Curve position path planning method, device and equipment based on deformation grid map and storage medium

Abstract

The invention discloses a curve position path planning method and device based on a deformation grid map, equipment and a storage medium, and relates to the technical field of intelligent driving path planning, and the method comprises the steps: obtaining a deformation grid map and a path search algorithm; path planning is carried out on the deformed grid map based on the path search algorithm to find a target grid, a driving path is determined, and the path planning comprises path search, collision detection and path reconstruction; and carrying out smoothing processing on the driving path to determine a driving optimization path, and controlling vehicle driving based on the driving optimization path to complete path planning. According to the method, path planning is carried out on the deformed grid map by utilizing path search, collision detection and path reconstruction, the search time is shortened by optimizing a path search algorithm, the efficiency of path planning is improved, the curve contour is more accurately fitted, the accuracy of path planning is improved, the path is dynamically adjusted by carrying out collision detection to avoid obstacles, and the accuracy of path planning is improved. And the driving safety of the vehicle is obviously improved.

Description

Technical Field

[0001] The present application relates to the technical field of intelligent driving path planning, and in particular to a method, device, equipment and storage medium for curve position path planning based on a deformed grid map. Background Art

[0002] With the development of autonomous driving and robot navigation technology, the demand for path planning is growing. Especially in the complex environment of urban roads or narrow curves, the accuracy and efficiency of path planning are directly related to the safety and reliability of the autonomous driving system. Therefore, a path planning method that can adapt to complex curve environments is needed to ensure that vehicles or robots can pass through curves safely and efficiently.

[0003] Currently, the existing practice is to construct a grid map and expand obstacles, construct a topological map and set topological points at the exit and entrance of the narrow passage, and use the topological map and search algorithm for path planning.

[0004] However, existing approaches do not perform well in complex curved environments, especially in terms of the accuracy of the path fitting the curve contour, which cannot meet the needs of high-precision path planning. In complex curved environments, the planned driving path cannot ensure that it fits the curve contour, resulting in reduced accuracy and safety of path planning. In addition, the vehicle's driving performance and safety planning are not considered, and there are driving risks in actual applications. Therefore, how to plan a driving path more efficiently, accurately and safely has become an urgent problem to be solved.

[0005] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0006] The main purpose of this application is to provide a curve location path planning method, device, equipment and storage medium based on a deformed grid map, aiming to solve the technical problem of how to plan a driving path more efficiently, accurately and safely.

[0007] To achieve the above objectives, the present application proposes a method for planning a curve path based on a deformed grid map, the method comprising:

[0008] Get the deformed grid map and path search algorithm;

[0009] Based on the path search algorithm, path planning is performed on the deformed grid map to find the target grid and determine the driving path, wherein the path planning includes path search, collision detection and path reconstruction;

[0010] The driving path is smoothed to determine an optimized driving path, and the vehicle is controlled to complete path planning based on the optimized driving path.

[0011] In one embodiment, the step of obtaining a deformed grid map and a path search algorithm comprises:

[0012] Obtain environmental data, curve characteristics, grid deformation status and heuristic functions;

[0013] Performing a preprocessing operation on the environmental data to determine preprocessed environmental data, wherein the preprocessing operation includes filtering, denoising and coordinate conversion;

[0014] Constructing a deformation grid map based on the preprocessed environmental data and the curve characteristics;

[0015] A path search algorithm is determined by adjusting grid parameters in the heuristic function based on the grid deformation state, wherein the heuristic function includes Manhattan distance and Euclidean distance.

[0016] In one embodiment, the step of performing path planning on the deformed grid map based on the path search algorithm to find the target grid and determine the driving path includes:

[0017] Get the starting grid and the target grid;

[0018] Performing a path search on the deformed grid map based on the path search algorithm, the starting grid and the target grid to determine a current grid;

[0019] Perform collision detection based on the current grid to mark the obstacle grid and determine the extended grid;

[0020] The path is reconstructed based on the extended grid and the starting grid to obtain a driving path.

[0021] In one embodiment, the step of performing path search on the deformed grid map based on the path search algorithm, the starting grid and the target grid to determine the current grid includes:

[0022] Expand adjacent grids based on the path search algorithm, the starting grid, and the target grid to determine an adjacent grid set;

[0023] Calculate a grid cost value set and a grid heuristic value set based on the adjacent grid set;

[0024] An extended necessary cost grid is selected based on the grid cost value set and the grid heuristic value set to obtain a current grid.

[0025] In one embodiment, the step of performing collision detection based on the current grid to mark the obstacle grid and determine the extended grid comprises:

[0026] Get the obstacle grid;

[0027] Detecting obstacle existence status based on the current grid and the obstacle grid, and determining a grid mark;

[0028] The obstacle avoidance grid is marked based on the grid to obtain an extended grid.

[0029] In one embodiment, the step of reconstructing the path based on the extended grid and the starting grid to obtain the driving path includes:

[0030] Taking the extended grid as the target grid, determining the backtracking starting point;

[0031] Determine a backtracking target point based on the starting grid;

[0032] The target search path is traced back based on the backtracking starting point and the backtracking target point to reconstruct the driving path.

