An environment detection method and device, and related products

Abstract

The present application relates to an environment detection method and device, related products, the method comprises the current frame is obtained from the car position and point cloud information;According to the car position and first preset range generates the first grid position of first precision grid map, according to the car position and second preset range generates the second grid position of second precision grid map, the first precision is different from the second precision, the first preset range is different from the second preset range;According to the first grid position, the second grid position and point cloud information, first grid attribute information and second grid attribute information of the first grid position and the second grid position are generated respectively;Output first, second grid position and first, second grid attribute information.The environment detection method and device, related products provided in the embodiment of the present application, in the surrounding of the car, set up the grid map of different range and precision cooperation each other again, the point cloud is projected to the grid map, realized the environment perception of large range high precision.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to an environmental detection method, apparatus, medium, computer device, and mobile tool. Background Technology

[0002] In autonomous driving environmental detection, lidar is typically used for environmental perception. LiDAR emits a laser beam that strikes the surface of an object in the environment and returns. The receiver receives the time difference between the return beam and the emission time. Based on this time difference and the speed of light in air, the total round-trip distance can be calculated. Furthermore, the azimuth angles of the laser beam during emission and reception allow for the determination of the target's 3D coordinates. The laser scans in a specific manner, producing a series of scan lines. Multiple laser heads are combined to form multiple scan lines. A single complete scan yields a series of 3D coordinates, collectively known as a laser point cloud. For environmental perception, this point cloud is projected onto a planar grid to obtain a 2D top-down view. Then, algorithms such as segmentation and clustering are used to identify individual targets in the environment. Alternatively, the point cloud can be directly input into a deep neural network to learn and identify targets in the environment.

[0003] In existing planar grid map creation schemes, a grid map is first established within a certain range around the vehicle. Based on the vehicle's absolute coordinates obtained from the navigation system, the absolute coordinates of all grid cells in the grid map are calculated. Then, the point cloud acquired by the LiDAR is projected onto the grid, rasterized, and the features of the point cloud in each cell are calculated. This allows for a preliminary assessment of the state of falling into a certain number of grid cells (whether it is an obstacle, whether it is passable, etc.). As the vehicle moves, new LiDAR point clouds are continuously projected onto the grid map based on the vehicle's real-time positioning status, thereby achieving multi-angle observation of the environment and the accumulation of observations at different times.

[0004] Existing technologies use a specific grid precision when rasterizing a certain area around a vehicle. If the rasterized area is large, the resolution of the raster map needs to be reduced (i.e., the coverage of a single grid cell needs to be increased). Otherwise, an excessive number of grid cells would lead to increased computational load and reduced real-time performance. However, when the size of a single grid cell in the raster map is large, the perception of the environment is relatively coarse and cannot meet the requirements for high precision. For example, when a vehicle is running at high speed, it needs to perceive the area within 60 meters in front of it. If the vehicle is operating in a complex environment, the perception precision within 10 meters of the vehicle cannot be less than 0.1 meters. In other words, while a large-area perception is required, high-precision perception is also needed in a small area. If the raster map is a single-precision raster map and the grid precision is selected as 0.1 meters, then the size of a single grid cell is 0.1m x 0.1m. If the raster map area is 60m x 60m in front of the vehicle, then the total number of grid cells would be 600 x 600 = 360,000, which exceeds the processing capacity of ordinary computing platforms. Single-resolution raster maps cannot solve the problem of large-scale, high-precision environmental perception under limited resources. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of existing technologies by providing an environmental detection method to solve the problems existing in environmental detection in the prior art.

[0006] To achieve the above objectives, the first aspect of the present invention provides an environmental detection method, the method comprising:

[0007] Obtain the vehicle's position and point cloud information for the current frame;

[0008] The first grid position of the first precision grid map is generated based on the vehicle position and the first preset range, and the second grid position of the second precision grid map is generated based on the vehicle position and the second preset range. The first precision is different from the second precision, and the first preset range is different from the second preset range.

