A target region determination method and apparatus, electronic device, and storage medium

Abstract

The application discloses a target area determination method, device and equipment and a storage medium. The method comprises the following steps: acquiring a grid map matched by an automatic driving vehicle in a current period; performing clustering processing on the grid in the grid map according to an occupied grid in the grid map, to obtain at least one occupied grid cluster; determining a polygonal convex hull matched by each occupied grid cluster, and determining a target area according to the vertex of each polygonal convex hull. The technical scheme solves the problems of large path planning calculation amount and long time consumption of the automatic driving vehicle, can improve the path planning efficiency while ensuring the accuracy of the target area, and meets the real-time demand of the automatic driving vehicle for path planning.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to a method, apparatus, electronic device, and storage medium for determining a target area. Background Technology

[0002] In the field of autonomous driving, common traffic targets in the driving environment, such as vehicles and pedestrians, are typically detected using deep learning-based target detection methods. However, for less common traffic targets, such as cardboard boxes and stones, the small sample size and the difficulty of large-scale training make it challenging to achieve effective target detection using deep learning. Therefore, clustering-based drivable area detection methods are needed for obstacle detection. These methods require high-resolution maps, the location information of the autonomous vehicle, and perception information to determine drivable areas and generate a grid map.

[0003] Existing technologies typically rely on occupied grid cells in grid maps for collision checks and path planning for autonomous vehicles. However, grid maps contain a massive number of grid cells with rich regional representations, requiring tens of thousands of collision check calculations to determine drivable paths, which is insufficient to meet the real-time requirements of autonomous driving. Therefore, there is an urgent need for a low-computational-load target region determination method to accurately represent drivable or non-drivable areas. Summary of the Invention

[0004] This invention provides a method, apparatus, device, and storage medium for determining a target area, in order to solve the problems of large computational load and long time consumption in path planning for autonomous vehicles. It can improve the efficiency of path planning while ensuring the accuracy of the target area, and meet the real-time requirements of autonomous vehicles for path planning.

[0005] According to one aspect of the present invention, a method for determining a target region is provided, the method comprising:

[0006] Obtain the grid map matched by the autonomous vehicle in the current cycle;

[0007] Based on the occupied graticules in the raster map, the graticules in the raster map are clustered to obtain at least one occupied graticule cluster;

[0008] Determine the convex hull of each occupied grid cluster and the target region based on the vertices of each convex hull.

[0009] According to another aspect of the present invention, a device for determining a target area is provided, the device comprising:

[0010] The grid map acquisition module is used to acquire the grid map matched by the autonomous vehicle in the current cycle.

[0011] The occupied raster cluster generation module is used to cluster the rasters in the raster map based on the occupied rasters in the raster map to obtain at least one occupied raster cluster;

[0012] The target region determination module is used to determine the polygon convex hulls that match each occupying grid cluster, and to determine the target region based on the vertices of each polygon convex hull.

[0013] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0014] At least one processor; and

[0015] A memory communicatively connected to the at least one processor; wherein,

[0016] The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the target region determination method according to any embodiment of the present invention.

[0017] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the method for determining a target region as described in any embodiment of the present invention.

[0018] The technical solution of this invention obtains the grid map matched by the autonomous vehicle in the current cycle, and performs clustering processing on the grid maps based on the occupied grids to obtain at least one occupied grid cluster. By determining the polygonal convex hull matched by each occupied grid cluster, the target region is determined based on the vertices of each polygonal convex hull. This technical solution solves the problems of large computational load and long time consumption in path planning for autonomous vehicles, improving path planning efficiency while ensuring the accuracy of the target region, and meeting the real-time requirements of autonomous vehicles for path planning.

[0019] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a flowchart of a method for determining a target region according to Embodiment 1 of the present invention;

[0022] Figure 2A This is a flowchart of a method for determining a target region according to Embodiment 2 of the present invention;

[0023] Figure 2B This is a schematic diagram of a grid map provided according to Embodiment 2 of the present invention;

[0024] Figure 2C This is a schematic diagram of a polygonal convex hull provided according to Embodiment 2 of the present invention;

[0025] Figure 2D This is a schematic diagram of the target area provided in Embodiment 2 of the present invention;

[0026] Figure 3 This is a schematic diagram of a target area determination device according to Embodiment 3 of the present invention;

[0027] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the target area determination method of the present invention. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be used interchangeably where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices. The acquisition, storage, use, and processing of data in the technical solutions of this application all comply with the relevant provisions of national laws and regulations.