[0033] In one embodiment, the step of smoothing the driving path to determine the optimized driving path includes:

[0034] Acquire a smoothing algorithm and a vehicle driving condition, wherein the smoothing algorithm includes a spline curve;

[0035] The driving path is smoothed based on the smoothing algorithm and the vehicle driving conditions to reduce potential interference items and obtain an optimized driving path.

[0036] In addition, to achieve the above purpose, the present application also proposes a curve position path planning device based on a deformed grid map, and the curve position path planning device based on a deformed grid map includes:

[0037] An acquisition module, used to obtain a deformed grid map and a path search algorithm;

[0038] A processing module, used for performing path planning on the deformed grid map based on the path search algorithm to find the target grid and determine the driving path, wherein the path planning includes path search, collision detection and path reconstruction;

[0039] The execution module is used to smooth the driving path to determine the driving optimization path, and control the vehicle driving based on the driving optimization path to complete the path planning.

[0040] In addition, to achieve the above-mentioned purpose, the present application also proposes a curve position path planning device based on a deformed grid map, the device comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, the computer program being configured to implement the steps of the curve position path planning method based on a deformed grid map as described above.

[0041] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the curve position path planning method based on the deformed grid map as described above are implemented.

[0042] One or more technical solutions proposed in this application have at least the following technical effects:

[0043] The present embodiment proposes a method for planning a path for a curve position based on a deformed grid map, which obtains a deformed grid map and a path search algorithm; based on the path search algorithm, the deformed grid map is used for path planning to find a target grid and determine a driving path, wherein the path planning includes path search, collision detection and path reconstruction; the driving path is smoothed to determine a driving optimization path, and the vehicle is controlled to complete the path planning based on the driving optimization path. The present application obtains a deformed grid map and a path search algorithm, and uses path search, collision detection and path reconstruction to plan a path for the deformed grid map, and performs smoothing to determine a driving optimization path to control vehicle driving, more accurately fit the curve contour, and improve the accuracy of path planning. By optimizing the path search algorithm, the search time is reduced, and the efficiency of path planning is improved. By performing real-time collision detection and dynamically adjusting the path to avoid obstacles, the driving safety of the vehicle is improved. At the same time, by smoothing the path, sharp turns and bumps are reduced, driving comfort is improved, and efficient, accurate and safe path planning is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0046] Figure 1 A flow chart of a method for planning a path along a curve based on a deformed grid map according to an embodiment of the present invention;

[0047] Figure 2 This is a schematic diagram of a scenario of a curve location path planning method based on a deformed grid map in this application;

[0048] Figure 3 A flow chart of the second embodiment of the method for planning a path for a curve position based on a deformed grid map provided in the present application;

[0049] Figure 4 A schematic diagram of a simplified process of a curve location path planning method based on a deformed grid map provided in an embodiment of the present application;

[0050] Figure 5 This is a schematic diagram of the module structure of a curve position path planning device based on a deformed grid map according to an embodiment of the present application;

[0051] Figure 6 Schematic diagram of the device structure of the hardware operating environment involved in the curve position path planning method based on the deformed grid map in the embodiment of the present application.

[0052] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0053] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0054] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0055] The main solution of the embodiment of the present application is: obtaining a deformed grid map and a path search algorithm; performing path planning on the deformed grid map based on the path search algorithm to find the target grid and determine the driving path, wherein the path planning includes path search, collision detection and path reconstruction; smoothing the driving path to determine the optimized driving path, and controlling the vehicle driving based on the optimized driving path to complete the path planning.

[0056] In this embodiment, for ease of description, the following description is made by taking the device for identifying the path planning of the curve position based on the deformed grid map as the execution subject.

[0057] Since the existing technology does not perform well in complex curved environments, especially in terms of the accuracy of the path fitting the curve contour, it cannot meet the needs of high-precision path planning. In complex curved environments, the planned driving path cannot ensure that it fits the curve contour, resulting in reduced accuracy and safety of path planning. In addition, the vehicle's driving performance and safety planning are not taken into consideration, which poses driving risks in actual applications.

[0058] The present application provides a solution, which includes obtaining a deformed grid map and a path search algorithm; performing path planning on the deformed grid map based on the path search algorithm to find a target grid and determine a driving path, wherein the path planning includes path search, collision detection and path reconstruction; smoothing the driving path to determine an optimized driving path, and controlling vehicle driving based on the optimized driving path to complete path planning.

[0059] It can be seen from the above embodiments that the present application obtains a deformed grid map and a path search algorithm, uses path search, collision detection and path reconstruction to perform path planning on the deformed grid map, and performs smoothing to determine the optimized driving path to control vehicle driving, more accurately fit the curve contour, and improve the accuracy of path planning. By optimizing the path search algorithm, the search time is reduced and the efficiency of path planning is improved. By performing real-time collision detection and dynamically adjusting the path to avoid obstacles, the driving safety of the vehicle is improved. At the same time, by smoothing the path, sharp turns and bumps are reduced, driving comfort is improved, and efficient, accurate and safe path planning is achieved.

