Method for planning a target path for a motor vehicle

Abstract

The invention relates to a method for planning a target path for the at least highly automated guidance of a motor vehicle within a parking space from a starting position located within the parking space to a target position located within the parking space, comprising the following steps: Receiving a digital map of the parking lot, where the digital map includes areas whose occupancy status is unknown or within which a dynamic object is located, Enlarging the areas so that the digital map includes the enlarged areas, Planning the target path from the start position to the target position based on the digital map with the enlarged areas, taking the enlarged areas into account, so that the planned target path leads to the enlarged areas from the start position to the target position without collisions. The invention relates to a device, a computer program and a machine-readable storage medium.

Description

[0001] The invention relates to a method for planning a target path for at least highly automated driving of a motor vehicle within a parking space, a device, a computer program and a machine-readable storage medium. State of the art

[0002] The patent specification EP 3 323 697 B1 discloses a method for planning a trajectory for autonomous parking of a motor vehicle in a parking area with multiple parking spaces.

[0003] The published patent application DE 10 2018 008 685 A1 discloses a method for training an artificial neural network.

[0004] The published patent application CN 115 560 771 A discloses a method for planning a path.

[0005] The published patent application CN 115 408 779 A discloses a method for testing an algorithm for a parking assistant. Disclosure of the invention

[0006] The object underlying the invention is to provide a concept for efficiently planning a target path for at least highly automated guidance of a motor vehicle within a parking space from a starting position located within the parking space to a target position located within the parking space.

[0007] This object is achieved by means of the respective subject matter of the independent claims. Advantageous embodiments of the invention are the subject matter of the respective dependent subclaims.

[0008] According to a first aspect, a method is provided for planning a target path for at least highly automated driving of a motor vehicle within a parking space from a starting position located within the parking space to a target position located within the parking space, comprising the following steps: Receiving a digital map of the parking lot, where the digital map includes areas whose occupancy status is unknown or within which a dynamic object is located, Enlarging the areas so that the digital map includes the enlarged areas, Planning the target path from the start position to the target position based on the digital map with the enlarged areas, taking the enlarged areas into account, so that the planned target path leads to the enlarged areas from the start position to the target position without collisions.

[0009] According to a second aspect, a device is provided which is configured to carry out all the steps of the method according to the first aspect.

[0010] According to a third aspect, a computer program is provided, comprising instructions which, when the computer program is executed by a computer, for example by the device according to the second aspect, cause the computer to carry out a method according to the first aspect.

[0011] According to a fourth aspect, a machine-readable storage medium is provided on which the computer program according to the third aspect is stored.

[0012] The invention is based on and incorporates the finding that the above-mentioned problem is solved by using a digital map of the parking lot to plan the target path from the starting position to the destination position of the parking lot. This digital map specifies areas whose occupancy status is unknown or within which a dynamic object is located.

[0013] It is planned that these areas will be enlarged so that the digital map includes the enlarged areas. The target path from the start position to the destination position is now planned in such a way that these enlarged areas are taken into account in the planning, so that the planned target path, i.e. the result of the planning, leads to the enlarged areas from the start position to the destination position without collisions. In other words, a planned target path does not lead through the enlarged areas, i.e. does not cross them, for example. A motor vehicle that drives along such a target path through the parking lot from the start position to the destination position will therefore generally not drive through areas of the parking lot whose occupancy status is unknown or within which a dynamic object is located.This provides, for example, the technical advantage that a collision risk for the motor vehicle with respect to a collision with an object during a journey from the starting position to the target position along or based on the planned target path can be efficiently reduced.

[0014] The planned target path therefore has a high probability that the vehicle can travel from the starting position to the target position without collision.

[0015] The target path can thus be planned efficiently.

[0016] This results in the technical advantage in particular that a concept is provided for the efficient planning of a target path for the at least highly automated driving of a motor vehicle within a parking space from a starting position located within the parking space to a target position located within the parking space.

[0017] The term “at least highly automated control” includes highly automated control, fully automated control and autonomous control.

[0018] This means that the motor vehicle is, for example, highly automated, fully automated or autonomous.