[0009] Based on the first grid position, the second grid position, and the point cloud information, generate first grid attribute information and second grid attribute information for the first grid position and the second grid position, respectively.

[0010] Output the positions and attribute information of the first and second grid cells.

[0011] Furthermore, the second preset range is set based on the vehicle's position.

[0012] Furthermore, the first preset range is set based on the vehicle's position or according to the boundary of the second preset range.

[0013] Furthermore, the first precision is lower than the second precision, and the first preset range includes the second preset range.

[0014] Furthermore, determine whether the current frame is the initial frame;

[0015] If so, generate the first grid position of the first precision grid map based on the vehicle position and the first preset range, and generate the second grid position of the second precision grid map based on the vehicle position and the second preset range;

[0016] If not, update the first grid position of the previous frame based on the vehicle position of the current frame and the first preset range to generate the first grid position of the current frame; update the second grid position of the previous frame based on the vehicle position of the current frame and the second preset range to generate the second grid position of the current frame.

[0017] Furthermore, the step of updating the first grid position of the previous frame based on the vehicle position of the current frame and the first preset range to generate the first grid position of the current frame specifically involves:

[0018] Delete grid positions from the previous frame that are not within the first preset range of the current frame, and create new grid positions that are within the first preset range of the current frame.

[0019] Furthermore, the step of updating the second grid position of the previous frame based on the vehicle position of the current frame and the second preset range to generate the second grid position of the current frame specifically involves:

[0020] Delete the grid positions in the previous frame that are not within the second preset range of the current frame, and create new grid positions that are within the second preset range of the current frame.

[0021] Furthermore, the method also includes:

[0022] Determine whether the first and second grid positions of the current frame are both newly created grids;

[0023] If so, based on the first grid position, the second grid position, and the point cloud information, generate the first grid attribute information and the second grid attribute information for the first grid position and the second grid position, respectively;

[0024] If not, inherit the first or second grid attribute information of the overlapping grid position of the previous frame; generate the first and second grid attribute information of the current frame based on the point cloud information of the current frame and the inherited first and second grid attribute information.

[0025] Furthermore, the inheritance of the first and second grid attribute information of the overlapping grid positions from the previous frame specifically includes:

[0026] If the first grid position of the current frame is a newly created grid position and overlaps with the second grid position of the previous frame, inherit the attribute information of the second grid of the previous frame;

[0027] If the first grid position of the current frame is the same as the first grid position of the previous frame, inherit the first grid attribute information of the previous frame;

[0028] If the second grid position of the current frame is a newly created grid position and overlaps with the first grid position of the previous frame, the preset inheritable attribute information of the first grid attribute information of the previous frame is inherited.

[0029] If the second grid position of the current frame is the same as the second grid position of the previous frame, the second grid attribute information of the previous frame is inherited.

[0030] Furthermore, the output of the positions and attribute information of the first and second grid cells specifically includes:

[0031] The first grid position and first grid attributes do not include the portion that overlaps with the second grid position.

[0032] A second aspect of the present invention provides an environmental monitoring device, the environmental monitoring device comprising:

[0033] The system includes a positioning module and a perception module. The positioning module is used to obtain the vehicle's position in the current frame, and the perception module is used to obtain point cloud information.

[0034] An environmental data processing module is configured to generate a first grid position of a first-precision raster map based on the vehicle's position and a first preset range, and to generate a second grid position of a second-precision raster map based on the vehicle's position and a second preset range, wherein the first precision and the second precision are different, and the first preset range and the second preset range are different; and to generate first grid attribute information and second grid attribute information of the first grid position and the second grid position based on the first grid position, the second grid position, and point cloud information, respectively.

[0035] An environmental data output module is used to output the positions and attribute information of the first and second grid cells.

[0036] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the environmental detection method according to any one of the first aspects.

[0037] A fourth aspect of the present invention provides a computer device including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the environmental detection method according to any one of the first aspects.

