Vehicle path planning method and device

Abstract

The invention provides a vehicle path planning method and device. The method comprises the following steps: acquiring vehicle parameters, environment sensing data, a path starting point and a path ending point; generating an upper-layer obstacle grid map and a lower-layer obstacle grid map based on the vehicle parameters and the environment perception data; performing collision detection based on the vehicle parameters in the upper-layer obstacle grid map and the lower-layer obstacle grid map to obtain an upper-layer collision detection result and a lower-layer collision detection result; combining the upper-layer collision detection result with the lower-layer collision detection result to generate a planned path from the path starting point to the path ending point; the planned path comprises obstacle-avoiding nodes for bypassing the upper-layer obstacle and obstacle-crossing nodes for crossing the lower-layer obstacle. Therefore, efficient path searching in the multi-obstacle complex scene is realized, and the vehicle has better trafficability in the multi-obstacle complex scene.

Description

Technical Field

[0001] This invention relates to the field of motion planning algorithm technology, and in particular to a vehicle path planning method and apparatus. Background Technology

[0002] With the rapid development of artificial intelligence, advanced sensing technology, and intelligent control, the level of vehicle intelligence has been significantly improved. Among these, vehicle path planning, as a core module of intelligent vehicle technology, undertakes the critical task of generating safe and efficient paths in complex dynamic environments. It needs to meet vehicle kinematic constraints (such as minimum turning radius and acceleration limits) and ensure that the vehicle smoothly travels from the starting point to the target location, making it one of the current research hotspots in academia.

[0003] Existing path planning algorithms typically determine collisions by judging whether the vehicle's grid overlaps with the obstacle grid using a two-dimensional projection plane—if overlap exists, it's considered a collision, thus tending to move the vehicle away from obstacles. However, collisions within a two-dimensional projection plane cannot fully reflect the real-world collision situation in three-dimensional space. For example, in a mining scenario, when faced with obstacles such as low pebbles, mounds of earth, or pits, a vehicle could more efficiently pass by crossing them, while a detour strategy is not only inefficient but may also lead to planning failure in scenarios with multiple obstacles or narrow passages; choosing to directly drive over these low obstacles could severely damage the vehicle's suspension system.

[0004] Therefore, how to more accurately assess collision risks in three-dimensional space and formulate more reasonable obstacle avoidance or crossing strategies for different types of obstacles such as small gravel and mounds of earth has become a key issue that current vehicle path planning technology urgently needs to address. Summary of the Invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art, and proposes a vehicle route planning method and apparatus.

[0006] In a first aspect, embodiments of the present invention provide a vehicle route planning method, comprising:

[0007] Acquire vehicle parameters, environmental perception data, path start point, and path end point;

[0008] Based on the vehicle parameters and the environmental perception data, an upper-layer obstacle grid map and a lower-layer obstacle grid map are generated.

[0009] Collision detection is performed based on the vehicle parameters in the upper obstacle grid map and the lower obstacle grid map respectively to obtain the upper collision detection result and the lower collision detection result.

[0010] Combining the upper-layer collision detection results and the lower-layer collision detection results, a planned path is generated from the path start point to the path end point; the planned path includes obstacle-avoidance nodes that bypass upper-layer obstacles and obstacle-crossing nodes that cross lower-layer obstacles.

[0011] Optionally, the environmental perception data includes 3D point cloud data; based on the vehicle parameters and the environmental perception data, an upper-layer obstacle grid map and a lower-layer obstacle grid map are generated, including:

[0012] The three-dimensional point cloud data is projected onto a two-dimensional plane to form a grid map, where each grid records the height information of the point cloud within it.

[0013] Using the vehicle chassis height in the vehicle parameters as a classification threshold, obstacle grids in the grid map with a height greater than or equal to the classification threshold are classified as the upper-layer obstacle grid map, and obstacle grids with a height less than the classification threshold are classified as the lower-layer obstacle grid map.

[0014] Optionally, the environmental perception data includes obstacle data; collision detection is performed based on the vehicle parameters in the upper obstacle grid map and the lower obstacle grid map respectively to obtain upper-layer collision detection results and lower-layer collision detection results, including:

[0015] Based on the vehicle parameters, the outer contour of the vehicle formed by the expansion of the vehicle body and the inner contour of the vehicle defined by the wheel positions are determined.