[0060] Based on this, the embodiment of the present application provides a curve position path planning method based on a deformed grid map, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the curve location path planning method based on the deformed grid map of the present application.

[0061] In this embodiment, the curve position path planning method based on the deformed grid map includes steps S10 to S30:

[0062] Step S10, obtaining a deformed grid map and a path search algorithm;

[0063] It should be noted that the deformed grid map reflects the feature of dividing roads into various grids to form a grid map, and the path search algorithm reflects the path feature of adapting to the deformed grid by adjusting the parameters in the heuristic function.

[0064] It can be understood that the deformed grid map can characterize the curvature and width of the curve, and the grid is deformed according to the characteristics of the curve, so as to more accurately fit the actual road contour, provide more detailed and accurate environmental information for path planning, adapt to the complex and changeable curve environment, and improve the adaptability and accuracy of path planning. The path search algorithm defines a heuristic function to improve the algorithm to evaluate and select the optimal path, such as Figure 2 As shown, Figure 2 This is a scenario diagram of the curve location path planning method based on the deformed grid map of this application. The closer the deformed grid is to the inner curve, the smaller the grid is, and the closer to the outside of the curve, the larger the grid is. The grid sizes are inconsistent, while each grid in the conventional grid is consistent. Therefore, the grid parameters in the heuristic function can be adjusted to adapt to the characteristics of the deformed grid and effectively search for the path from the starting point to the target point.

[0065] For ease of understanding, the following is explained by taking the acquisition of a deformed grid map and a path search algorithm as an example, wherein the information collection device is an information collection module, and the storage device is a memory.

[0066] The information acquisition module obtains environmental data, curve characteristics, grid deformation status and heuristic functions, that is, uses lidar, camera and other sensors to collect environmental data, including the location information, shape information and size information of obstacles, and preprocesses the environmental data to determine the preprocessed environmental data, that is, preprocesses the collected data, including filtering, denoising, coordinate conversion and other operations to improve the accuracy and reliability of the data, and constructs a deformed grid map based on the preprocessed environmental data and the curve characteristics, that is, divides the environment into multiple grid units, each grid represents a small area, and the size of the grid can be adjusted according to the actual environment and path planning requirements, thereby obtaining a deformed grid map. In the curve area, the grid is deformed according to the curvature and width of the curve. The deformed grid can better fit the curve contour and improve the accuracy of path planning. The size and shape of the deformed grid can be dynamically adjusted as needed, and the connection relationship between the deformed grids is ensured so that a smooth transition can be achieved during the path search process. The grid parameters in the heuristic function are adjusted based on the grid deformation state to determine the path search algorithm, that is, the A* algorithm can be used for path search, and a heuristic function is defined to improve the A* algorithm, so as to determine the shortest path length from the current grid to the target grid, wherein the heuristic function can include Manhattan distance, Euclidean distance, etc., so as to obtain the path search algorithm. In the deformed grid map, the heuristic function is appropriately adjusted according to the deformation of the grid to more accurately reflect the actual path length, and subsequent processing is performed based on the deformed grid map and the path search algorithm.

[0067] In a feasible implementation, step S10 may include steps A11 to A14:

[0068] Step A11, obtaining environmental data, curve characteristics, grid deformation state and heuristic function;

[0069] It should be noted that the environmental data reflects the characteristics of the surrounding environment collected by the sensor, the curve characteristics reflect the characteristics of the curvature or width of the curve, the grid deformation state reflects the characteristics of the grid map fitting the road contour state, and the heuristic function reflects the characteristics of the desired shortest path length from the current grid to the target grid.

[0070] It is understandable that through accurate environmental data perception and curve characteristics analysis, combined with dynamic adjustment of the grid deformation state, a deformed grid map that better fits the actual road contour can be constructed, thereby improving the accuracy of path planning. The optimized heuristic function can reduce the search space of the path search algorithm, speed up the search speed, and significantly improve the efficiency of path planning.

[0071] Step A12, performing a preprocessing operation on the environmental data to determine preprocessed environmental data, wherein the preprocessing operation includes filtering, denoising and coordinate conversion;

[0072] It should be noted that the pre-processed environmental data reflects the characteristics of eliminating noise and errors in the environmental data collected by the sensor and converting it into data suitable for path planning.

[0073] It can be understood that through the preprocessing operations of filtering, denoising and coordinate transformation, the accuracy of environmental data can be significantly improved, the impact of sensor errors on path planning can be reduced, ensuring that the data received by the path planning algorithm is reliable and consistent, and adapting environmental data to different path planning algorithms and coordinate systems, thereby enhancing the adaptability of the path planning system to different environments.