[0019] Highly automated driving corresponds to automation level 3 according to the definition of the Federal Highway Research Institute (BASt). Fully automated driving corresponds to automation level 4 according to the BASt definition. Autonomous driving corresponds to automation level 5 according to SAE (J3016), where SAE stands for "Society of Automotive Engineers."

[0020] The planned target path is thus suitable so that the motor vehicle can be guided or driven from the starting position to the target position based on it, at least in a highly automated manner.

[0021] For example, the vehicle performs an AVP process within the parking space. AVP stands for "Automated Valet Parking," which translates into German as "automatic parking process."

[0022] An AVP process includes, for example, at least highly automated driving of the motor vehicle from a drop zone, also called a drop-off location, to a parking location, and at least highly automated driving of the motor vehicle from a parking location to a pick-up location, also called a pickup zone. At a drop-off location, a driver of the motor vehicle drops off the motor vehicle for an AVP process. At a pick-up location, the motor vehicle is picked up after the AVP process has ended.

[0023] A parking space, as defined in this description, can also be referred to as a parking area and serves as a parking space for motor vehicles. The parking space thus forms, in particular, a contiguous area that includes several parking spaces (in the case of a parking space on private property) or parking bays (in the case of a parking space on public property). According to one embodiment, the parking space can be enclosed by a parking garage. In particular, the parking space is enclosed by a garage.

[0024] An occupancy status is, for example, one of the following occupancy states: occupied, unoccupied, or free. If it is not known whether the area is occupied or unoccupied, then the occupancy status is unknown. Unknown means that it is not known whether the area is free of a dynamic object or not. For example, the occupancy status is unknown because the area of the parking space is not or cannot be detected by an environmental sensor. In other words, there may be areas within the parking space that are not detected or monitored by sensors, so it is not known whether or not there is a dynamic object within the area.

[0025] A dynamic object is to be seen in contrast to a static object. A static object, as described, is an object that is statically arranged within the parking space and cannot move. For example, a static object is part of the parking space's infrastructure, such as a wall or a pillar. A dynamic object is an object that can move, i.e. that can be mobile, even if it is currently stationary, for example. In other words, a parked motor vehicle, i.e. a motor vehicle with a speed of 0 m / s, is a dynamic object insofar as such a motor vehicle can move, i.e. can be dynamic.

[0026] For example, the digital map can specify other areas of the parking lot, or such other areas are included in the digital map. These other areas, for example, identify or include static objects. For example, such other areas represent infrastructure elements of the parking lot, such as pillars, walls, and curbs.

[0027] For example, enlarging the areas results in the other areas being reduced accordingly. For example, the other areas immediately adjacent to the enlarged areas are reduced in size.

[0028] For example, such other zones mark areas of the parking lot that are freely accessible. Thus, for example, increasing the size of the zones will reduce the size of such other zone(s).

[0029] In one embodiment of the method, it is provided that the target path is planned using a BiRRT* algorithm, according to which a first search tree from the start position to the target position is determined based on the digital map with the enlarged areas such that the first search tree is collision-free with the enlarged areas, and according to which a second search tree is determined from the target position to the start position such that the second search tree is collision-free with the enlarged areas, wherein the target path is planned based on the first and the second search tree.

[0030] This provides the technical advantage, for example, that the target path can be planned efficiently.

[0031] The abbreviation “BiRRT*” stands for “Bidirectional Rapidly Exploring Random Trees”.

[0032] In one embodiment of the method, it is provided that an occupancy grid of the parking space is defined, wherein it is provided that a disk is defined in the digital map around each cell of the occupancy grid, which is a cell representing a dynamic object, so that previously free cell(s) are covered or overlapped by the disk.

[0033] This results in the technical advantage, for example, that previously free cells are overdrawn by the disc. This advantageously allows the possible movement of an object at a defined constant speed to be predicted. This prediction can be performed throughout the entire journey of the vehicle for dynamically classified cells and unknown cells. If the vehicle intersects these expanded areas during its journey, the journey is aborted, for example. Therefore, it is so important to consider these areas during path planning to avoid driving too close to unknown areas (which are enlarged during the journey).