[0030] Example 1

[0031] Figure 1 This is a flowchart illustrating a method for determining a target area according to Embodiment 1 of the present invention. This embodiment is applicable to determining drivable areas in autonomous driving scenarios. The method can be executed by a target area determination device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0032] S110. Obtain the grid map matched by the autonomous vehicle in the current cycle.

[0033] This solution can be implemented by autonomous vehicles, which can periodically collect perception information from the driving environment using sensors such as radar and cameras. Based on the perception information, the autonomous vehicle's location information, and map information matched with the location information, the autonomous vehicle can generate a grid map.

[0034] The size of the grid map can be determined based on the perception range of the autonomous vehicle's sensors. For example, taking the autonomous vehicle's driving direction as the longitudinal direction and the direction perpendicular to the driving direction as the lateral direction, the perception range can be determined based on the radar deployed in the autonomous vehicle, thus the grid map could be 50 meters longitudinally and 20 meters laterally. The grid shape in the grid map can be rectangular, and the size of each grid can be the same or different. For example, the grid size within 10 meters of the autonomous vehicle can be smaller, and the grid size in areas beyond 10 meters of the autonomous vehicle can be larger. In a specific example, the grids are equal in length and width, both 0.1 meters, and each grid in the grid map is identical, containing a total of 100,000 grids.

[0035] After obtaining the grid map, autonomous vehicles can use a drivable area detection algorithm to determine the drivability of each grid cell in the map and classify it as a grid type. Grid types can include occupied and unoccupied grids. The drivable area detection algorithm can determine the drivability of a grid cell based on its laser point cloud data. If a grid cell is drivable, it is classified as an occupied grid; if it is impassable, it is classified as an unoccupied grid.

[0036] S120. Based on the occupied graticles in the raster map, perform clustering processing on the graticles in the raster map to obtain at least one occupied graticle cluster.

[0037] After determining the traffic status of each grid cell in the grid map, the autonomous vehicle can cluster the occupied grid cells and determine one or more clusters of occupied grid cells based on the clustering results. The autonomous vehicle can cluster the occupied grid cells using density-based clustering algorithms. Specifically, density-based clustering algorithms can be one of the following: Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Euclidean clustering, and MeanShift clustering.

[0038] S130. Determine the convex hull of each occupied grid cluster and determine the target region based on the vertices of each polygon convex hull.

[0039] Understandably, autonomous vehicles can perform convex hull representation on the shape of each occupied grid cluster to obtain the polygonal convex hull matching each occupied grid cluster. The center point of each occupied grid can be used to represent that occupied grid. Autonomous vehicles can establish a coordinate system with the grid map as the plane, such as a Cartesian coordinate system, and perform convex hull calculation based on the coordinates of the center point of each occupied grid in each occupied grid cluster, thereby obtaining the polygonal convex hull.

[0040] After obtaining the polygonal convex hull, the autonomous vehicle can use either the region enclosed by the vertices of the polygonal convex hull, or the region outside the region enclosed by the vertices of the polygonal convex hull, as the target region. Alternatively, it can filter the vertices of the polygonal convex hull, using either the region enclosed by the filtered vertices or the region outside the filtered vertices as the target region. The region enclosed by the vertices of the polygonal convex hull and the region enclosed by the filtered vertices can be considered as the region that the autonomous vehicle cannot traverse, while the region outside the region enclosed by the vertices of the polygonal convex hull and the region outside the filtered vertices can be considered as the region that the autonomous vehicle can traverse.

[0041] After the target area is determined, autonomous vehicles can plan their routes based on the boundaries of the target area to achieve safe and reliable autonomous driving.

[0042] This scheme can merge multiple occupied and non-occupied grids by clustering occupied grids, and represent the merged region by polygon convex hull, so as to greatly reduce the number of points and edges in the target region, thereby reducing the computational load of path planning.