[0074] Step A13, constructing a deformed grid map based on the preprocessed environmental data and the curve characteristics;

[0075] It can be understood that adjusting the deformed grid based on the preprocessed environmental data to construct a deformed grid map can more accurately fit the actual road contour, provide more detailed and accurate environmental information for path planning, adapt to complex and changeable curved environments, and improve the adaptability and accuracy of path planning.

[0076] Step A14: adjusting grid parameters in the heuristic function based on the grid deformation state to determine a path search algorithm, wherein the heuristic function includes Manhattan distance and Euclidean distance.

[0077] It can be understood that by adjusting the grid parameters in the heuristic function, the path search algorithm can adapt to the complex and changeable curve environment, improve the adaptability of the algorithm, and more accurately estimate the path length from the current grid to the target grid, thereby improving the accuracy of path planning and significantly improving the user experience.

[0078] Step S20, performing path planning on the deformed grid map based on the path search algorithm to find the target grid and determine the driving path, wherein the path planning includes path search, collision detection and path reconstruction;

[0079] It should be noted that the driving path reflects the characteristics of the driving path from the starting point to the target point found and determined by using a path search algorithm.

[0080] It can be understood that the application of the path search algorithm, combined with the characteristics of the deformed grid map, can more accurately identify a driving path that meets the actual road conditions, while optimizing the path search process and improving planning efficiency.

[0081] For ease of understanding, the driving path determination is taken as an example for explanation, wherein the information collection device is an information collection module, the storage device is a memory, and the processing device is a processing module.

[0082] The information acquisition module obtains the starting grid and the target grid, that is, extracts the starting grid and the target grid from the constructed deformed grid map, performs path search on the deformed grid map based on the path search algorithm, the starting grid and the target grid, determines the current grid, that is, starts from the starting grid, sequentially expands the adjacent grids to perform path search, and the grid reached during the search is the current grid, calculates the grid cost value and grid heuristic value of each grid, the grid cost value is the actual path length from the starting grid to the current grid, and the grid heuristic value is the heuristic estimated length from the current grid to the target grid, and selects the grid. The grid with the smallest cost value is expanded, and the obstacle grid is marked based on the current grid for collision detection to determine the expanded grid. That is, when the grid is expanded, collision detection is performed to determine whether there is an obstacle in the current grid. If there is an obstacle, the grid is marked as impassable and the grid is avoided in the path search process. Otherwise, the grid is continued to be expanded, and the path is reconstructed based on the expanded grid and the starting grid to obtain the driving path. That is, when the target grid is searched, it is traced back from the target grid to the starting grid to reconstruct the complete path to obtain the driving path, and subsequent processing is performed based on the driving path.

[0083] Step S30, smoothing the driving path to determine an optimized driving path, and controlling the vehicle to drive based on the optimized driving path to complete path planning.

[0084] It should be noted that the optimized driving path reflects the characteristics of smoothing the driving path to eliminate potential interference items and obtain a more natural and smooth path.

[0085] It is understandable that smoothing can be performed to eliminate sharp turns and unnecessary broken lines in the path, and smoothing algorithms such as spline curves can be used to optimize the path to make the path more natural and smooth. The vehicle's driving performance and safety requirements need to be considered when smoothing to ensure that the smoothed path still meets the vehicle's driving conditions, thereby significantly improving the vehicle's comfort.

[0086] For ease of understanding, an example of determining an optimized driving path is used for explanation, wherein the information collection device is an information collection module, the storage device is a memory, and the execution device is an execution module.

[0087] The information acquisition module obtains smoothing algorithms, such as spline curves and Kalman filters, and obtains vehicle driving conditions, such as limiting continuous turns. Based on the smoothing algorithm and the vehicle driving conditions, the driving path is smoothed to reduce potential interference items, and an optimized driving path is obtained, that is, smoothing is performed to eliminate sharp turns and unnecessary broken lines in the path, and smoothing algorithms such as spline curves are used to optimize the path to make the path more natural and smooth. When performing smoothing, the vehicle's driving performance and safety requirements need to be considered to ensure that the smoothed path still meets the vehicle's driving conditions, thereby controlling the vehicle's driving to complete the path planning.

[0088] In a feasible implementation, step S30 may include steps B11 to B13:

[0089] Step B11, obtaining a smoothing algorithm and a vehicle driving condition, wherein the smoothing algorithm includes a spline curve;

[0090] It should be noted that the smoothing algorithm reflects the characteristics of smoothing the driving path to create a smooth and continuous curve, and the vehicle driving condition reflects the characteristics of the actual driving performance and safety requirements of the vehicle restricted in path planning.

[0091] It can be understood that by smoothing the driving path through the smoothing algorithm, sharp turns and unnecessary zigzags in the path are reduced, the risk of vehicle accidents is reduced, and the smooth path reduces vehicle bumps and sudden braking, providing a more comfortable riding experience. At the same time, combined with the actual driving conditions of the vehicle, the path planning results are highly adaptable and can be applied to different vehicles and changing road environments.

[0092] Step B12: Smoothing the driving path based on the smoothing algorithm and the vehicle driving conditions to reduce potential interference items and obtain an optimized driving path.

