A path planning method and device, and related products

Abstract

The present application relates to a kind of path planning method and device, related product, according to the interpolation processing of ground height data measured to generate grid height map;According to the gradient descent value and gradient direction vector of each grid in grid height map, the height gradient vector of grid is calculated;Path planning is carried out in grid height map, the included angle between the heading information of path point and the height gradient vector of the grid where path point is located is calculated;According to the included angle, the cost value of path point is calculated according to cost function;According to the cost value, the planned path is adjusted.The present application generates grid height map, calculates the included angle between the heading information and the height gradient vector in the grid of path point, so that the road slope is accurately considered in path search, so as to improve the safety of automatic driving path planning and improve the passing efficiency of automatic driving vehicle.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to a path planning method, a path planning device, a computer server, a chip system, a computer-readable storage medium, a computer program product containing instructions, and a mobile tool. Background Technology

[0002] Autonomous driving systems include modules such as high-precision maps, localization, perception, decision-making, path planning, and control. High-precision maps, as a component of the autonomous driving system, support almost all other modules. In environments with complex terrain, such as rugged mountain roads, maps provide information on road undulations to assist the path planning module in making more reasonable plans, thereby avoiding impassable potholes and bumps, or utilizing ramps to improve driving efficiency.

[0003] Current technical solutions use height grid maps in map modules to represent ground undulations. They filter out potholes or bumps by setting thresholds, or abstract the ground as a road and describe slope information along the driving direction to be considered and avoided during path planning. However, existing solutions can only express slope characteristics like the presence of potholes or bumps, or roughly indicate the existence of uphill or downhill slopes, but cannot quantitatively express precise slope and aspect information. This results in inflexible backend path planning, limiting vehicle passability and driving efficiency. Summary of the Invention

[0004] The purpose of this invention is to address the shortcomings of existing technologies by providing a path planning method and apparatus. This method generates a grid height map, calculates and stores the height gradient vector corresponding to each grid point in the grid height map, acquires the heading information of path points during path planning, and calculates the angle between the heading information and the height gradient vector of the grid where the path point is located. Based on this angle, the corresponding cost is calculated, thereby accurately considering road slope in path search, thus improving the safety of autonomous driving path planning and increasing the traffic efficiency of autonomous vehicles.

[0005] To achieve the above objectives, the first aspect of the present invention provides a path planning method, the method comprising:

[0006] The raster map is generated by interpolating the ground height data obtained from the measurement.

[0007] Determine the gradient descent value and target gradient direction vector of each grid cell in the grid height map, and calculate the height gradient vector corresponding to each grid cell based on the gradient descent value and target gradient direction vector of each grid cell;

[0008] Path planning is performed in the grid height map. When searching for path points during the path planning process, the angle between the heading information of the path point and the height gradient vector of the grid where the path point is located is calculated.

[0009] The cost value of the path point is determined based on the included angle and a preset cost function, wherein the more consistent the included angle is with the road slope requirement of the planned path, the smaller the cost value calculated by the cost function.

[0010] Preferably, determining the gradient descent value and target gradient direction vector of each grid cell in the grid height map specifically includes:

[0011] Each grid in the grid height map is taken as the target grid; for each target grid, multiple adjacent grids of the target grid are determined; and the gradient descent value and target gradient direction vector of the target grid are determined based on the height value and gradient direction vector of the adjacent grids of the target grid.

[0012] More preferably, the gradient descent value and target gradient direction vector of the target grid are determined based on the height values ​​and gradient direction vectors of the adjacent grids of the target grid, specifically including:

[0013] For each adjacent grid cell, the gradient descent value of the adjacent grid cell is determined based on the height value and gradient direction vector of the adjacent grid cell;

[0014] Select the neighboring grid with the largest gradient descent value, and determine the gradient descent value and gradient direction vector of the neighboring grid as the gradient descent value and target gradient direction vector of the target grid.

[0015] Preferably, the cost function is set as follows:

[0016] f = (θ / π)*grad(x,y), where f is the cost of the path point, grad(x,y) is the gradient descent value of the grid cell containing the path point, and θ is the angle between the heading information of the path point and the height gradient vector of the grid cell containing the path point.