[0043] The technical solution of this invention obtains the grid map matched by the autonomous vehicle in the current cycle, and performs clustering processing on the grid maps based on the occupied grids to obtain at least one occupied grid cluster. By determining the polygonal convex hull matched by each occupied grid cluster, the target region is determined based on the vertices of each polygonal convex hull. This technical solution solves the problems of large computational load and long time consumption in path planning for autonomous vehicles, improving path planning efficiency while ensuring the accuracy of the target region, and meeting the real-time requirements of autonomous vehicles for path planning.

[0044] Example 2

[0045] Figure 2A This is a flowchart of a method for determining a target region according to Embodiment 2 of the present invention. This embodiment is a refinement based on the above embodiment. Figure 2A As shown, the method includes:

[0046] S201. Obtain the grid map matched by the current cycle for the autonomous vehicle.

[0047] This solution uses a specific raster map as an example to explain the method for determining the target area. Figure 2B This is a schematic diagram of a grid map provided according to Embodiment 2 of the present invention. The autonomous vehicle establishes a grid map as a plane, as shown below. Figure 2B The diagram shows a Cartesian coordinate system. In the grid map, black grids are occupied grids, and white grids are unoccupied grids.

[0048] S202. Determine the target grid in the occupied grid of the grid map.

[0049] Autonomous vehicles can randomly select an occupying grid cell in a grid map as the target grid cell.

[0050] S203. Based on the target raster, create a target raster cluster.

[0051] Autonomous vehicles can create a target grid cluster centered on the target grid.

[0052] S204. Determine the occupied graticles that are reachable from the target graticle density, and add the occupied graticles that are reachable from the target graticle density to the target occupied graticle cluster.

[0053] As is easily understood, the occupied grids reachable from the target grid density can be any occupied grids within a preset range centered on the target grid. This preset range can be determined based on attributes such as the length and width of the autonomous vehicle. The autonomous vehicle can add these occupied grids reachable from the target grid density to the target occupied grid cluster.

[0054] In this scheme, optionally, determining the occupied grid cells reachable from the target grid density includes:

[0055] Centered on the target grid, determine the grid matrix that matches the target grid according to the preset search step size;

[0056] The occupied grid cells in the grid matrix that match the target grid are taken as the occupied grid cells that the target grid density can reach.

[0057] After selecting a target grid, the autonomous vehicle can use a matrix search method centered on the target grid to determine the occupiesable grids with the target grid density achievable. The matrix search allows setting the grid matrix size via a search step size, which can be the number of grids separating the target grid from the matrix boundary. For example, Figure 2B The grid g1 shown is the target grid. The search step size is 1. The dashed box centered on grid g1 represents the grid matrix matched by the target grid.

[0058] If the target raster is a boundary raster in a raster map, the autonomous vehicle can determine the raster matrix that matches the target raster based on the boundaries associated with it. For example, Figure 2B The grid g2 shown is the target grid, with a search step size of 2. The dashed box centered on grid g2 represents the grid matrix matched by the target grid. For example, Figure 2B The grid g3 shown is the target grid, with a search step size of 3. The dashed box centered on grid g3 represents the grid matrix matched by the target grid.

[0059] After obtaining the grid matrix that matches the target grid, the autonomous vehicle can use the occupied grids within the grid matrix as the occupied grids that are achievable by the target grid density.

[0060] This scheme can quickly determine the occupied graticles that are achievable by the target graticle density through a matrix search centered on the target graticle, thereby enabling rapid clustering of the occupied graticles.

[0061] S205. Sequentially select the occupied grids that are reachable from the target grid density as the new target grids.

[0062] After completing the first update of the target occupied grid cluster, the autonomous vehicle can sequentially use the occupied grids that are density-reachable from the target grid as the new target grids and determine whether there are density-reachable occupied grids for the new target grids.

[0063] S206. Determine whether there is an occupied grid with a density reachable from the target grid.

[0064] If the target grid has a density-reachable occupied grid, then return to step S230 to expand the target occupied grid cluster. If the target grid does not have a density-reachable occupied grid, then proceed to step S206.

[0065] S207. Determine if there are any unvisited occupied grid cells in the grid map.