[0038] A fifth aspect of the present invention provides a mobile tool, characterized in that it includes the computer device described in the fifth aspect.

[0039] The environmental detection method, device, and related products provided by this invention achieve large-scale, high-precision environmental perception by setting up grid maps of different ranges and accuracies around the vehicle and then projecting point clouds onto the grid maps. Attached Figure Description

[0040] Figure 1 This is one of the flowcharts for the environmental detection method provided in Embodiment 1 of the present invention;

[0041] Figure 2 This is a schematic diagram of the multi-resolution raster map layout provided in Embodiment 1 of the present invention;

[0042] Figure 3 This is the second flowchart of the environmental detection method provided in Embodiment 1 of the present invention;

[0043] Figure 4 This is the third flowchart of the environmental detection method provided in Embodiment 1 of the present invention;

[0044] Figure 5 This is a schematic diagram of the environmental monitoring device provided in Embodiment 2 of the present invention;

[0045] Figure 6 This is a schematic diagram of the computer device structure provided in Embodiment 5 of the present invention. Detailed Implementation

[0046] The present application will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings.

[0047] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0048] This invention addresses the varying accuracy requirements of environmental detection for vehicles at different distances by using grids of varying precision across different map areas. It achieves low-resolution full coverage over large areas while using high-resolution grids for smaller, specific regions, enabling multi-resolution sensing. This approach ensures both large-scale environmental detection and high-precision detection in specific areas, even with limited resources. When a vehicle moves, if a newly created grid falls into a grid of a different resolution from the previous frame, the grid attributes of the covered grid from the previous frame are inherited according to inheritance rules, improving the initialization efficiency of new grids.

[0049] Example 1

[0050] Figure 1This is one of the flowcharts for an environmental detection method provided in Embodiment 1 of the present invention. The executing entity of this application is a terminal, server, or processor with computing capabilities. By way of example and not limitation, this application illustrates the application of this method in an autonomous vehicle. When this method is applied to an autonomous vehicle, the executing entity is the control unit of the autonomous vehicle, also known as the autonomous driving domain controller, which possesses capabilities such as perception, localization, path planning, decision control, and communication. It typically connects to external sensors such as cameras, millimeter-wave radar, lidar, and inertial measurement units (IMUs). The method includes:

[0051] Step 110: Obtain the vehicle's position and point cloud information for the current frame.

[0052] Specifically, the autonomous vehicle's navigation system obtains the absolute coordinates of the current frame, including the coordinates of the vehicle's center point and the front, rear, left, and right coordinates of the vehicle itself. The point cloud information of the current frame can be obtained by scanning the surrounding obstacles using a specific method using a LiDAR transmitter. The vehicle's body point cloud information is then removed from the point cloud information based on the vehicle's front, rear, left, and right coordinates to avoid treating the vehicle body as an obstacle.

[0053] Step 120: Generate the first grid position of the first precision grid map based on the vehicle position and the first preset range; generate the second grid position of the second precision grid map based on the vehicle position and the second preset range. The first precision and the second precision are different, and the first preset range and the second preset range are different.

[0054] Specifically, based on the varying accuracy requirements of the vehicle's environmental detection across different ranges, and considering the computing power of the sensing devices and the availability of sensors, the system maximizes the use of computing power to generate the first grid position of a first-precision grid map within a first preset range, and the second grid position of a second-precision grid map within a second preset range. The first and second precision grid maps include the coordinates of the grid center point relative to the vehicle's center point, the grid area radius, and the size of a single grid cell, where the area of ​​a single grid cell is negatively correlated with its accuracy. In autonomous driving environmental monitoring, if the vehicle is in a high-speed, complex environment, it requires environmental detection over a large area while simultaneously demanding high-precision detection within a smaller area. Given limited processor capacity, simultaneously setting up large-area low-precision and small-area high-precision grid maps can meet the environmental detection needs in high-speed, complex environments.