[0016] In the upper obstacle grid map, it is determined whether the outer contour of the vehicle overlaps with the obstacle grid to obtain the upper collision detection result;

[0017] In the lower-level obstacle grid map, three-dimensional collision detection is performed based on the vehicle's outer contour, the vehicle's inner contour, and the three-dimensional envelope of the lower-level obstacles in the obstacle data to obtain the lower-level collision detection result.

[0018] Optionally, in the lower-layer obstacle grid map, three-dimensional collision detection is performed based on the vehicle's outer contour, the vehicle's inner contour, and the three-dimensional envelope of the lower-layer obstacles in the obstacle data to obtain the lower-layer collision detection result, including:

[0019] Based on the three-dimensional dimensions of the lower layer obstacle, an obstacle cube envelope is established;

[0020] If the obstacle cube envelope is not present in the outer contour of the vehicle, it is determined that there is no collision.

[0021] If the obstacle cube envelope exists within the vehicle's outer contour, the lower-level collision detection result is determined based on the type of the obstacle cube envelope.

[0022] Optionally, if the obstacle cube envelope exists within the vehicle's outer contour, the lower-level collision detection result is determined based on the type of the obstacle cube envelope, including:

[0023] If the type of the obstacle cube envelope is a pit, then detect whether the obstacle cube envelope collides with the inner contour of the vehicle to obtain the lower-level collision detection result;

[0024] If the type of the obstacle cube envelope is not a pit, then the lower-level collision detection result is determined based on the height of the obstacle cube envelope and the vehicle parameters.

[0025] Optionally, if the obstacle cube envelope is not a pit, the lower-level collision detection result is determined based on the height of the obstacle cube envelope and the vehicle parameters, including:

[0026] Determine whether the height difference between the vehicle's minimum ground clearance and the envelope of the obstacle cube is less than a safety threshold;

[0027] If not, then the lower-level collision detection result is determined to be a collision;

[0028] If yes, then a preset judgment formula is used to determine whether the entire envelope of the obstacle cube is within the inner contour of the vehicle; if yes, then the lower-level collision detection result is determined to be no collision; if no, then the lower-level collision detection result is determined to be a collision.

[0029] Optionally, the judgment formula is specifically as follows:

[0030] ;

[0031] in, , , , These are the four vertices of the vehicle's inner contour. The point corresponding to the envelope of the obstacle cube.

[0032] Secondly, embodiments of the present invention provide a vehicle route planning device, comprising:

[0033] The acquisition module is used to acquire vehicle parameters, environmental perception data, path start point, and path end point.

[0034] The map generation module is used to generate an upper-layer obstacle grid map and a lower-layer obstacle grid map based on the vehicle parameters and the environmental perception data.

[0035] The detection module is used to perform collision detection based on the vehicle parameters in the upper obstacle grid map and the lower obstacle grid map respectively, and obtain the upper collision detection result and the lower collision detection result.

[0036] The planning module combines the upper-layer collision detection results and the lower-layer collision detection results to generate a planned path from the path start point to the path end point; the planned path includes obstacle-avoidance nodes that bypass upper-layer obstacles and obstacle-crossing nodes that cross lower-layer obstacles.

[0037] Thirdly, the present invention provides an electronic device including a processor and a memory, the memory storing computer-readable instructions that, when executed by the processor, perform the steps of the method provided in the first aspect above.

[0038] Fourthly, the present invention provides a storage medium having a computer program stored thereon, which, when executed by a processor, performs the steps of the method provided in the first aspect above.

[0039] Fifthly, the present invention provides a computer program product comprising a computer program that, when executed by a processor, performs the steps of the method provided in the first aspect above.

[0040] As can be seen from the above technical solutions, the present invention has the following advantages:

[0041] This invention provides a vehicle path planning method and apparatus. The method includes: acquiring vehicle parameters, environmental perception data, a path start point, and a path end point; generating an upper-layer obstacle grid map and a lower-layer obstacle grid map based on the vehicle parameters and the environmental perception data; performing collision detection in the upper-layer obstacle grid map and the lower-layer obstacle grid map respectively, based on the vehicle parameters, to obtain upper-layer collision detection results and lower-layer collision detection results; combining the upper-layer collision detection results and the lower-layer collision detection results to generate a planned path from the path start point to the path end point; the planned path includes obstacle avoidance nodes that bypass upper-layer obstacles and obstacle crossing nodes that cross lower-layer obstacles. By constructing upper and lower-layer obstacle grid maps based on vehicle parameters and combined with environmental perception data, and performing collision detection on each, the planned path is determined based on the collision detection results. This enables efficient path search in complex multi-obstacle scenarios, resulting in better vehicle passability in such scenarios. Attached Figure Description

[0042] Figure 1 This is a flowchart illustrating a vehicle routing method according to a first embodiment of the present invention.