[0066] When no occupied grid is density-reachable from the target grid, the autonomous vehicle completes the clustering of the target occupied grid cluster and determines whether there are any unvisited occupied grids in the grid map. If there are no unvisited occupied grids in the grid map, it means that the clustering of all occupied grids in the grid map has been completed. If there are unvisited occupied grids in the grid map, it means that there are still occupied grids in the grid map that have not been clustered, and the process continues to execute S207.

[0067] S208. Identify unvisited occupied grids in the grid map, and identify the target grid among the unvisited occupied grids.

[0068] The autonomous vehicle can randomly select an occupied grid from the unvisited occupied grids in the grid map as the target grid, and return to execute S203-S207 until the clustering processing of all occupied grids in the grid map is completed, and obtain the clustering result cluster of occupied grids matched by the grid map.

[0069] S209, each output occupies a raster cluster.

[0070] S210. Determine the center coordinates of each occupied grid cell in the occupied grid cluster, and determine the convex hull of the polygon based on the center coordinates of each occupied grid cell.

[0071] In essence, an autonomous vehicle can determine a polygonal convex hull for each occupied grid cluster. Specifically, the autonomous vehicle can determine the center coordinates of each occupied grid cell in the occupied grid cluster. By comparing the center coordinates of each occupied grid cell in the occupied grid cluster, the autonomous vehicle can determine the boundary vertices of the polygonal convex hull based on convex hull calculation methods such as the Graham scan algorithm, Jarvis algorithm, fast convex hull algorithm, and Andrew's monotone chain algorithm. Figure 2C This is a schematic diagram of the polygonal convex hull provided according to Embodiment 2 of the present invention, as shown below. Figure 2C As shown, points 1-11 corresponding to the center coordinates of each grid cell are the boundary vertices of the polygon's convex hull. Connecting the boundary vertices of the polygon's convex hull in a clockwise or counterclockwise direction yields the polygon's convex hull.

[0072] S211. Determine the target region based on the vertices of the convex hull of each polygon.

[0073] It should be noted that, as Figure 2CThe polygonal convex hull shown has 11 edges. If the region inside or outside the polygonal convex hull is directly used as the target region, collision calculations need to be performed on all 11 edges to obtain a drivable route for the autonomous vehicle during path planning. However, by filtering the vertices of the polygonal convex hull and minimizing the number of vertices within the allowable range of shape variations, the number of edges can be reduced accordingly, thereby effectively reducing the amount of collision calculation.

[0074] In one feasible solution, determining the target region based on the vertices of the convex hull of each polygon includes:

[0075] If the number of vertices of the polygon convex hull is greater than 4, then the four extreme vertices are determined based on the vertex coordinates of the polygon convex hull, and the connecting lines between adjacent extreme vertices are determined.

[0076] The target vertex is determined from the vertices between adjacent extreme vertices by using the straight lines connecting adjacent extreme vertices.

[0077] The target region is determined based on each extreme vertex and the target vertex between adjacent extreme vertices.

[0078] Based on the above scheme, optionally, determining the target vertex among the vertices between adjacent extreme vertices includes:

[0079] Determine the number of vertices between adjacent extreme vertices;

[0080] If the number of vertices between adjacent extreme vertices is greater than or equal to 2, then determine the distance between each vertex of the adjacent extreme vertex and the line connecting the adjacent extreme vertices.

[0081] The vertex between the two adjacent extreme vertices with the largest distance is taken as the target vertex.

[0082] Autonomous vehicles can determine the vertices corresponding to the maximum, minimum, maximum, and minimum coordinate values ​​on the first, second, and third coordinate axes, respectively, within the coordinate system of the polygon's convex hull. These vertices are then designated as extreme vertices. Figure 2C As shown, the first coordinate axis can be the X-axis, the second coordinate axis can be the Y-axis, the number of vertices of the polygon's convex hull is 11, which is greater than 4, and the four extreme vertices are point 1, point 4, point 7 and point 10.