[0093] It can be understood that by reducing potential interference items in the path, an optimized driving path is obtained, such as reducing sharp turns and mutations, which reduces the risk of vehicle accidents and improves driving safety. The smoothed path reduces vehicle bumps and swaying, providing a more comfortable ride experience. At the same time, it is more in line with actual driving requirements, reduces driving errors caused by inaccurate path planning, and improves the accuracy and reliability of path planning.

[0094] This embodiment proposes a method for planning a path for a curve position based on a deformed grid map, which obtains a deformed grid map and a path search algorithm; based on the path search algorithm, the deformed grid map is used for path planning to find a target grid and determine a driving path, wherein the path planning includes path search, collision detection and path reconstruction; the driving path is smoothed to determine an optimized driving path, and the vehicle is controlled to complete the path planning based on the optimized driving path. The technical problem of how to plan a driving path more efficiently and safely is solved. Compared with the prior art, the present application obtains a deformed grid map and a path search algorithm, uses path search, collision detection and path reconstruction to perform efficient path planning on the deformed grid map, and performs smoothing to determine an optimized driving path, thereby improving the safety of path planning, enhancing obstacle avoidance capabilities, and improving the comfort of vehicle driving.

[0095] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction and will not be repeated later.

[0096] In this embodiment, refer to Figure 3 , Figure 3 This is a flow chart of Embodiment 2 of the method for planning a path for a curve position based on a deformed grid map provided by the present application. Step S20 specifically includes steps S21 to S24:

[0097] Step S21, obtaining a starting grid and a target grid;

[0098] It should be noted that the starting grid reflects the characteristics of the starting point of the path planning, and the target grid reflects the characteristics of the end point of the path planning.

[0099] It can be understood that the starting grid can represent the starting grid of the path search algorithm, and the target grid can represent the grid of the destination that the vehicle needs to reach during the path planning process, thereby providing direction and goals for path planning, ensuring that the path search can be carried out efficiently towards the predetermined goal, thereby planning a path that better meets actual needs.

[0100] For ease of understanding, an example of obtaining a starting grid and a target grid is used for explanation, wherein the information acquisition device is an information acquisition module, the storage device is a memory, and the processing device is a processing module.

[0101] The information acquisition module obtains environmental data, curve characteristics, grid deformation status and heuristic functions, that is, uses sensors such as laser radar and cameras to collect environmental data, including location information, shape information and size information of obstacles, and performs preprocessing operations on the environmental data to determine preprocessed environmental data, that is, preprocessing the collected data, including filtering, denoising, coordinate conversion and other operations to improve the accuracy and reliability of the data, and constructs a deformed grid map based on the preprocessed environmental data and the curve characteristics, that is, dividing the environment into multiple grid units, each grid represents a small area, and the size of the grid can be adjusted according to the actual environment and path planning requirements, so as to obtain a deformed grid map, extract the starting grid and the target grid from the constructed deformed grid map, and perform subsequent processing based on the starting grid and the target grid.

[0102] Step S22, performing a path search on the deformed grid map based on the path search algorithm, the starting grid and the target grid to determine a current grid;

[0103] It should be noted that the current grid reflects the characteristics of the instant grid position when the algorithm performs path search on the deformed grid map.

[0104] It is understandable that the current grid can represent the area that the search algorithm has explored, and based on this grid, the next path search is performed, and the appropriate grid is selected for expansion, dynamically adapting to environmental changes, and responding to the appearance of obstacles or changes in the path in a timely manner.

[0105] For ease of understanding, the following description is given by taking determining the current grid as an example, wherein the information collection device is an information collection module, the storage device is a memory, and the processing device is a processing module.

[0106] The information acquisition module obtains a path search algorithm, such as an A* algorithm, obtains a starting grid, obtains a target grid, uses the A* algorithm to perform path search, and defines a heuristic function to estimate the shortest path length from the current grid to the target grid. The heuristic function includes Manhattan distance, Euclidean distance, etc. In a deformed grid map, the heuristic function is appropriately adjusted according to the deformation of the grid to more accurately reflect the actual path length. Based on the path search algorithm, the starting grid and the target grid, the adjacent grids are expanded to determine the adjacent grid set, that is, starting from the starting grid, the adjacent grids are sequentially expanded, and the expanded adjacent grids are combined into an adjacent grid set. Based on the adjacent grid set, a grid cost value set and a grid heuristic value set are calculated, that is, a grid cost value g and a grid heuristic value set h of each grid in the adjacent grid set are calculated, and the calculated grid cost values ​​and grid heuristic values ​​of multiple grids are combined into a grid cost value set and a grid heuristic value set. Based on the grid cost value set and the grid heuristic value set, the necessary cost grid is selected to be expanded to obtain the current grid, that is, the cumulative value f of a single grid is calculated as:

[0107] f=g+h

[0108] Among them, the g value represents the actual path length from the starting grid to the current grid, that is, the grid cost value g, and the h value represents the heuristic estimated length from the current grid to the target grid, that is, the grid heuristic value set h.