[0043] Figure 2 This is a flowchart illustrating a second embodiment of the vehicle routing method of the present invention;

[0044] Figure 3 This is a schematic diagram of obstacle height detection in a second embodiment of the vehicle path planning method of the present invention;

[0045] Figure 4 This is a schematic outline diagram of a second embodiment of the vehicle routing method of the present invention;

[0046] Figure 5 This is a schematic diagram illustrating the generation of the planned path in a second embodiment of the vehicle path planning method of the present invention;

[0047] Figure 6 This is a structural block diagram of an embodiment of the vehicle routing device of the present invention;

[0048] Figure 7 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0049] To enable those skilled in the art to better understand the technical solutions of the present invention, exemplary embodiments of the present invention are described below in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to aid understanding. These should be considered merely exemplary. Therefore, those skilled in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0050] Where there is no conflict, the various embodiments of the present invention and the features thereof may be combined with each other.

[0051] As used herein, the term “and / or” includes any and all combinations of one or more related enumerated entries.

[0052] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used herein, the singular forms “a” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will also be understood that when the terms “comprising” and / or “made of” are used in this specification, the presence of the stated feature, integral, step, operation, element, and / or component is specified, but the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof is not excluded. Terms such as “connected” or “linked” are not limited to physical or mechanical connections but can include electrical connections, whether direct or indirect.

[0053] Unless otherwise specified, all terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having the meaning consistent with their meaning in the context of the relevant art and the invention, and will not be interpreted as having an idealized or overly formal meaning unless expressly so defined herein.

[0054] In the technical solution of this invention, the collection, storage, use, processing, transmission, provision, and disclosure of user personal information all comply with relevant laws and regulations and do not violate public order and good morals. The use of user data in this technical solution follows relevant national laws and regulations (e.g., the "Information Security Technology - Personal Information Security Specification"). For example: appropriate measures are taken for personal information access control; restrictions are imposed on the display of personal information; the purpose of using personal information does not exceed the scope of direct or reasonable association; and explicit identity targeting is eliminated when using personal information to avoid precisely locating a specific individual.

[0055] In the related art, (the related art is analyzed, and the technical problem solved by this application is pointed out)

[0056] To address at least one of the technical problems existing in the aforementioned related technologies, the present invention provides a control method for displaying vehicle driving range. Figure 1 This is a flowchart illustrating a vehicle routing method provided in an embodiment of the present invention; the method includes:

[0057] Step S101: Obtain vehicle parameters, environmental perception data, path start point, and path end point;

[0058] Vehicle parameter acquisition: Extract various vehicle parameters from the vehicle's control system or configuration file, such as vehicle chassis height, minimum ground clearance, wheel width, wheel length, track width, and vehicle dimensions. These parameters are used for subsequent map building and collision detection.

[0059] In this embodiment, environmental information, including 3D point cloud data and obstacle data, is collected by sensors such as LiDAR and cameras installed on the vehicle. The 3D point cloud data contains the 3D coordinates of objects in the environment, while the obstacle data records the location and type of obstacles. Simultaneously, based on user input or task requirements, the vehicle's starting and target positions are determined as the start and end points for path planning.

[0060] Step S102: Based on the vehicle parameters and the environmental perception data, generate an upper-layer obstacle grid map and a lower-layer obstacle grid map;

[0061] In this embodiment, obstacle information of roads in a high-precision map is extracted to establish an initial grid map. The 3D point cloud data from the current frame of the LiDAR is projected onto the grid map. Each grid contains several 3D points, which retain information such as height and intensity. Each grid is traversed, and its attributes are determined based on the information of the 3D points within it, such as the number of points, maximum height, and minimum height. If there are no obstacles within the grid, it is considered a movable area and assigned a value of 0; if there are obstacles within the grid, it is considered a non-movable area and assigned a value of 1.

[0062] In the specific implementation, obstacles in the grid map are divided based on the vehicle chassis height. Obstacle grids with a height greater than or equal to the vehicle chassis height are classified as upper-layer obstacle grid maps, while obstacle grids with a height less than the vehicle chassis height are classified as lower-layer obstacle grid maps.