[0055] In one possible implementation, the precision of the first precision raster map is lower than that of the second precision raster map, the first preset range includes the second preset range, the second preset range is set with the vehicle position as the base point, and the first preset range is set with the vehicle position as the base point. Figure 2This is a schematic diagram of the multi-resolution raster map layout provided in Embodiment 1 of the present invention, as shown below. Figure 2 As shown, it includes vehicle 1 and the first precision grid. Figure 2 First precision grid 21, second precision grid Figure 3 Second precision grid 31.

[0056] like Figure 2 As shown, a first-precision grid is generated within a first preset range, using the center of vehicle 1 as the base point. Figure 2 The first preset range is a square region S1 enclosed by an area E meters to the right of the center point of vehicle 1, an area F meters to the left, an area G meters in front, and an area H meters behind. Assuming each grid cell is L meters long and Q meters wide, the square region S1 is divided into equal parts based on the enclosed square region S1 and the length L meters and width Q meters of each grid cell, with each grid cell area L x Q meters, thus generating a first-precision grid area. Figure 2 The number of first-precision grids 21 is (E+F)x(G+H) / (LxQ).

[0057] Using the center of vehicle 1 as the base point, a second precision grid is generated within a second preset range. Figure 3 The second preset range is a square region S2 enclosed by an area A meters to the right of the center point of vehicle 1, an area B meters to the left, an area C meters in front, and an area D meters behind, where A is less than E, B is less than F, C is less than G, D is less than H, and S2 is less than S1. Assume each grid cell is M meters long and N meters wide, where M x N is less than L x Q, meaning the second precision is higher than the first precision. Region S2 is within region S1, meaning the first preset range is greater than the second preset range. Based on the enclosed square region S2 and the length M meters and width N meters of each grid cell, the square region S2 is divided into square regions S2 by averaging the area of ​​each grid cell M x N meters, generating the second precision grid area. Figure 3 The number of second-precision grids 31 is (C+D)x(A+B) / (NxM).

[0058] In another possible implementation, the first preset range is set according to the boundary of the second preset range. When set according to the boundary of the second preset range, it extends outward from the boundary of the second preset range to the first preset range. Assuming the second preset range is a square area S2 enclosed by an area A meters to the right of the center point of vehicle 1, an area B meters to the left, an area C meters in front, and an area D meters behind, then the first preset range can be defined as a closed strip area S3 enclosed by an area from A meters to A+a meters to the right of the center point of vehicle 1, an area from B meters to B+b meters to the left, an area from C meters to C+c meters in front, and an area from D meters to D+d behind, where a, b, c, and d are all greater than 0. The strip area S3 is divided into equal parts based on the area of ​​each grid cell, and a first-precision grid map is generated. It should be noted that the first and second preset range areas in the above embodiments are both square areas. The shape of the first and second preset range areas is not limited here, and can be standard graphic areas such as circles and ellipses, or non-standard graphic areas.

[0059] In a preferred embodiment, such as Figure 3 As shown, step 120 also includes the following:

[0060] Step 210: Determine whether the current frame is the initial frame.

[0061] If so, proceed to step 120.

[0062] Step 220: If not, update the first grid position of the previous frame based on the vehicle position of the current frame and the first preset range to generate the first grid position of the current frame; update the second grid position of the previous frame based on the vehicle position of the current frame and the second preset range to generate the second grid position of the current frame.

[0063] Specifically, if the current frame is not the initial frame, grid positions that were outside the first preset range of the current frame due to vehicle movement in the previous frame are deleted, and new grid positions that enter the first preset range of the current frame are created. Similarly, grid positions that were outside the second preset range of the current frame due to vehicle movement in the previous frame are deleted, and new grid positions that enter the second preset range of the current frame are created. When deleting grid positions from the previous frame, deletion is performed on a single grid unit, and the grids within the preset range of the current frame are filled in. Inheriting grid positions reduces the computational load of regenerating grid positions for each frame.

[0064] Step 130: Based on the first grid position, the second grid position, and the point cloud information, generate the first grid attribute information and the second grid attribute information for the first grid position and the second grid position, respectively.