[0017] Preferred options also include:

[0018] The height gradient vector corresponding to each grid cell is stored in the grid height map.

[0019] A second aspect of the present invention provides a path planning apparatus, characterized in that the apparatus comprises:

[0020] An interpolation processing module is used to interpolate the grid map based on the measured ground height data to generate a grid height map.

[0021] The vector calculation module determines the gradient descent value and target gradient direction vector of each grid in the grid height map, and calculates the height gradient vector corresponding to each grid based on the gradient descent value and target gradient direction vector of each grid.

[0022] The path planning module performs path planning on the grid height map. During the path planning process, when searching for path points, it calculates the angle between the heading information of the path point and the height gradient vector of the grid where the path point is located.

[0023] The cost value module determines the cost value of the path point based on the included angle and a preset cost function.

[0024] A third aspect of the present invention provides a computer server, characterized in that it includes: a memory, a processor, and a transceiver;

[0025] The processor is used to couple with the memory, read and execute instructions in the memory to implement the path planning method as described in the first aspect;

[0026] The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

[0027] A fourth aspect of the present invention provides a chip system, characterized in that it includes a processor coupled to a memory, the memory storing program instructions, and when the program instructions stored in the memory are executed by the processor, the path planning method as described in the first aspect is implemented.

[0028] The fifth aspect of the present invention provides a computer-readable storage medium, characterized in that it includes a program or instructions that, when run on a computer, implement the path planning method as described in the first aspect.

[0029] The sixth aspect of the present invention provides a computer program product containing instructions, characterized in that, when the computer program product is run on a computer, the computer performs the path planning method as described in the first aspect.

[0030] A seventh aspect of the present invention provides a mobile tool, characterized in that it includes the computer server described in the third aspect above.

[0031] This invention provides a path planning method and apparatus. By generating a grid height map, calculating and storing the height gradient vector corresponding to each grid point in the grid height map, obtaining the heading information of the path point during the path planning process, and calculating the angle between the heading information and the height gradient vector within the grid of the path point, the corresponding cost is calculated based on the angle, thereby accurately considering the road slope in the path search, thus improving the safety of autonomous driving path planning and increasing the traffic efficiency of autonomous driving. Attached Figure Description

[0032] Figure 1 A flowchart of the path planning method provided in Embodiment 1 of the present invention;

[0033] Figure 2 This is a schematic diagram of the computational grid provided in Embodiment 1 of the present invention;

[0034] Figure 3 This is a schematic diagram of path planning provided in Embodiment 1 of the present invention;

[0035] Figure 4 This is a structural block diagram of the path planning device provided in Embodiment 2 of the present invention. Detailed Implementation

[0036] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

[0037] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0038] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other.

[0039] This invention can be described in the general context of computer-executable instructions, such as program modules, that are executed by a computer. Generally, program modules include routines, programs, objects, elements, data structures, etc., that perform a specific task or implement a specific abstract data type. This invention can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0040] In this invention, terms such as "module," "device," and "system" refer to relevant entities applied to a computer, such as hardware, combinations of hardware and software, software, or software in execution. More specifically, for example, an element can be, but is not limited to, a process running on a processor, a processor, an object, an executable element, an execution thread, a program, and / or a computer. Furthermore, an application program or script running on a server, and the server itself, can also be an element. One or more elements may be in an execution process and / or thread, and elements may be localized on a single computer and / or distributed across two or more computers, and may be run on various computer-readable media. Elements can also communicate via local and / or remote processes based on signals having one or more data packets, for example, signals from data interacting with another element in a local system, a distributed system, and / or interacting with other systems via signals over a network of the Internet.

[0041] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising" or "including" include not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0042] The path planning method in this embodiment of the invention can be applied to a path planning device, enabling users to plan routes in various scenarios. The path planning device can be, for example, but not limited to, devices such as smartphones, tablets, personal PCs, computers, and cloud servers. Specifically, the path planning method in this embodiment of the invention can also be applied to mobile vehicles, such as autonomous passenger vehicles, minibuses, buses, trucks, unmanned cleaning vehicles, unmanned sanitation vehicles, unmanned delivery vehicles, and robotic vacuum cleaners; this invention does not limit its application to these applications.