[0063] Step S103: Based on the vehicle parameters, collision detection is performed in the upper obstacle grid map and the lower obstacle grid map respectively to obtain the upper collision detection result and the lower collision detection result.

[0064] In this embodiment of the application, collision detection is performed on the upper obstacle grid map and the lower obstacle grid map respectively to obtain the upper collision detection result and the lower collision detection result.

[0065] Step S104: Combining the upper-layer collision detection results and the lower-layer collision detection results, a planned path from the path start point to the path end point is generated; the planned path includes obstacle-avoiding nodes that bypass upper-layer obstacles and obstacle-crossing nodes that cross lower-layer obstacles.

[0066] In this embodiment, a hybrid A* algorithm (also known as a hybrid Astar algorithm) can be used to combine collision detection results from upper and lower layers to expand the search for nodes. During the search process, a path is generated that includes nodes that expand in various ways, such as obstacle avoidance and obstacle crossing. Obstacle crossing nodes are used to cross lower-level obstacles, while conventional obstacle avoidance nodes are used to bypass upper-level obstacles. By continuously expanding and filtering child nodes, a planned path from the path start point to the path end point that conforms to vehicle kinematic constraints is generated.

[0067] This invention provides a vehicle path planning method, comprising: acquiring vehicle parameters, environmental perception data, a path start point, and a path end point; generating an upper-layer obstacle grid map and a lower-layer obstacle grid map based on the vehicle parameters and the environmental perception data; performing collision detection in the upper-layer obstacle grid map and the lower-layer obstacle grid map respectively, based on the vehicle parameters, to obtain upper-layer collision detection results and lower-layer collision detection results; combining the upper-layer collision detection results and the lower-layer collision detection results to generate a planned path from the path start point to the path end point; the planned path includes obstacle avoidance nodes that bypass upper-layer obstacles and obstacle crossing nodes that cross lower-layer obstacles. By constructing upper and lower-layer obstacle grid maps based on vehicle parameters and combined with environmental perception data, and performing collision detection on each, the planned path is determined based on the collision detection results, enabling efficient path search in complex multi-obstacle scenarios, thus improving the vehicle's passability in such scenarios.

[0068] This invention also provides a vehicle route planning method; please refer to [link / reference]. Figure 2 , Figure 2 This is a flowchart illustrating a second embodiment of the vehicle routing method of the present invention, the steps of which include:

[0069] Step S201: Obtain vehicle parameters, environmental perception data, path start point, and path end point; the environmental perception data includes 3D point cloud data and obstacle data;

[0070] Step S202: Project the three-dimensional point cloud data onto a two-dimensional plane to form a grid map, wherein each grid records the height information of the point cloud within it;

[0071] In this embodiment, a two-dimensional grid map is established, and the size of the grid and the extent of the map are determined. The three-dimensional point cloud data collected by the LiDAR is projected onto this two-dimensional plane, with each three-dimensional point corresponding to a specific grid cell. Each grid cell records the height information of its internal point cloud, such as maximum and minimum height, for subsequent determination of the grid cell's attributes.

[0072] Step S203: Using the vehicle chassis height in the vehicle parameters as the classification threshold, the obstacle grids in the grid map with a height greater than or equal to the classification threshold are classified as the upper-layer obstacle grid map, and the obstacle grids with a height less than the classification threshold are classified as the lower-layer obstacle grid map.

[0073] In this embodiment, each grid cell in the grid map is traversed to obtain its recorded point cloud height information. Based on the vehicle chassis height, grid cells with heights greater than or equal to a threshold are classified as upper-layer obstacle grid cells, and grid cells with heights less than the threshold are classified as lower-layer obstacle grid cells.

[0074] Step S204: Based on the vehicle parameters, determine the vehicle outer contour formed by the vehicle body expansion and the vehicle inner contour defined by the wheel positions.

[0075] In this embodiment, the vehicle body is expanded based on its dimensions and a preset safety threshold to generate the vehicle's outer contour, ensuring a certain safety buffer space during vehicle operation. The vehicle's inner contour is determined based on the wheel positions and a reasonably designed safety threshold; this inner contour represents the vehicle's safe traversable area.

[0076] Step S205: In the upper obstacle grid map, determine whether the vehicle's outer contour overlaps with the obstacle grid to obtain the upper collision detection result;

[0077] In this embodiment, the vehicle's outer contour is compared with the obstacle grid in the upper-layer obstacle grid map of the current node. If the vehicle's outer contour overlaps with any obstacle grid, a collision is determined, and the current node becomes unusable; if they do not overlap, no collision is determined, and the next layer detection continues.