[0109] The grid with the smallest cost is selected for expansion to obtain the position of the current grid, until the expansion reaches the target grid or ends when it cannot be expanded further.

[0110] In a feasible implementation, step S22 may include steps C11 to C13:

[0111] Step C11, expanding adjacent grids based on the path search algorithm, the starting grid and the target grid to determine an adjacent grid set;

[0112] It should be noted that the adjacent grid set reflects the characteristics of the expandable grid set around the current grid.

[0113] It can be understood that the adjacent grid set includes all grids around the current grid, so that the expansion grid can be quickly evaluated and selected without blindly searching the entire map, which improves the search efficiency and provides multiple expansion directions. The most promising path is expanded according to the cost value of the grid, which optimizes the allocation of computing resources, enhances the feasibility and diversity of path planning, and significantly improves the quality of the final planned path.

[0114] Step C12, calculating a grid cost value set and a grid heuristic value set based on the adjacent grid set;

[0115] It should be noted that the grid cost value set reflects the characteristics of the cost value set composed of the actual path length of each grid from the starting grid to the current grid, and the grid heuristic value set reflects the characteristics of the heuristic value set composed of the estimated distance of each grid from the current grid to the target grid.

[0116] Step C13: Selecting and extending a necessary cost grid based on the grid cost value set and the grid heuristic value set to obtain a current grid.

[0117] It can be understood that the grid cost value set can represent the cost of passing through the grid, and the grid heuristic value set can represent the evaluation of the expected cost of reaching the target, so as to more comprehensively evaluate the total cost of each path segment, select the path with the lowest cost, optimize the final path planning, and reduce unnecessary searches. Combined with the cost value set, it can accelerate the finding of the optimal or approximately optimal path and improve the search efficiency.

[0118] Step S23, performing collision detection based on the current grid to mark the obstacle grid and determine the extended grid;

[0119] It should be noted that the extended grid reflects the feature that no obstacle is detected in the grid that is extended to during the path search, and the grid is successfully extended.

[0120] For ease of understanding, an explanation is given by taking determination of an extended grid as an example, wherein the information collection device is an information collection module, the storage device is a memory, and the processing device is a processing module.

[0121] The information acquisition module obtains the obstacle grid, detects the obstacle existence status based on the current grid and the obstacle grid, determines the grid mark, avoids the obstacle grid based on the grid mark, and obtains the extended grid, that is, determines whether there is an obstacle in the current grid. If there is an obstacle, the grid is marked as impassable and the grid is avoided during the path search process. Otherwise, the grid is marked as allowed to pass, the grid is extended for path planning, and the extended grid is obtained. Subsequent processing is performed based on the extended grid.

[0122] In a feasible implementation, step S23 may include steps D11 to D13:

[0123] Step D11, obtaining an obstacle grid;

[0124] It should be noted that the obstacle grid reflects the characteristics of the occupied grid unit positions in the grid map.

[0125] It can be understood that the obstacle grid clarifies the specific location and range of obstacles, so that the path planning algorithm can effectively avoid obstacles, reduce collision risks, improve the safety of path planning, and quickly identify inaccessible areas, reduce search space, and thus optimize path search efficiency.

[0126] Step D12, detecting the obstacle presence status based on the current grid and the obstacle grid, and determining a grid mark;

[0127] It should be noted that the grid mark reflects the characteristics of the obstacle existence status.

[0128] It can be understood that it is determined whether there is an obstacle in the current grid. If there is an obstacle, the grid is marked as impassable, otherwise, the grid is marked as allowed to pass.

[0129] Step D13, obtaining an extended grid based on the grid marking obstacle avoidance grid.

[0130] It is understandable that when the grid is expanded, collision detection is performed to determine whether there are obstacles in the current grid. If there are obstacles, the grid is marked as impassable and avoided during the path search process. Otherwise, the grid is expanded for path planning.

[0131] Step S24: reconstructing a path based on the extended grid and the starting grid to obtain a driving path.

[0132] It should be noted that the driving path reflects the characteristics of the path actually reconstructed after avoiding obstacles.

[0133] It can be understood that by avoiding obstacles marked by obstacle grids, the risk of collision can be reduced, driving safety can be improved, and real-time traffic data and road conditions can be taken into consideration to provide vehicles with safer paths, reduce driving time, and improve overall traffic efficiency. At the same time, dynamic adjustments can be made so that vehicles can respond to changes in traffic conditions in a timely manner, avoid congested sections, choose a better driving path, reduce sharp turns and bumps, and significantly improve driving comfort and passenger riding experience.

[0134] For ease of understanding, the driving path is obtained as an example for explanation, wherein the information collection device is an information collection module, the storage device is a memory, and the processing device is a processing module.

[0135] The information acquisition module obtains the extended grid and the starting grid, takes the extended grid as the target grid, determines the backtracking starting point, determines the backtracking target point based on the starting grid, backtracks the target search path based on the backtracking starting point and the backtracking target point, and reconstructs the driving path. That is, when the target grid is searched, it backtracks from the target grid to the starting grid, reconstructs the complete path, and controls the vehicle to complete the path planning.