[0083] Based on points 1 and 4, we can derive the connecting line L1. Based on points 4 and 7, we can derive the connecting line L2. Based on points 7 and 10, we can derive the connecting line L3. Based on points 1 and 10, we can derive the connecting line L4. There is only one vertex between points 1 and 10, namely point 11. Therefore, we take point 11 as the target vertex between points 1 and 10. The vertices of the polygon's convex hull between points 1 and 4 include points 2 and 3. We calculate the distances from points 2 and 3 to the connecting line L1. We take point 3, which has the largest distance from the connecting line L1, as the target vertex between points 1 and 4. Similarly, we can determine that the target vertex between points 4 and 7 is point 6, and the target vertex between points 7 and 10 is point 8.

[0084] After obtaining the target vertex, the autonomous vehicle can remove all vertices except the extreme vertex and the target vertex, and connect each extreme vertex and the target vertex between adjacent extreme vertices according to the connection order of each vertex in the polygon convex hull to obtain the improved polygon convex hull. Figure 2D This is a schematic diagram of the target area provided in Embodiment 2 of the present invention, as shown below. Figure 2D As shown, autonomous vehicles can use the region inside or outside the improved polygonal convex hull as the target region.

[0085] The above scheme can reduce the number of vertices in the polygonal convex hull. It can minimize the number of vertices while ensuring that the shape of the polygonal convex hull does not change significantly, thereby improving the path planning efficiency of autonomous vehicles.

[0086] In another feasible approach, determining the target region based on the vertices of each polygon's convex hull includes:

[0087] If the number of vertices of the polygon convex hull is less than or equal to 4, then the internal or external region of the polygon convex hull is taken as the target region.

[0088] If the number of vertices in the polygonal convex hull is less than or equal to 4 and the number of edges in the polygonal convex hull is small, there is no need to filter the vertices of the polygonal convex hull, and the internal or external region of the polygonal convex hull can be directly used as the target region.

[0089] The technical solution of this invention obtains the grid map matched by the autonomous vehicle in the current cycle, and performs clustering processing on the grid maps based on the occupied grids to obtain at least one occupied grid cluster. By determining the polygonal convex hull matched by each occupied grid cluster, the target region is determined based on the vertices of each polygonal convex hull. This technical solution solves the problems of large computational load and long time consumption in path planning for autonomous vehicles, improving path planning efficiency while ensuring the accuracy of the target region, and meeting the real-time requirements of autonomous vehicles for path planning.

[0090] Example 3

[0091] Figure 3 This is a schematic diagram of a target area determination device provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes:

[0092] The grid map acquisition module 310 is used to acquire the grid map matched by the autonomous vehicle in the current cycle.

[0093] The occupied grid cluster generation module 320 is used to perform clustering processing on the grid cells in the grid map based on the occupied grid cells in the grid map to obtain at least one occupied grid cluster.

[0094] The target region determination module 330 is used to determine the polygonal convex hulls that match each occupying grid cluster, and to determine the target region based on the vertices of each polygonal convex hull.

[0095] In this solution, optionally, the occupying grid cluster generation module 320 includes:

[0096] The target raster cluster establishment unit is used to determine the target raster in the occupied raster of the raster map and establish the target raster cluster based on the target raster;

[0097] Occupied grid addition unit, used to determine occupied grids that are reachable from the target grid density, and add the occupied grids that are reachable from the target grid density to the target occupied grid cluster;

[0098] The first update unit for the target grid is used to sequentially take the occupied grids that are reachable from the target grid density as new target grids, return to determine the occupied grids that are reachable from the target grid density, add the occupied grids that are reachable from the target grid density to the target occupied grid cluster, until there are no occupied grids that are reachable from the target grid density.

[0099] The second update unit for the target raster is used to determine unvisited occupied rasters in the raster map, determine the target raster among the unvisited occupied rasters, and return to execute the creation of a target raster cluster based on the target raster until there are no unvisited occupied rasters in the raster map.

[0100] Occupied grid cluster output unit, used to output each occupied grid cluster.

[0101] Based on the above scheme, optionally, the occupying grid joining unit is specifically used for:

[0102] Centered on the target grid, determine the grid matrix that matches the target grid according to the preset search step size;

[0103] The occupied grid cells in the grid matrix that match the target grid are taken as the occupied grid cells that the target grid density can reach.