[0043] This invention provides a path planning method that generates a grid height map, calculates and stores the height gradient vector corresponding to each grid point in the grid height map, obtains the heading information of the path point during the path planning process, and calculates the angle between the heading information and the height gradient vector within the grid of the path point. Based on the angle, the corresponding cost value is calculated, thereby accurately considering the road slope in the path search, thus improving the safety of autonomous driving path planning and increasing the traffic efficiency of autonomous vehicles.

[0044] Example 1

[0045] Figure 1 A flowchart of a path planning method provided in an embodiment of the present invention, the method comprising:

[0046] Step 100: Interpolate the raster map based on the measured ground height data to generate a raster height map.

[0047] First, the raster map is interpolated based on the actual measured ground height data to generate a raster height map. The ground height data can be measured using a laser sensor, and the distance between the grids in the generated raster height map can be, for example, 5 cm.

[0048] Step 110: Determine the gradient descent value and target gradient direction vector of each grid in the grid height map, and calculate the height gradient vector corresponding to each grid based on the gradient descent value and target gradient direction vector of each grid.

[0049] In one embodiment, step 110 can be implemented as follows:

[0050] First, each cell in the grid height map is used as the target cell;

[0051] Secondly, for each adjacent grid cell, the gradient descent value of the adjacent grid cell is determined based on the height value and gradient direction vector of the adjacent grid cell; the adjacent grid cell with the largest gradient descent value is selected, and the gradient descent value and gradient direction vector of the adjacent grid cell are determined as the gradient descent value and target gradient direction vector of the target grid cell.

[0052] In one specific embodiment, the N surrounding adjacent grids of the target grid can be considered as adjacent grids, for example, the 8 surrounding grids or 24 surrounding grids can be considered as adjacent grids. Figure 2 As shown, the eight surrounding grids of the target grid w0 are considered its neighboring grids. The gradient descent values ​​for each of the eight target grids are calculated using the following formula:

[0053]

[0054] Among them, (x i y i ) represents the i-th adjacent cell. Let Δwi be the gradient descent value of the i-th adjacent grid cell, Δxi be the height value of the i-th adjacent grid cell, and (Δxi, Δyi) be the gradient direction vector of the i-th adjacent grid cell.

[0055] Where (x0, y0) is the target grid. This represents the gradient descent value of the target raster.

[0056] Next, the gradient descent value of the target grid is multiplied by the gradient direction vector of the target grid to obtain the height gradient vector of the target grid.

[0057] Step 120: Perform path planning in the grid height map. When searching for path points during the path planning process, calculate the angle between the heading information of the path point and the height gradient vector of the grid where the path point is located.

[0058] Specifically, path planning is performed in the grid height map, and during the path planning process, when searching for waypoints, the driving direction of the heading information within the waypoint grid is obtained, expressed as a unit vector: L=(Δx c ,Δy c Then, calculate the angle θ between vector L and the height gradient vector within the corresponding grid cell based on the vector dot product (where 0 <= θ <= π):

[0059] When θ = 0, the vector L coincides with the direction of the height gradient vector. When the vehicle travels along this direction, its height decreases the fastest, that is, this direction is the direction with the steepest downhill slope.

[0060] When 0 < θ < π / 2, the vector L is in the same direction as the height gradient vector. When the vehicle travels in this direction, its height will decrease, but it is not the direction of the fastest decrease. That is, this direction is downhill, but not the steepest downhill direction.

[0061] When θ = π / 2, the vector L is perpendicular to the direction of the height gradient vector. The vehicle's height remains unchanged when it travels along this direction, which is flat ground.

[0062] When π / 2 < θ < π, the vector L is opposite to the height gradient vector. When the vehicle travels in this direction, its height will increase. That is, this direction is the uphill direction, but it is not the steepest uphill direction.

[0063] When θ = π, the vector L is in the exact opposite direction to the height gradient vector. The vehicle's height increases the fastest when traveling in this direction, which is the direction with the steepest uphill slope.

[0064] Step 130: Determine the cost of the path point based on the included angle and the preset cost function.