[0136] In a feasible implementation, step S24 may include steps E11 to E13:

[0137] Step E11, taking the extended grid as the target grid and determining the backtracking starting point;

[0138] It should be noted that the backtracking starting point reflects the characteristics of the starting position where the backtracking process starts when the target grid is reached or it is determined that the current path cannot reach the target grid.

[0139] Step E12, determining a backtracking target point based on the starting grid;

[0140] It should be noted that the backtracking target point reflects the characteristics of the end point of the backtracking process when the target grid is reached or it is determined that the current path cannot reach the target grid.

[0141] Step E13, reconstructing the driving path by retracing the target search path based on the retracing starting point and the retracing target point.

[0142] It can be understood that by clearly defining the backtracking starting point and the backtracking target point, the search algorithm can flexibly adjust the search strategy and replan the path when encountering obstacles or failing to reach the target grid, thereby enhancing the flexibility of the path search and accurately backtracking from the target grid to the starting grid to reconstruct the complete driving path, thereby improving the accuracy of path planning.

[0143] This embodiment proposes a method for planning a path for a curve position based on a deformed grid map, which obtains a starting grid and a target grid; performs a path search on the deformed grid map based on the path search algorithm, the starting grid and the target grid to determine the current grid; performs collision detection based on the current grid to mark the obstacle grid and determine the extended grid; performs path reconstruction based on the extended grid and the starting grid to obtain a driving path. The technical problem of how to plan a driving path more accurately and safely is solved. Compared with the prior art, the present application obtains the starting grid and the target grid, determines the current grid on the deformed grid map, performs collision detection to mark the obstacle grid to obtain the extended grid, and reconstructs the driving path based on the extended grid and the starting grid, thereby improving the accuracy and safety of path planning, while optimizing driving efficiency and vehicle safety.

[0144] For example, in order to help understand the implementation process of the curve position path planning method based on the deformed grid map obtained by combining this embodiment with the above-mentioned embodiment 1, please refer to Figure 4 , Figure 4 A brief flow chart of a curve location path planning method based on a deformed grid map is provided, specifically:

[0145] Environmental perception and preprocessing: Use sensors to collect environmental data and perform preprocessing. Deformed grid map construction: Construct a deformed grid map based on the preprocessed environmental data and curve characteristics. A* path search: Apply the A* algorithm on the deformed grid map to search for paths, and perform collision detection and obstacle avoidance at the same time. Path smoothing: Smooth the searched path to obtain an optimized driving path. Path output and execution: Output the optimized path to the vehicle control system for execution. Referring to Real Number Example 1, a deformed grid map and a path search algorithm are obtained; based on the path search algorithm, path planning is performed on the deformed grid map to find the target grid and determine the driving path, wherein the path planning includes path search, collision detection, and path reconstruction; the driving path is smoothed to determine the optimized driving path, and the vehicle is controlled to complete the path planning based on the optimized driving path. Referring to Example 2, a starting grid and a target grid are obtained; a path search is performed on the deformed grid map based on the path search algorithm, the starting grid and the target grid to determine a current grid; a collision detection obstacle grid is marked based on the current grid to determine an extended grid; a path is reconstructed based on the extended grid and the starting grid to obtain a driving path.

[0146] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the curve position path planning method based on deformed grid maps of the present application. More forms of simple transformations based on this technical concept are all within the scope of protection of the present application.

[0147] This application also provides a curve position path planning device based on a deformed grid map, please refer to Figure 5 , the curve position path planning device based on the deformed grid map includes:

[0148] An acquisition module 10 is used to acquire a deformed grid map and a path search algorithm;

[0149] A processing module 20, configured to perform path planning on the deformed grid map based on the path search algorithm to find a target grid and determine a driving path, wherein the path planning includes path search, collision detection and path reconstruction;

[0150] The execution module 30 is used to perform smoothing processing on the driving path to determine an optimized driving path, and control the vehicle driving based on the optimized driving path to complete the path planning.

[0151] The acquisition module 10 is also used to acquire environmental data, curve characteristics, grid deformation status and heuristic functions;

[0152] Performing a preprocessing operation on the environmental data to determine preprocessed environmental data, wherein the preprocessing operation includes filtering, denoising and coordinate conversion;

[0153] Constructing a deformation grid map based on the preprocessed environmental data and the curve characteristics;

[0154] A path search algorithm is determined by adjusting grid parameters in the heuristic function based on the grid deformation state, wherein the heuristic function includes Manhattan distance and Euclidean distance.

[0155] The processing module 20 is further used to obtain a starting grid and a target grid;

[0156] Performing a path search on the deformed grid map based on the path search algorithm, the starting grid and the target grid to determine a current grid;

[0157] Perform collision detection based on the current grid to mark the obstacle grid and determine the extended grid;

[0158] The path is reconstructed based on the extended grid and the starting grid to obtain a driving path.