[0065] Specifically, the point cloud information is projected onto the first and second grid positions to obtain a two-dimensional top view of the point cloud. Then, through algorithms such as segmentation and clustering, the attribute information of the first and second grids is obtained. The attribute information of the first and second grids includes grid occupancy status, point cloud height difference, point cloud density, maximum point cloud height, minimum point cloud height, point cloud category, etc.

[0066] In a preferred embodiment, such as Figure 4 As shown, step 130 is preceded by:

[0067] Step 310: Determine whether the current frame is the initial frame.

[0068] If so, proceed to step 130.

[0069] If not, proceed to steps 320 and 330.

[0070] Step 320: Inherit the first or second grid attribute information of the overlapping grid position of the previous frame.

[0071] In one possible implementation, if the first grid position of the current frame is a newly created grid position and overlaps with the second grid position of the previous frame, the attribute information of the second grid in the previous frame is inherited; if the first grid position of the current frame is the same as the first grid position of the previous frame, the attribute information of the first grid in the previous frame is inherited; if the second grid position of the current frame is a newly created grid position and overlaps with the first grid position of the previous frame, the preset inheritable attribute information of the attribute information of the first grid in the previous frame is inherited; if the second grid position of the current frame is the same as the second grid position of the previous frame, the attribute information of the second grid in the previous frame is inherited.

[0072] In this context, the first grid position in the current frame is the newly created grid position, which overlaps with the second grid position in the previous frame. If the area of ​​a single second grid is smaller than the area of ​​the first grid, and multiple second grids fall into a first grid, the attributes of multiple high-precision second grids are summarized and merged. This includes merging the average height of the point cloud observed in the previous frame, resuming the maximum and minimum heights, recalculating the height difference, and selecting the point cloud category based on the quantity advantage of different types of high-precision grids.

[0073] In this context, the second grid position in the current frame is a newly created grid position that overlaps with the first grid position in the previous frame. It inherits a portion of the preset inheritable attribute information of the first grid in the previous frame. The preset inheritable attribute information may include point cloud height difference, point cloud density, maximum point cloud height, minimum point cloud height, etc., but does not include grid occupancy status. Due to the difference in grid precision, the generated grid occupancy status may be different when determining the first grid occupancy status and the second grid occupancy status. For grids with higher precision, the occupancy status determination is more accurate, so the grid occupancy status of the previous frame is not inherited.

[0074] Step 330: Generate the first and second raster attribute information of the current frame based on the point cloud information of the current frame and the inherited first and second raster attribute information.

[0075] The point cloud information of the current frame is projected onto the first and second grid positions of the current frame. This point cloud information includes the number of points newly added to the grid, the minimum and maximum point heights, the height difference, and the point density. The point cloud information of the current frame, along with the inherited grid attribute information from the first and second grids, are then combined to generate the first and second grid attribute information for the current frame. The occupancy state of the current frame's grids can be generated through Bayesian probability estimation or Kalman filtering. Inheriting attribute information from the previous frame improves the accuracy of the current frame's grid occupancy state.

[0076] Step 140: Output the positions and attribute information of the first and second grid cells.

[0077] In a preferred embodiment, the first grid position and the first grid attribute do not include the portion that overlaps with the second grid position.

[0078] Specifically, the output of the first and second grid attribute information for the current frame includes grid occupancy status and the positions of the first and second grids. When the first and second grid positions overlap, and the second grid has higher precision than the first grid, the grid occupancy status in the second grid attribute is more accurate. To avoid outputting different occupancy statuses in overlapping areas, when outputting grid attribute information, only the grid occupancy status and second grid position of the second grid attribute are output for the overlapping area, excluding the grid occupancy status and first grid position of the first grid attribute. The output first and second grid positions and the grid occupancy status of the first and second grid attributes indicate whether the grid position is passable. The binary information of the output grid occupancy status can be provided to downstream autonomous driving modules, such as decision-making and planning modules and control modules.