[0034] For cells representing static objects (especially walls, curbs), no radial magnification through the disc is performed.

[0035] After defining the slice around each dynamic cell, the map is converted for ease of use. Cells are then either occupied or unoccupied, since dynamics no longer play a role. This enables storage and computational efficiency, as a cell state can then be expressed using Boolean values.

[0036] To calculate the radius r of a disk, it is assumed that the dynamic object occupying the corresponding cell moves with a maximum uniform speed v Objekt in any direction for a prediction time t Prädiktion Under these assumptions, the radius of the disk is calculated, for example, according to the following formula: r=vObject×tPrediction

[0037] The speed v Objekt and / or the prediction time t Prädiktion are particularly parameterizable. For example, t Prädiktion= 1s (the imposed goal of the AVP function is standstill for moving objects within one second). The assumed speed v Objekt is, for example, between 1 m / s and 1.5 m / s and can be parameterized based on empirical values.

[0038] In one embodiment of the method, it is provided that the areas of the digital map are defined as cells of an occupancy grid of the parking lot, so that the enlargement of the areas is an enlargement of the corresponding cells of the occupancy grid, wherein the target path is planned based on the occupancy grid with the enlarged cells.

[0039] This provides the technical advantage, for example, that the target path can be planned efficiently.

[0040] This provides the technical advantage, for example, that the target pose progression can be planned efficiently.

[0041] A target pose of the vehicle is defined, for example, by x, y, φ, and a velocity. For example, a target pose is defined relative to a parking space coordinate system.

[0042] In one embodiment of the method, it is provided that a polygon, in particular a quadrilateral, representing the motor vehicle is defined based on a length and a width of the motor vehicle, wherein it is defined that a potential target path is collision-free if none of the enlarged regions is located within a circumference of the polygon, in particular the quadrilateral, when the polygon moves along the potential target path according to the target pose profile corresponding to the potential target path, wherein it is defined that a potential target path is subject to collision if one of the enlarged regions is located within an incircle of the polygon, in particular the quadrilateral, when the polygon moves along the potential target path according to the target pose profile corresponding to the potential target path.

[0043] This provides the technical advantage, for example, that the collision check can be performed efficiently. Representing the vehicle with a polygon, especially a quadrilateral, provides the technical advantage that the collision check requires less computing power compared to a collision check that considers the actual dimensions or shape of the vehicle for all potential target paths.

[0044] A polygon in the sense of the description is, for example, a quadrilateral, for example a rectangle.

[0045] For example, a safety margin can be added to the length of the motor vehicle and / or the width of the motor vehicle, so that the polygon is determined based on the length and width of the motor vehicle plus (each) a safety margin.

[0046] The respective safety margin can, for example, be fixed or predetermined, or it can be determined specifically for a motor vehicle. The safety margin can, for example, be a percentage based on the width or length.

[0047] In one embodiment of the method, it is provided that if one of the enlarged areas is located outside the incircle but within the circumference of the polygon, in particular the quadrilateral, then a collision check of the potential target path is carried out based on a real shape of the motor vehicle.

[0048] This results in the technical advantage, for example, of efficiently performing collision checks. This means that a collision check based on the actual shape of the vehicle is only performed for unclear cases. "Unclear cases" refer to cases in which the enlarged area is located outside the incircle but still within the circumference of the polygon. In such a case, it is advantageous to use the actual shape of the vehicle for collision checking rather than its representation by a polygon.

[0049] The real shape is described, for example, in the form of a parameter set as another polygon. The parameter set specifies, for example, the position of the vehicle's prominent outer points starting from the vehicle center or rear axle center. Connecting two consecutive points results in the line of the vehicle's contour (2D viewed from a bird's eye view) between these points.

[0050] This parameter set can, for example, be stored on an AVP server and / or dynamically requested from a server of the vehicle manufacturer.

[0051] Regarding the additional polygon, a distinction must be made here from the polygon of the first test step (especially the rectangle). Hence the distinction by "additional." This polygon logically consists of a large number of vertices (on the order of 20-30). A safety margin can also be added to this additional polygon. See also the above comments in connection with the polygon and the safety margin.