[0104] In one feasible solution, the target area determination module 330 includes:

[0105] The polygon convex hull determination unit is used to determine the center coordinates of each occupied grid in the occupied grid cluster, and to determine the polygon convex hull based on the center coordinates of each occupied grid.

[0106] Based on the above solution, optionally, the target region determination module 330 further includes a target region determination unit, the target region determination unit comprising:

[0107] Connecting lines determine sub-units. If the number of vertices of the polygon convex hull is greater than 4, then based on the vertex coordinates of the polygon convex hull, four extreme vertices are determined, and connecting lines between adjacent extreme vertices are determined.

[0108] The target vertex determination sub-unit is used to determine the target vertex among the vertices between adjacent extreme vertices based on the connecting lines of adjacent extreme vertices;

[0109] The target region determination sub-unit is used to determine the target region based on each extreme vertex and the target vertices between adjacent extreme vertices.

[0110] Based on the above scheme, optionally, the target vertex determination sub-unit is specifically used for:

[0111] Determine the number of vertices between adjacent extreme vertices;

[0112] If the number of vertices between adjacent extreme vertices is greater than or equal to 2, then determine the distance between each vertex of the adjacent extreme vertex and the line connecting the adjacent extreme vertices.

[0113] The vertex between the two adjacent extreme vertices with the largest distance is taken as the target vertex.

[0114] In another feasible embodiment, the target region determination module 330 is further configured to:

[0115] If the number of vertices of the polygon convex hull is less than or equal to 4, then the internal or external region of the polygon convex hull is taken as the target region.

[0116] The target region determination device provided in the embodiments of the present invention can execute the target region determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0117] Example 4

[0118] Figure 4A schematic diagram of an electronic device 410 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0119] like Figure 4 As shown, the electronic device 410 includes at least one processor 411 and a memory, such as a read-only memory (ROM) 412 or a random access memory (RAM) 413, communicatively connected to the at least one processor 411. The memory stores computer programs executable by the at least one processor. The processor 411 can perform various appropriate actions and processes based on the computer program stored in the ROM 412 or loaded from storage unit 418 into the RAM 413. The RAM 413 may also store various programs and data required for the operation of the electronic device 410. The processor 411, ROM 412, and RAM 413 are interconnected via a bus 414. An input / output (I / O) interface 415 is also connected to the bus 414.

[0120] Multiple components in electronic device 410 are connected to I / O interface 415, including: input unit 416, such as keyboard, mouse, etc.; output unit 417, such as various types of displays, speakers, etc.; storage unit 418, such as disk, optical disk, etc.; and communication unit 419, such as network card, modem, wireless transceiver, etc. Communication unit 419 allows electronic device 410 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0121] Processor 411 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 411 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 411 performs the various methods and processes described above, such as the method for determining the target region.

[0122] In some embodiments, the method for determining the target region may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 418. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 410 via ROM 412 and / or communication unit 419. When the computer program is loaded into RAM 413 and executed by processor 411, one or more steps of the method for determining the target region described above may be performed. Alternatively, in other embodiments, processor 411 may be configured to perform the method for determining the target region by any other suitable means (e.g., by means of firmware).

[0123] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0124] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other device with a defined programmable target area, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0125] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0126] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0127] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0128] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0129] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0130] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining a target region, characterized in that, The method includes: Obtain the grid map matched by the autonomous vehicle in the current cycle, wherein the size of the grid map is determined based on the perception range of the autonomous vehicle's sensors; Based on the drivable area detection algorithm, the drivability status of each grid in the grid map is judged, and the grid type of each grid in the grid map is determined. The grid type includes occupied grids and non-occupied grids. The drivable area detection algorithm is used to judge the drivability status of the grid based on the laser point cloud data of the grid area. Based on the occupied graticules in the raster map, the graticules in the raster map are clustered to obtain at least one occupied graticule cluster; Determine the convex hull of each occupied grid cluster and the target region based on the vertices of each convex hull; The step of clustering the rasters in the raster map based on the occupied rasters in the raster map to obtain at least one occupied raster cluster includes: Identify the target grid within the occupied grid of the grid map; Create a target raster cluster based on the target raster; Determine the occupied graticles that are reachable from the target graticle density, and add the occupied graticles that are reachable from the target graticle density to the target occupied graticle cluster; The process involves sequentially identifying occupied graticles reachable from the target graticle density as new target graticles, returning to determine which occupied graticles are reachable from the target graticle density, and adding these occupied graticles to the target occupied graticle cluster until no occupied graticles are reachable from the target graticle density. Identify unvisited occupied grids in the grid map, determine the target grid among the unvisited occupied grids, return to execution, and build a target grid cluster based on the target grid until there are no more unvisited occupied grids in the grid map. Each output occupies a specific raster cluster; The determination of the polygonal convex hull matching each occupying grid cluster includes: Determine the center coordinates of each occupied grid cell in the occupied grid cluster, and determine the convex hull of the polygon based on the center coordinates of each occupied grid cell.