[0079] Example 2

[0080] Example 2 provides an environmental monitoring device, such as Figure 5 As shown, the environmental monitoring device 400 includes: a positioning module 401, a sensing module 402, an environmental data processing module 403, and an environmental data output module 404.

[0081] The positioning module 401 is used to obtain the vehicle's position in the current frame, and the perception module 402 is used to obtain point cloud information.

[0082] The environmental data processing module 403 is used to generate a first grid position of a first precision grid map based on the vehicle's position and a first preset range, and to generate a second grid position of a second precision grid map based on the vehicle's position and a second preset range. The first precision and the second precision are different, and the first preset range and the second preset range are different. Based on the first grid position, the second grid position, and point cloud information, the module generates first grid attribute information and second grid attribute information for the first grid position and the second grid position, respectively.

[0083] The environmental data output module 404 is used to output the positions and attribute information of the first and second grids.

[0084] The environmental data processing module 403 is also used to determine whether the current frame is the initial frame; if so, it generates the first grid position of the first precision grid map based on the vehicle position and the first preset range, and generates the second grid position of the second precision grid map based on the vehicle position and the second preset range; if not, it updates the first grid position of the previous frame based on the vehicle position of the current frame and the first preset range to generate the first grid position of the current frame; and updates the second grid position of the previous frame based on the vehicle position of the current frame and the second preset range to generate the second grid position of the current frame.

[0085] The environmental data processing module 403 is also used to determine whether the first grid position and the second grid position of the current frame are both newly created grids; if so, it generates the first grid attribute information and the second grid attribute information of the first grid position and the second grid position respectively based on the first grid position, the second grid position and the point cloud information; if not, it inherits the first grid attribute information or the second grid attribute information of the overlapping grid position of the previous frame; and generates the first grid attribute information and the second grid attribute information of the current frame based on the point cloud information of the current frame and the inherited first and second grid attribute information.

[0086] Specifically, the environmental data processing module 403 inherits the first and second grid attribute information of the overlapping grid positions of the previous frame. Specifically: if the first grid position of the current frame is a newly created grid position and overlaps with the second grid position of the previous frame, it inherits the second grid attribute information of the previous frame; if the first grid position of the current frame is the same as the first grid position of the previous frame, it inherits the first grid attribute information of the previous frame; if the second grid position of the current frame is a newly created grid position and overlaps with the first grid position of the previous frame, it inherits the preset inheritable attribute information of the first grid attribute information of the previous frame; if the second grid position of the current frame is the same as the second grid position of the previous frame, it inherits the second grid attribute information of the previous frame.

[0087] The second preset range is set based on the vehicle's position; the first preset range is set based on the vehicle's position or according to the boundary of the second preset range.

[0088] The first precision is lower than the second precision, and the first preset range includes the second preset range.

[0089] The environmental data processing module 403 updates the first grid position of the previous frame and generates the first grid position of the current frame based on the vehicle position and the first preset range of the current frame. Specifically, it deletes the grid positions in the previous frame that are not within the first preset range of the current frame and creates new grid positions that enter the first preset range of the current frame.

[0090] The environmental data processing module 403 updates the second grid position of the previous frame based on the vehicle position and the second preset range of the current frame to generate the second grid position of the current frame. Specifically, it deletes grid positions in the previous frame that are not within the second preset range of the current frame and creates new grid positions that are within the second preset range of the current frame.

[0091] The environmental data output module 404 outputs the positions and attribute information of the first and second grids, specifically: the positions and attributes of the first grid do not include the parts that overlap with the positions of the second grids.

[0092] It should be noted that the division of the various modules in the above device is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these modules can be implemented entirely in software via processing elements; they can be fully implemented in hardware; or some modules can be implemented by processing elements calling software, while others are implemented in hardware. For example, the environmental data processing module can be a separate processing element, or it can be integrated into a chip in the above device. Alternatively, it can be stored as program code in the memory of the above device, and its functions can be called and executed by a processing element of the device. The implementation of other modules is similar. Moreover, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed through integrated logic circuits in the hardware of the processor element or through software instructions.