[0078] Step S206: In the lower obstacle grid map, perform three-dimensional collision detection based on the vehicle outer contour, the vehicle inner contour and the three-dimensional envelope of the lower obstacle in the obstacle data to obtain the lower collision detection result.

[0079] Specifically, this includes: establishing an obstacle cube envelope based on the three-dimensional dimensions of the obstacle beneath the barrier;

[0080] If the obstacle cube envelope is not present in the outer contour of the vehicle, it is determined that there is no collision.

[0081] If the obstacle cube envelope exists within the vehicle's outer contour, the lower-level collision detection result is determined based on the type of the obstacle cube envelope.

[0082] In this embodiment, if the obstacle cube envelope is a pit, then it is detected whether the obstacle cube envelope collides with the inner contour of the vehicle to obtain the lower-level collision detection result; if the obstacle cube envelope is not a pit, then the lower-level collision detection result is determined based on the height of the obstacle cube envelope and the vehicle parameters.

[0083] In an optional embodiment, if the obstacle cube envelope is not a pit, the lower-level collision detection result is determined based on the height of the obstacle cube envelope and the vehicle parameters, including:

[0084] Determine whether the height difference between the vehicle's minimum ground clearance and the envelope of the obstacle cube is less than a safety threshold;

[0085] If not, then the lower-level collision detection result is determined to be a collision;

[0086] If yes, then a preset judgment formula is used to determine whether the entire envelope of the obstacle cube is within the inner contour of the vehicle; if yes, then the lower-level collision detection result is determined to be no collision; if no, then the lower-level collision detection result is determined to be a collision.

[0087] The specific judgment formula is as follows:

[0088] ;

[0089] in, , , , These are the four vertices of the vehicle's inner contour. The point corresponding to the envelope of the obstacle cube.

[0090] In this embodiment, the maximum cubic envelope of the lower-level obstacle is constructed based on its three-dimensional size information for collision detection.

[0091] In the specific implementation, it is determined whether there is an obstacle envelope within the vehicle's outer contour: if there is no obstacle envelope, it is determined as no collision. If there is an obstacle envelope within the outer contour, a classification judgment is performed: when the obstacle type is a pit, collision detection is directly performed between the pit obstacle envelope and the vehicle's inner contour; if a collision occurs, it is determined as a collision; otherwise, it is determined as no collision. When the obstacle type is not a pit, it is first determined whether the obstacle height is less than the vehicle's minimum ground clearance: if the obstacle height is not less than the vehicle's minimum ground clearance, it is determined as a collision between the vehicle and the obstacle. If the obstacle height detection fails... When the vehicle collides with the obstacle; when the obstacle height detection passes... If so, continue to detect whether the vehicle's inner contour collides with the obstacle's envelope, such as... Figure 3 As shown.

[0092] The vehicle is considered to be in a non-collision state only if the entire obstacle envelope lies within the vehicle's inner contour; otherwise, a collision is considered to have occurred. The vehicle's inner contour is generated based on a safety threshold designed with reasonable wheel positions, while the vehicle's outer contour is generated by expanding the vehicle body according to this safety threshold. The vehicle's inner contour represents its safe traversable area. Figure 4 As shown, the black areas represent obstacles, and the vehicle's inner outline is formed by... , , and The vehicle's main body outline is a quadrilateral ABCD, while the outer outline is composed of dashed quadrilaterals. Indicates the width of the vehicle's inner profile. , and These represent the width, length, and height of the obstacle, respectively. and Indicates the wheel width and wheel length. Indicates wheelbase. Indicates the vehicle's minimum ground clearance. This indicates the safety threshold for the expansion of the vehicle's outer contour. This represents the safety threshold related to the maximum steering position of the front wheels. This represents the safety threshold related to the vehicle's minimum ground clearance.

[0093] In refined 3D collision detection, the collision relationship between obstacle envelopes and vehicle contours can be determined by the inclusion relationship between envelope points and rectangles. The determination formula is as follows:

[0094] ;

[0095] If the relationships between all the envelope points of an obstacle and the vehicle's inner contour satisfy the above formula, then the obstacle can be determined to be located within the vehicle's inner contour. Combining a two-layer collision detection strategy, the hybrid A* algorithm can generate paths that include various forms of obstacle-around and obstacle-crossing extension nodes, such as... Figure 5 As shown. Where O' is the parent node, For obstacle crossing nodes, This is a standard obstacle avoidance node. A path conforming to vehicle kinematic constraints is generated through an extended search of its child nodes.