[0065] The cost of a path point is determined based on the included angle θ calculated in step 120 and the preset cost function. The closer the included angle θ is to the road gradient requirement of the planned path, the smaller the calculated cost. For example, when the road planning requires vehicles to descend the slope at the fastest speed, the cost function can be set as follows:

[0066] f = (θ / π)*grad(x,y), where f is the cost of the path point, grad(x,y) is the gradient descent value of the grid cell containing the path point, and θ is the angle between the heading information of the path point and the height gradient vector of the grid cell containing the path point.

[0067] The closer the included angle is to the road slope requirement in the planned path of the autonomous vehicle, the smaller the cost value calculated by the cost function. By readjusting the planned path and accurately considering the road slope, the safety and driving efficiency of the autonomous vehicle can be improved.

[0068] Figure 3 This is a schematic diagram of path planning provided in Embodiment 1 of the present invention, as shown below. Figure 3 As shown, l1 is the cumulative planned route with an angle of 0 between the vehicle's driving direction and the gradient direction, l2 is the cumulative planned route with an angle of π / 2 between the vehicle's driving direction and the gradient direction, and l3 is the cumulative planned route with an angle of π between the vehicle's driving direction and the gradient direction. Here, l1 is the route with the fastest descent, l2 is the route with the vehicle traveling horizontally, and l3 is the route with the fastest ascent. In the path planning method provided in Embodiment 1 of this invention, the slope and aspect information of path points can be accurately expressed by calculating the height gradient vector of the grid, and the cost of the angle with the vehicle's driving direction is calculated, improving the accuracy of path planning for autonomous vehicles, enhancing the safety of autonomous vehicles, and increasing the driving efficiency of autonomous vehicles.

[0069] Example 2

[0070] Embodiment 2 of the present invention provides a path planning device. Figure 4 This is a structural block diagram of the path planning device provided in Embodiment 2 of the present invention, as shown below. Figure 4 As shown, the path planning device includes: an interpolation processing module 401, a vector calculation module 402, a path planning module 403, and a cost module 404.

[0071] Interpolation processing module 401 performs interpolation processing on the grid map based on the ground height data measured by the laser sensor to generate a grid height map.

[0072] The vector calculation module 402 calculates the height gradient vector corresponding to each grid cell based on the gradient descent value and the target gradient direction vector of each grid cell in the grid height map generated by the interpolation processing module 401.

[0073] The path planning module 403 performs path planning in the grid height map, and when searching for path points during the path planning process, it calculates the angle between the heading information of the path point and the height gradient vector of the grid where the path point is located.

[0074] The cost value module 404 determines the cost value of the path point based on the included angle and a preset cost function.

[0075] Example 3

[0076] Embodiment 3 of the present invention provides a computer server, including: a memory, a processor, and a transceiver;

[0077] The processor is used to couple with the memory, read and execute instructions in the memory to implement any of the path planning methods provided in Embodiment 1 above;

[0078] The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

[0079] Example 4

[0080] Embodiment 4 of the present invention provides a chip system including a processor and a memory coupled together. The memory stores program instructions. When the program instructions stored in the memory are executed by the processor, any path planning method as provided in Embodiment 1 is implemented.

[0081] Example 5

[0082] Embodiment 5 of the present invention provides a computer system, including a memory and one or more processors communicatively connected to the memory;

[0083] The memory stores instructions that can be executed by one or more processors to enable one or more processors to implement any of the path planning methods provided in Embodiment 1.

[0084] Example 6

[0085] Embodiment 6 of the present invention provides a computer-readable storage medium including a program or instructions, which, when run on a computer, implements any of the path planning methods provided in Embodiment 1.

[0086] Example 7

[0087] Example 7 provides a computer program product containing instructions that, when run on a computer, cause the computer to execute any of the path planning methods provided in Example 1.

[0088] Example 8

[0089] Embodiment 8 of the present invention provides a mobile tool, including the aforementioned computer server. The mobile tool can be any movable tool, such as vehicles (e.g., passenger cars, buses, coaches, vans, trucks, heavy-duty vehicles, trailers, drop trailers, cranes, excavators, bulldozers, road trains, sweepers, water trucks, garbage trucks, engineering vehicles, rescue vehicles, logistics carts, AGVs (Automated Guided Vehicles), etc.), motorcycles, bicycles, tricycles, handcarts, robots, sweepers, balance scooters, etc. This application does not strictly limit the type of mobile tool, and will not exhaustively list them here.