[0093] For example, these modules can be one or more integrated circuits configured to implement the above methods, such as one or more Application Specific Integrated Circuits (ASICs), one or more Digital Signal Processors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs). As another example, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together as a System-on-a-Chip (SOC).

[0094] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. This computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The aforementioned computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The aforementioned computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the aforementioned computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, Bluetooth, microwave, etc.) means. The aforementioned computer-readable storage medium can be any available medium that a computer can access, or a data storage device such as a server or data center that integrates one or more available media. The aforementioned available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks (SSDs)).

[0095] Example 3

[0096] Embodiment 3 provides a computer program product containing instructions that, when run on a computer, cause the computer to execute any of the environmental detection methods provided in Embodiment 1.

[0097] Example 4

[0098] Embodiment 4 of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the environmental detection methods provided in Embodiment 1.

[0099] Example 5

[0100] Embodiment 5 of the present invention provides a computer device, Figure 6 This is a schematic diagram of the computer device structure provided in Embodiment 5 of the present invention. Figure 6 As shown, it includes a memory 500, a processor 600, and a computer program stored in the memory. The processor executes the computer program to implement any of the environmental detection methods provided in Embodiment 1 above.

[0101] Example 6

[0102] Embodiment 6 of the present invention provides a mobile tool, including the computer device described in Embodiment 5 above.

[0103] The mobile equipment referred to in this application can be vehicle equipment or robotic equipment with the following various functions:

[0104] (1) Passenger transport function, such as family cars, buses, etc.;

[0105] (2) Cargo carrying function, such as ordinary trucks, box trucks, trailers, enclosed trucks, tank trucks, flatbed trucks, container trucks, dump trucks, special structure trucks, etc.

[0106] (3) Tool functions, such as logistics delivery vehicles, automated guided vehicles (AGVs), patrol vehicles, cranes, hoists, excavators, bulldozers, loaders, road rollers, loaders, off-road engineering vehicles, armored engineering vehicles, sewage treatment vehicles, sanitation vehicles, vacuum trucks, floor scrubbers, water sprinkler trucks, sweeping robots, food delivery robots, shopping guide robots, lawnmowers, golf carts, etc.

[0107] (4) Entertainment functions, such as recreational vehicles, amusement park equipment, balance bikes, etc.;

[0108] (5) Special rescue functions, such as fire trucks, ambulances, power repair vehicles, and engineering emergency rescue vehicles.

[0109] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0110] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0111] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented in hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0112] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An environmental detection method, characterized in that, The method includes: Obtain the vehicle's position and point cloud information for the current frame; The first grid position of the first precision grid map is generated based on the vehicle position and the first preset range, and the second grid position of the second precision grid map is generated based on the vehicle position and the second preset range. The first precision is different from the second precision, and the first preset range is different from the second preset range. Based on the first grid position, the second grid position, and the point cloud information, generate first grid attribute information and second grid attribute information for the first grid position and the second grid position, respectively. Output the positions and attribute information of the first and second grid cells; Determine whether the first and second grid positions of the current frame are both newly created grids; If so, based on the first grid position, the second grid position, and the point cloud information, generate the first grid attribute information and the second grid attribute information for the first grid position and the second grid position, respectively; If not, inherit the first or second grid attribute information of the overlapping grid position of the previous frame; generate the first and second grid attribute information of the current frame based on the point cloud information of the current frame and the inherited first and second grid attribute information; Specifically, the inheritance of the first and second grid attribute information from the overlapping grid positions of the previous frame includes: If the first grid position of the current frame is a newly created grid position and overlaps with the second grid position of the previous frame, inherit the attribute information of the second grid of the previous frame; If the first grid position of the current frame is the same as the first grid position of the previous frame, inherit the first grid attribute information of the previous frame; If the second grid position of the current frame is a newly created grid position and overlaps with the first grid position of the previous frame, the preset inheritable attribute information of the first grid attribute information of the previous frame is inherited. If the second grid position of the current frame is the same as the second grid position of the previous frame, the second grid attribute information of the previous frame is inherited.