[0096] Step S207: Using the hybrid A* algorithm, combining the upper-layer collision detection results and the lower-layer collision detection results, a planned path from the starting point of the path to the ending point of the path is generated; the planned path includes obstacle-avoiding nodes that bypass the upper-layer obstacles and obstacle-crossing nodes that cross the lower-layer obstacles.

[0097] This invention provides a vehicle path planning method, comprising: acquiring vehicle parameters, environmental perception data, a path start point, and a path end point; generating an upper-layer obstacle grid map and a lower-layer obstacle grid map based on the vehicle parameters and the environmental perception data; performing collision detection based on the vehicle parameters in the upper-layer obstacle grid map and the lower-layer obstacle grid map respectively, to obtain upper-layer collision detection results and lower-layer collision detection results; and generating a planned path from the path start point to the path end point by combining the upper-layer collision detection results and the lower-layer collision detection results using a hybrid A* algorithm; the planned path includes obstacle avoidance nodes that bypass upper-layer obstacles and obstacle crossing nodes that cross lower-layer obstacles. Based on vehicle parameters and combined with environmental perception data, a two-layer obstacle grid map is constructed, and collision detection is performed separately. Then, the planned path is determined by combining the collision detection results with the hybrid A* algorithm. This intelligent vehicle path planning method, which has two obstacle avoidance forms, namely detour and cross-traffic, can flexibly handle various obstacles and make reasonable avoidances based on their characteristics. This allows for more efficient planning of the optimal path that conforms to human driving behavior habits, making the search path more flexible and improving the stability and safety of vehicle driving.

[0098] This invention also provides a vehicle route planning device; please refer to [link / reference]. Figure 7 , Figure 7 This is a structural block diagram of an embodiment of a vehicle routing device according to the present invention. The device includes:

[0099] The acquisition module 301 is used to acquire vehicle parameters, environmental perception data, path start point and path end point;

[0100] The map generation module 302 is used to generate an upper-layer obstacle grid map and a lower-layer obstacle grid map based on the vehicle parameters and the environmental perception data.

[0101] The detection module 303 is used to perform collision detection based on the vehicle parameters in the upper obstacle grid map and the lower obstacle grid map respectively, and obtain the upper collision detection result and the lower collision detection result.

[0102] The planning module 304 is used to combine the upper-layer collision detection results and the lower-layer collision detection results to generate a planned path from the path start point to the path end point; the planned path includes obstacle-avoidance nodes that bypass the upper-layer obstacles and obstacle-crossing nodes that cross the lower-layer obstacles.

[0103] In an optional embodiment, the environmental perception data includes three-dimensional point cloud data; the map generation module 302 includes:

[0104] The projection submodule is used to project the three-dimensional point cloud data onto a two-dimensional plane to form a grid map, wherein each grid records the height information of the point cloud within it.

[0105] The map generation table module is used to classify obstacle grids in the grid map whose height is greater than or equal to the classification threshold as the upper-layer obstacle grid map, and obstacle grids whose height is less than the classification threshold as the lower-layer obstacle grid map, using the vehicle chassis height in the vehicle parameters as the classification threshold.

[0106] In an optional embodiment, the environmental perception data includes obstacle data; the detection module 303 includes:

[0107] The contour determination submodule is used to determine the vehicle's outer contour formed by the vehicle body expansion and the vehicle's inner contour defined by the wheel positions, based on the vehicle parameters.

[0108] The upper-level collision result determination submodule is used to determine whether the vehicle's outer contour overlaps with the obstacle grid in the upper-level obstacle grid map, and to obtain the upper-level collision detection result;

[0109] The lower-level collision result determination submodule is used to perform three-dimensional collision detection in the lower-level obstacle grid map based on the vehicle's outer contour, the vehicle's inner contour, and the three-dimensional envelope of the lower-level obstacles in the obstacle data, and obtain the lower-level collision detection result.

[0110] In an optional embodiment, the lower-level collision result determination submodule includes:

[0111] A cube envelope establishment unit is used to establish a cube envelope of the obstacle based on the three-dimensional size information of the obstacle in the lower layer.

[0112] A collision-free determination unit is used to determine that there is no collision when the obstacle cube envelope does not exist in the outer contour of the vehicle.