[0090] The path planning method and apparatus of the present invention generate a grid height map, calculate the height gradient vector corresponding to each grid point and store it in the grid height map, obtain the heading information of the path point during the path planning process, and calculate the angle between the heading information and the height gradient vector in the grid of the path point, and calculate the corresponding cost value based on the angle, thereby accurately considering the road slope in the path search, thereby improving the safety of autonomous driving path planning and improving the traffic efficiency of autonomous vehicles.

[0091] 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.

[0092] 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.

[0093] 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. A path planning method, characterized in that, The method includes: The raster map is generated by interpolating the ground height data obtained from the measurement. Determine the gradient descent value and target gradient direction vector of each grid cell in the grid height map, and calculate the height gradient vector corresponding to each grid cell based on the gradient descent value and target gradient direction vector of each grid cell; Path planning is performed in the grid height map. When searching for path points during the path planning process, the angle between the heading information of the path point and the height gradient vector of the grid where the path point is located is calculated. The cost value of the path point is determined based on the included angle and a preset cost function, wherein the more consistent the included angle is with the road slope requirement of the planned path, the smaller the cost value calculated by the cost function.

2. The path planning method according to claim 1, characterized in that, Determine the gradient descent value and target gradient direction vector for each grid cell in the grid height map, specifically including: Each grid in the grid height map is taken as the target grid; for each target grid, multiple adjacent grids of the target grid are determined; and the gradient descent value and target gradient direction vector of the target grid are determined based on the height value and gradient direction vector of the adjacent grids of the target grid.

3. The path planning method according to claim 2, characterized in that, Based on the height values ​​and gradient direction vectors of the target grid's adjacent grids, the gradient descent value and target gradient direction vector of the target grid are determined, specifically including: For each adjacent grid cell, the gradient descent value of the adjacent grid cell is determined based on the height value and gradient direction vector of the adjacent grid cell; Select the neighboring grid with the largest gradient descent value, and determine the gradient descent value and gradient direction vector of the neighboring grid as the gradient descent value and target gradient direction vector of the target grid.

4. The path planning method according to claim 1, characterized in that, The cost function is set as follows: f=(θ / )*grad(x,y), where f is the cost of the path point, grad(x,y) is the gradient descent value of the grid where the path point is located, θ is the angle between the heading information of the path point and the height gradient vector of the grid where the path point is located; (x,y) represents the coordinates of the grid where the path point is located in the grid height map.

5. The path planning method according to claim 1, characterized in that, Also includes: The height gradient vector corresponding to each grid cell is stored in the grid height map.

6. A path planning device, characterized in that, The device includes: An interpolation processing module is used to interpolate the grid map based on the measured ground height data to generate a grid height map. The vector calculation module determines the gradient descent value and target gradient direction vector of each grid in the grid height map, and calculates the height gradient vector corresponding to each grid based on the gradient descent value and target gradient direction vector of each grid. The path planning module performs path planning on the grid height map. During the path planning process, when searching for path points, it calculates the angle between the heading information of the path point and the height gradient vector of the grid where the path point is located. The cost value module determines the cost value of the path point based on the included angle and a preset cost function.

7. A computer server, characterized in that, include: Memory, processor, and transceiver; The processor is used to couple with the memory, read and execute instructions in the memory to implement the path planning method according to any one of claims 1-5; The transceiver is coupled to the processor, and the processor controls the transceiver to send and receive messages.

8. A chip system, characterized in that, The device includes a processor coupled to a memory storing program instructions, which, when executed by the processor, implement the path planning method according to any one of claims 1-5.

9. A computer-readable storage medium, characterized in that, Includes a program or instructions that, when run on a computer, implement the path planning method according to any one of claims 1-5.

10. A computer program product containing instructions, characterized in that, When the computer program product is run on a computer, the computer performs the path planning method according to any one of claims 1-5.

11. A mobile tool, characterized in that, Includes the computer server described in claim 7 above.

Images