2. The environmental monitoring method according to claim 1, characterized in that, The second preset range is set based on the vehicle's position.

3. The environmental monitoring method according to claim 2, characterized in that, The first preset range is set based on the vehicle's position or according to the boundary of the second preset range.

4. The environmental monitoring method according to claim 2, characterized in that, The first precision is lower than the second precision, and the first preset range includes the second preset range.

5. The environmental monitoring method according to claim 1, characterized in that, The method further includes: Determine if the current frame is the initial frame; If so, generate the first grid position of the first precision grid map based on the vehicle position and the first preset range, and generate the second grid position of the second precision grid map based on the vehicle position and the second preset range; If not, update the first grid position of the previous frame based on the vehicle position of the current frame and the first preset range to generate the first grid position of the current frame; update the second grid position of the previous frame based on the vehicle position of the current frame and the second preset range to generate the second grid position of the current frame.

6. The environmental monitoring method according to claim 5, characterized in that, The step of updating the first grid position of the previous frame based on the vehicle position of the current frame and the first preset range to generate the first grid position of the current frame is specifically as follows: Delete grid positions from the previous frame that are not within the first preset range of the current frame, and create new grid positions that are within the first preset range of the current frame.

7. The environmental monitoring method according to claim 5, characterized in that, The step of updating the second grid position of the previous frame based on the vehicle position of the current frame and the second preset range to generate the second grid position of the current frame is specifically as follows: Delete the grid positions in the previous frame that are not within the second preset range of the current frame, and create new grid positions that are within the second preset range of the current frame.

8. The environmental monitoring method according to claim 4, characterized in that, The output of the first and second grid positions and the first and second grid attribute information specifically includes: The first grid position and first grid attributes do not include the portion that overlaps with the second grid position.

9. An environmental monitoring device, characterized in that, The environmental monitoring device includes: The system includes a positioning module and a perception module. The positioning module is used to obtain the vehicle's position in the current frame, and the perception module is used to obtain point cloud information. An environmental data processing module is configured to generate a first grid position of a first-precision raster map based on the vehicle's position and a first preset range, and to generate a second grid position of a second-precision raster map based on the vehicle's position and a second preset range, wherein the first precision and the second precision are different, and the first preset range and the second preset range are different; generate first grid attribute information and second grid attribute information for the first grid position and the second grid position respectively based on the first grid position, the second grid position, and point cloud information; and determine whether the first grid position and the second grid position in the current frame are both newly created rasters. If so, based on the first grid position, the second grid position, and the point cloud information, generate the first grid attribute information and the second grid attribute information for the first grid position and the second grid position, respectively; If not, inherit the first or second grid attribute information of the overlapping grid position of the previous frame; generate the first and second grid attribute information of the current frame based on the point cloud information of the current frame and the inherited first and second grid attribute information; Specifically, the inheritance of the first and second grid attribute information from the overlapping grid positions of the previous frame includes: If the first grid position of the current frame is a newly created grid position and overlaps with the second grid position of the previous frame, inherit the attribute information of the second grid of the previous frame; If the first grid position of the current frame is the same as the first grid position of the previous frame, inherit the first grid attribute information of the previous frame; If the second grid position of the current frame is a newly created grid position and overlaps with the first grid position of the previous frame, the preset inheritable attribute information of the first grid attribute information of the previous frame is inherited. If the second grid position of the current frame is the same as the second grid position of the previous frame, inherit the second grid attribute information of the previous frame; An environmental data output module is used to output the positions and attribute information of the first and second grid cells.

10. A computer-readable storage 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 described in claims 1-8.

11. A computer device comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to claims 1-8.

12. A mobile tool, characterized in that, Includes the computer device as described in claim 11.

Images