[0052] For example, the device is programmed to execute the computer program.

[0053] The method is carried out, for example, by means of the device.

[0054] Device features result analogously from corresponding process features and vice versa. This means that the technical functionalities of the process result from the corresponding technical functionalities of the device and vice versa.

[0055] For example, the method is a computer-implemented method.

[0056] For example, the method includes outputting target path signals representing the planned target path.

[0057] The device comprises, for example, an input configured to receive the digital map of the parking space. The device comprises, for example, a processor configured to plan the desired path or, in addition, to plan the desired pose progression. The device comprises, for example, an output configured to output the desired path signals. The processor comprises, for example, one or more processors.

[0058] The device is, for example, a computer. The device is, for example, implemented in a cloud infrastructure.

[0059] The embodiments and exemplary embodiments described here can be combined with one another in any way, even if this is not explicitly described.

[0060] The invention is explained in more detail below using preferred embodiments. These show: Fig. 1 a flowchart of a method according to the first aspect, Fig. 2 a device according to the second aspect, Fig. 3 a machine-readable storage medium according to the fourth aspect, Fig. 4 a parking lot with areas whose occupancy status is unknown or within which a dynamic object is located, Fig. 5 the parking space according to Fig. 4 with enlarged areas and Fig. 6 to 8 each show an example collision check.

[0061] In the following, the same reference symbols may be used for the same features.

[0062] Fig. 1 shows a flowchart of a method for planning a target path for at least highly automated driving of a motor vehicle within a parking space from a starting position located within the parking space to a target position located within the parking space, comprising the following steps: Receiving 101 a digital map of the parking lot, wherein the digital map includes areas whose occupancy status is unknown or within which a dynamic object is located, Enlarge 103 of the areas so that the digital map includes the enlarged areas, Planning 105 the target path from the start position to the target position based on the digital map with the enlarged areas, taking into account the enlarged areas, so that the planned target path leads collision-free to the enlarged areas from the start position to the target position.

[0063] Fig. 2 shows a device 201 which is configured to carry out all steps of the method according to the first aspect.

[0064] Fig. 3 shows a machine-readable storage medium 301 on which a computer program 303 is stored. The computer program 303 includes instructions that, when executed by a computer, cause the computer program 303 to execute a method according to the first aspect.

[0065] Fig. 4 shows a parking space 401.

[0066] An x, y coordinate system 403 is placed on the parking space 401. The coordinate system 403 includes an x-axis 405 and a y-axis 407. The abscissa of the coordinate system 403 is the x-axis 405. The ordinate of the coordinate system 403 is the y-axis 407. Several areas 409, 411 of the parking space 401 are defined, for which the respective occupancy status is occupied or unknown.

[0067] Furthermore, another area 413 of the parking space is defined, the occupancy status of which is free. Furthermore, other areas 415 of the parking space 401 are defined, which are intended to identify static objects. Furthermore, other areas with the reference symbol 417 are defined, which are also intended to identify static objects. Such static objects include, for example, walls and curbs.

[0068] According to the concept described here, in order to plan a target path from a starting position to a destination position, the areas of a parking space for which the occupancy status is unknown or occupied are enlarged. Fig. 5 such an enlargement of these areas, in this case areas 409, 411. The enlarged areas are in Fig. 5 are additionally designated with reference numerals 501, 503. Reference numeral 501 designates enlarged area 409. Reference numeral 503 designates enlarged area 411.

[0069] Corresponding to the enlarged regions 501, 503, the other regions 413, 415, and 417 are reduced in size or no longer exist. Accordingly, a reduced region 413 is defined, which is additionally identified by the reference numeral 505. Due to the enlargement of the regions 409, 411, the other regions 415, 417 are now encompassed by these enlarged regions and are therefore Fig. 5 is not provided with a reference symbol.

[0070] The planning of the target path is now carried out in such a way that the planned target path runs collision-free to the enlarged areas 501, 503.

[0071] Fig. Figures 6 to 8 each show an example collision check.