[0113] The lower-level collision result determination unit is used to determine the lower-level collision detection result based on the type of the obstacle cube envelope when the obstacle cube envelope exists in the outer contour of the vehicle.

[0114] In an optional embodiment, the lower-level collision result determination unit includes:

[0115] The first lower-level collision detection result determination subunit is used to detect whether the obstacle cube envelope collides with the inner contour of the vehicle when the type of the obstacle cube envelope is a pit, and to obtain the lower-level collision detection result.

[0116] The second lower-level collision detection result determination subunit is used to determine the lower-level collision detection result based on the height of the obstacle cube envelope and the vehicle parameters when the obstacle cube envelope is not a pit.

[0117] In an optional embodiment, the second lower-level collision detection result determination subunit is specifically used to: determine whether the height difference between the vehicle's minimum ground clearance and the obstacle cube envelope is less than a safety threshold; if not, determine that the lower-level collision detection result is a collision; if yes, determine whether the obstacle cube envelope is entirely within the vehicle's inner contour using a preset judgment formula; if yes, determine that the lower-level collision detection result is no collision; if no, determine that the lower-level collision detection result is a collision.

[0118] In an optional embodiment, the determination formula is specifically as follows:

[0119] ;

[0120] in, , , , These are the four vertices of the vehicle's inner contour.

[0121] Based on the same inventive concept, embodiments of the present invention also provide an electronic device. Figure 5 This is a structural block diagram of an electronic device provided in an embodiment of the present invention. Figure 5 As shown, an embodiment of the present invention provides an electronic device including: one or more processors 101, a memory 102, and one or more I / O interfaces 103. The memory 102 stores one or more programs, which, when executed by the one or more processors, enable the one or more processors to implement any of the vehicle routing methods described in the above embodiments; the one or more I / O interfaces 103 are connected between the processors and the memory, configured to enable information interaction between the processors and the memory.

[0122] The processor 101 is a device with data processing capabilities, including but not limited to a central processing unit (CPU); the memory 102 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and flash memory (FLASH); the I / O interface (read / write interface) 103 is connected between the processor 101 and the memory 102, and can realize information interaction between the processor 101 and the memory 102, including but not limited to a data bus (Bus).

[0123] In some embodiments, the processor 101, memory 102, and I / O interface 103 are interconnected via bus 104, and thus connected to other components of the computing device.

[0124] In some embodiments, the one or more processors 101 include a field-programmable gate array.

[0125] This invention also provides a computer-readable medium. The computer-readable medium stores a computer program, which, when executed by a processor, implements the steps of any of the vehicle routing methods described in the above embodiments. The computer-readable storage medium may be volatile or non-volatile.

[0126] This invention also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code. When the computer-readable code is run in the processor of an electronic device, the processor in the electronic device executes the above-described vehicle routing method.

[0127] Those skilled in the art will understand that all or some of the steps, systems, and apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software can be distributed on a computer-readable storage medium, which may include computer storage media (or non-transitory media) and communication media (or transient media).

[0128] As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, such as computer-readable program instructions, data structures, program modules, or other data. Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technologies, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, it is known to those skilled in the art that communication media typically contain computer-readable program instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0129] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0130] The computer program instructions used to perform the operations of this invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuitry, such as programmable logic circuitry, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), is personalized by utilizing state information from the computer-readable program instructions. This electronic circuitry can execute the computer-readable program instructions to implement various aspects of the invention.

[0131] The computer program product described herein can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0132] Various aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0133] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0134] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0135] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction, which contains one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those shown in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0136] Example embodiments have been disclosed herein, and while specific terminology has been used, it is for illustrative purposes only and should be construed as such, and is not intended to be limiting. In some instances, it will be apparent to those skilled in the art that features, characteristics, and / or elements described in conjunction with particular embodiments may be used alone, or in combination with features, characteristics, and / or elements described in conjunction with other embodiments, unless otherwise expressly indicated. Therefore, those skilled in the art will understand that various changes in form and detail may be made without departing from the scope of the invention as set forth in the appended claims.

Claims

1. A vehicle route planning method, characterized in that, include: Acquire vehicle parameters, environmental perception data, path start point, and path end point; Based on the vehicle parameters and the environmental perception data, an upper-layer obstacle grid map and a lower-layer obstacle grid map are generated. Collision detection is performed based on the vehicle parameters in the upper obstacle grid map and the lower obstacle grid map respectively to obtain the upper collision detection result and the lower collision detection result. By combining the upper-layer collision detection results and the lower-layer collision detection results, a planned path is generated from the starting point of the path to the ending point of the path; The planned path includes obstacle-avoidance nodes that bypass upper-level obstacles and obstacle-crossing nodes that cross lower-level obstacles.

