for the presence of at least one minimum distance, wherein paths and / or configuration samples are excluded for which the minimum distance is not present; - providing (S6) at least one possible path (22') as a movement trajectory of the motor vehicle to a control device (16) of the motor vehicle (10) for controlling the autonomous motor vehicle (10) to the target position into the target state.Method according to claim 1, wherein paths whose distance to objects are below a predetermined safety distance value are evaluated worse by the path criterion than paths above the safety distance value.Method according to one of the preceding claims, wherein a speed of the motor vehicle (10) is defined in the movement trajectory as a function of a distance of the motor vehicle (10) from respective objects (24).Method according to one of the preceding claims, wherein the respective state of the motor vehicle (10) comprises at least one orientation of the motor vehicle (10) in the environment and a steering angle angle angle angle, wherein configuration samples (20, 20'. 20"), which are excluded by the orientation of the motor vehicle ( 10) and the steering angle angle angle.Method according to one of the preceding claims, wherein objects (24) in the environment are classified according to low and high objects (24), wherein for high objects (24) the presence of the minimum distance is checked, wherein for low objects (24) the configuration space (18) is divided into a height profile grid with inclination information, wherein for configuration samples (20, 20', 20") which are located in the vicinity of a low object (24) a wheel position of the motor vehicle is determined from the state of the respective configuration samples (20, 20', 20") in relation to the low object (24), wherein depending on the wheel position a lateral distance of a respective wheel (30) to the low object (24) is determined, wherein the possible path (22) and / or the configuration sample for which the lateral distance is below a wheel distance threshold is excluded.Method according to Claim 5, wherein a pass of the low object (24) is checked on the basis of the height profile grid, wherein a pass of the low object (24) is permitted if a height and / or inclination of the low object below a height threshold value is determined from the height profile grids and if an angle (δ) of the wheel position to the low object is within a predefined angle range.Method according to Claim 6, wherein a speed when low objects (24) are traveled over is adapted to a predefined speed value for the creation of a movement trajectory of the motor vehicle (10).Method according to one of Claims 4 to 6, wherein those paths are preferred in which no passing of low objects is provided.Method according to one of the preceding claims, wherein regions around objects (24), in particular tall objects (24), are divided into at least three distance regions (A1, A2, A3), a near region (A1) up to a first predefined distance from the object (24), a middle region (A2) starting from the first predefined distance to a second predefined distance from the object (24), wherein the second distance is greater than the first distance, and a far region (A3) starting from the second predefined distance to a third predefined distance from the object (24), wherein the third distance is greater than the second distance, wherein a validity of the movement trajectory is checked cyclically after the provision of the movement trajectory, and, in the event of a change in the environment, a recalculation of the movement trajectory takes place using the following criteria: - if the motor vehicle (10) is located in the far region (A3) during the recalculation: ◯ determination of a path and / or a movement trajectory which runs in the far region (A3); ◯ if entry into the mid region (A2) is unavoidable, determination of a path and / or a movement trajectory which leads back into the far region (A3); ◯ reduction of a speed as a function of the distance; - if the motor vehicle (10) is located in the mid region (A2) during the recalculation: ◯ determination of a path and / or a movement trajectory which is remote from the object (24) and / or which leads into the far region (A3); ◯ if no path is determined that is remote from the object, stopping the motor vehicle (10); - if the motor vehicle (10) is in the near range (A1) during the recalculation: o stopping the motor vehicle (10).Motor vehicle (10) comprising at least one computing device (14), wherein the computing device is designed to carry out a method according to one of the preceding claims.

Images