[0072] Specifically, an occupancy grid 601 comprising cells 603 is defined. Reference numeral 605 points to a hatching that indicates occupied cells. A motor vehicle is identified by a rectangle with reference numeral 607. Reference numeral 609 points to a circumcircle of rectangle 607. Reference numeral 611 points to an incircle of rectangle 607.

[0073] According to Fig. 6, the occupied cells 605 are located outside the perimeter 609. Therefore, it is determined here that the motor vehicle does not collide with objects within the cells 605. The corresponding pose of the motor vehicle is collision-free with these areas 605.

[0074] Fig. Figure 7 shows the case in which the occupied cells 605 are located outside the incircle 611, but at least partially within the circumcircle 609. This is an ambiguous case, so according to the concept described here, for example, it is intended to perform the collision check based on the actual dimensions or the actual shape of the motor vehicle. In such a case, the motor vehicle is no longer represented by a rectangle for the purpose of performing the collision check.

[0075] Fig. Figure 8 shows the case in which the occupied cells 605 are located within the incircle 611, or at least partially within the incircle 611. Here, it is determined that in such a case, the motor vehicle collides with objects. The corresponding pose is thus subject to collision and not collision-free with the cells 605. QUOTES CONTAINED IN THE DESCRIPTION

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

[0000] EP 3 323 697 B1

[0002] DE 10 2018 008 685 A1

[0003] CN 115 560 771 A

[0004] CN 115 408 779 A

[0005]

Claims

[1] Method for planning a target path for the at least highly automated guidance of a motor vehicle within a parking space (401) from a starting position located within the parking space (401) to a target position located within the parking space (401), comprising the following steps: Receiving (101) a digital map of the parking lot (401), wherein the digital map contains areas (409, 411) whose occupancy status is unknown or within which a dynamic object is located, Enlarging (103) the areas (409, 411) so that the digital map includes the enlarged areas (501, 503), Planning (105) the target path from the starting position to the target position based on the digital map with the enlarged areas (501, 503) taking into account the enlarged areas (501, 503) so that the planned target path leads collision-free to the enlarged areas (501, 503) from the starting position to the target position. [2] The method according to claim 1, wherein the target path is planned using a BiRRT* algorithm, according to which a first search tree from the start position to the target position is determined based on the digital map with the enlarged areas (501, 503) such that the first search tree is collision-free to the enlarged areas (501, 503), and according to which a second search tree is determined from the target position to the start position such that the second search tree is collision-free to the enlarged areas (501, 503), wherein the target path is planned based on the first and the second search tree. [3] Method according to claim 1 or 2, wherein an occupancy grid of the parking space (401) is defined, wherein it is provided that around each cell of the occupancy grid, which is a cell representing a dynamic object, a disk is defined in the digital map, so that previously free cell(s) are covered or overlapped by the disk. [4] Method according to one of the preceding claims, wherein the planning of the target path comprises planning a course of a target pose of the motor vehicle along the target path to be planned such that the planned target pose course is collision-free with the enlarged areas (501, 503). [5] Method according to claim 4, wherein a polygon, in particular a quadrilateral (607) representing the motor vehicle is defined based on a length and a width of the motor vehicle, wherein it is defined that a potential target path is collision-free if none of the enlarged regions (501, 503) is located within a circumcircle (609) of the polygon, in particular of the quadrilateral (607), when the polygon moves along the potential target path according to the target pose profile corresponding to the potential target path, wherein it is defined that a potential target path is subject to collision if one of the enlarged regions (501, 503) is located within an incircle (611) of the polygon, in particular of the quadrilateral (607), when the polygon moves along the potential target path according to the target pose profile corresponding to the potential target path. [6] Method according to claim 5, wherein, if one of the enlarged areas (501, 503) is located outside the incircle (611) but within the circumcircle (609) of the polygon, in particular the quadrangle (607), then a collision check of the potential target path is carried out based on a real shape of the motor vehicle. [7] Device (201) which is arranged to carry out all the steps of the method according to one of the preceding claims. [8] Computer program (303) comprising instructions which, when the computer program (303) is executed by a computer, cause the computer to carry out a method according to one of claims 1 to 6. [9] Machine-readable storage medium (301) on which the computer program (303) according to claim 8 is stored.

Images