2. The vehicle routing method according to claim 1, characterized in that, The environmental perception data includes 3D point cloud data; based on the vehicle parameters and the environmental perception data, an upper-layer obstacle grid map and a lower-layer obstacle grid map are generated, including: The three-dimensional point cloud data is projected onto a two-dimensional plane to form a grid map, where each grid records the height information of the point cloud within it. Using the vehicle chassis height in the vehicle parameters as a classification threshold, obstacle grids in the grid map with a height greater than or equal to the classification threshold are classified as the upper-layer obstacle grid map, and obstacle grids with a height less than the classification threshold are classified as the lower-layer obstacle grid map.

3. The vehicle routing method according to claim 1 or 2, characterized in that, The environmental perception data includes obstacle data; collision detection is performed based on the vehicle parameters in the upper obstacle grid map and the lower obstacle grid map respectively, to obtain upper-layer collision detection results and lower-layer collision detection results, including: Based on the vehicle parameters, the outer contour of the vehicle formed by the expansion of the vehicle body and the inner contour of the vehicle defined by the wheel positions are determined. In the upper obstacle grid map, it is determined whether the outer contour of the vehicle overlaps with the obstacle grid to obtain the upper collision detection result; In the lower-level obstacle grid map, three-dimensional collision detection is performed based on the vehicle's outer contour, the vehicle's inner contour, and the three-dimensional envelope of the lower-level obstacles in the obstacle data to obtain the lower-level collision detection result.

4. The vehicle routing method according to claim 3, characterized in that, In the lower-layer obstacle grid map, three-dimensional collision detection is performed based on the vehicle's outer contour, the vehicle's inner contour, and the three-dimensional envelope of the lower-layer obstacles in the obstacle data to obtain the lower-layer collision detection results, including: Based on the three-dimensional dimensions of the lower layer obstacle, an obstacle cube envelope is established; If the obstacle cube envelope is not present in the outer contour of the vehicle, it is determined that there is no collision. If the obstacle cube envelope exists within the vehicle's outer contour, the lower-level collision detection result is determined based on the type of the obstacle cube envelope.

5. The vehicle routing method according to claim 4, characterized in that, If the obstacle cube envelope exists within the vehicle's outer contour, then the lower-level collision detection result is determined based on the type of the obstacle cube envelope, including: If the type of the obstacle cube envelope is a pit, then detect whether the obstacle cube envelope collides with the inner contour of the vehicle to obtain the lower-level collision detection result; If the type of the obstacle cube envelope is not a pit, then the lower-level collision detection result is determined based on the height of the obstacle cube envelope and the vehicle parameters.

6. The vehicle routing method according to claim 3, characterized in that, If the obstacle cube envelope is not a pit, then the lower-level collision detection result is determined based on the height of the obstacle cube envelope and the vehicle parameters, including: Determine whether the height difference between the vehicle's minimum ground clearance and the envelope of the obstacle cube is less than a safety threshold; If not, then the lower-level collision detection result is determined to be a collision; If yes, then a preset judgment formula is used to determine whether the entire envelope of the obstacle cube is within the inner contour of the vehicle; if yes, then the lower-level collision detection result is determined to be no collision; if no, then the lower-level collision detection result is determined to be a collision.

7. The vehicle routing method according to claim 6, characterized in that, The specific formula for determining this is: ； in, , , , These are the four vertices of the vehicle's inner contour. The point corresponding to the envelope of the obstacle cube.

8. A vehicle route planning device, characterized in that, include: The acquisition module is used to acquire vehicle parameters, environmental perception data, path start point, and path end point. The map generation module is used to generate an upper-layer obstacle grid map and a lower-layer obstacle grid map based on the vehicle parameters and the environmental perception data. The detection module is used to perform collision detection based on the vehicle parameters in the upper obstacle grid map and the lower obstacle grid map respectively, and obtain the upper collision detection result and the lower collision detection result. The planning module combines the upper-layer collision detection results and the lower-layer collision detection results to generate a planned path from the path start point to the path end point. The planned path includes obstacle-avoidance nodes that bypass upper-level obstacles and obstacle-crossing nodes that cross lower-level obstacles.

9. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in any one of claims 1 to 7.

10. A computer-readable medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images