2. The method according to claim 1, characterized in that, The determination of occupied grid cells reachable from the target grid density includes: Centered on the target grid, determine the grid matrix that matches the target grid according to the preset search step size; The occupied grid cells in the grid matrix that match the target grid are taken as the occupied grid cells that the target grid density can reach.

3. The method according to claim 1, characterized in that, The step of determining the target region based on the vertices of each polygon's convex hull includes: If the number of vertices of the polygon convex hull is greater than 4, then the four extreme vertices are determined based on the vertex coordinates of the polygon convex hull, and the connecting lines between adjacent extreme vertices are determined. The target vertex is determined from the vertices between adjacent extreme vertices by using the straight lines connecting adjacent extreme vertices. The target region is determined based on each extreme vertex and the target vertex between adjacent extreme vertices.

4. The method according to claim 3, characterized in that, Determining the target vertex among the vertices between adjacent extreme vertices includes: Determine the number of vertices between adjacent extreme vertices; If the number of vertices between adjacent extreme vertices is greater than or equal to 2, then determine the distance between each vertex of the adjacent extreme vertex and the line connecting the adjacent extreme vertices. The vertex between the two adjacent extreme vertices with the largest distance is taken as the target vertex.

5. The method according to claim 1, characterized in that, The step of determining the target region based on the vertices of each polygon's convex hull includes: If the number of vertices of the polygon convex hull is less than or equal to 4, then the internal or external region of the polygon convex hull is taken as the target region.

6. A device for determining a target area, characterized in that, include: The grid map acquisition module is used to acquire the grid map matched by the autonomous vehicle in the current cycle. The size of the grid map is determined based on the perception range of the autonomous vehicle's sensors. Based on the drivable area detection algorithm, the drivability status of each grid in the grid map is judged, and the grid type of each grid in the grid map is determined. The grid type includes occupied grids and non-occupied grids. The drivable area detection algorithm is used to judge the drivability status of the grid based on the laser point cloud data of the grid area. The occupied raster cluster generation module is used to cluster the rasters in the raster map based on the occupied rasters in the raster map to obtain at least one occupied raster cluster; The target region determination module is used to determine the polygon convex hulls that match each occupying grid cluster, and to determine the target region based on the vertices of each polygon convex hull. The occupying grid cluster generation module specifically includes: The target raster cluster establishment unit is used to determine the target raster in the occupied raster of the raster map and establish the target raster cluster based on the target raster; Occupied grid addition unit, used to determine occupied grids that are reachable from the target grid density, and add the occupied grids that are reachable from the target grid density to the target occupied grid cluster; The first update unit for the target grid is used to sequentially take the occupied grids that are reachable from the target grid density as new target grids, return to determine the occupied grids that are reachable from the target grid density, add the occupied grids that are reachable from the target grid density to the target occupied grid cluster, until there are no occupied grids that are reachable from the target grid density. The second update unit for the target raster is used to determine unvisited occupied rasters in the raster map, determine the target raster among the unvisited occupied rasters, and return to execute the creation of a target raster cluster based on the target raster until there are no unvisited occupied rasters in the raster map. Occupied grid cluster output unit, used to output each occupied grid cluster; The target region determination module specifically includes: The polygon convex hull determination unit is used to determine the center coordinates of each occupied grid in the occupied grid cluster, and to determine the polygon convex hull based on the center coordinates of each occupied grid.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the method for determining the target region according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the method for determining the target region as described in any one of claims 1-5.

Images