[0159] The processing module 20 is further configured to expand adjacent grids based on the path search algorithm, the starting grid and the target grid to determine an adjacent grid set;

[0160] Calculate a grid cost value set and a grid heuristic value set based on the adjacent grid set;

[0161] An extended necessary cost grid is selected based on the grid cost value set and the grid heuristic value set to obtain a current grid.

[0162] The processing module 20 is also used to obtain an obstacle grid;

[0163] Detecting obstacle existence status based on the current grid and the obstacle grid, and determining a grid mark;

[0164] The obstacle avoidance grid is marked based on the grid to obtain an extended grid.

[0165] The processing module 20 is further used to use the extended grid as a target grid to determine a backtracking starting point;

[0166] Determine a backtracking target point based on the starting grid;

[0167] The target search path is traced back based on the backtracking starting point and the backtracking target point to reconstruct the driving path.

[0168] The execution module 30 is further used to obtain a smoothing algorithm and a vehicle driving condition, wherein the smoothing algorithm includes a spline curve;

[0169] The driving path is smoothed based on the smoothing algorithm and the vehicle driving conditions to reduce potential interference items and obtain an optimized driving path.

[0170] The curve position path planning device based on deformed grid map provided by the present application adopts the curve position path planning method based on deformed grid map in the above embodiment, which can solve the technical problem of how to plan a driving path more efficiently, accurately and safely. Compared with the prior art, the beneficial effects of the curve position path planning device based on deformed grid map provided by the present application are the same as the beneficial effects of the curve position path planning method based on deformed grid map provided by the above embodiment, and the other technical features of the curve position path planning device based on deformed grid map are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0171] The present application provides a curve position path planning device based on a deformed grid map, and the curve position path planning device based on a deformed grid map includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the curve position path planning method based on the deformed grid map in the above-mentioned embodiment one.

[0172] Reference below Figure 6 , which shows a schematic diagram of the structure of a curve position path planning device based on a deformed grid map suitable for implementing the embodiment of the present application. The curve position path planning device based on a deformed grid map in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The curve position path planning device based on the deformed grid map shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0173] like Figure 6As shown, the curve position path planning device based on the deformed grid map may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 to the random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the curve position path planning device based on the deformed grid map are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the curve position path planning device based on the deformed grid map to communicate wirelessly or wired with other devices to exchange data. Although the curve position path planning device based on the deformed grid map with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0174] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0175] The curve position path planning device based on deformed grid map provided by the present application adopts the curve position path planning method based on deformed grid map in the above embodiment, which can solve the technical problem of how to plan a driving path more efficiently, accurately and safely. Compared with the prior art, the beneficial effects of the curve position path planning device based on deformed grid map provided by the present application are the same as the beneficial effects of the curve position path planning method based on deformed grid map provided by the above embodiment, and the other technical features of the curve position path planning device based on deformed grid map are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0176] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0177] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0178] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the curve position path planning method based on a deformed grid map in the above-mentioned embodiment.

[0179] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0180] The computer-readable storage medium may be included in the curve position path planning device based on the deformed grid map; or may exist independently without being assembled into the curve position path planning device based on the deformed grid map.

[0181] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by a curve position path planning device based on a deformed grid map, the curve position path planning device based on a deformed grid map: obtains a deformed grid map and a path search algorithm; performs path planning on the deformed grid map based on the path search algorithm to find a target grid and determine a driving path, wherein the path planning includes path search, collision detection and path reconstruction; smoothes the driving path to determine an optimized driving path, and controls the vehicle to complete the path planning based on the optimized driving path.

[0182] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0183] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0184] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0185] The readable storage medium provided by the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned method for planning the path of a curve position based on a deformed grid map, and can solve the technical problem of how to plan a driving path more efficiently, accurately, and safely. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present application are the same as the beneficial effects of the method for planning the path of a curve position based on a deformed grid map provided by the above-mentioned embodiment, and will not be described in detail here.

[0186] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for planning a curve position path based on a deformed grid map, characterized in that: The method includes: Get the deformed grid map and path search algorithm; Based on the path search algorithm, path planning is performed on the deformed grid map to find the target grid and determine the driving path, wherein the path planning includes path search, collision detection and path reconstruction; The driving path is smoothed to determine an optimized driving path, and the vehicle is controlled to complete path planning based on the optimized driving path.

2. The method according to claim 1, characterized in that The steps of obtaining a deformed grid map and a path search algorithm include: Obtain environmental data, curve characteristics, grid deformation status and heuristic functions; Performing a preprocessing operation on the environmental data to determine preprocessed environmental data, wherein the preprocessing operation includes filtering, denoising and coordinate conversion; Constructing a deformation grid map based on the preprocessed environmental data and the curve characteristics; A path search algorithm is determined by adjusting grid parameters in the heuristic function based on the grid deformation state, wherein the heuristic function includes Manhattan distance and Euclidean distance.

3. The method according to claim 1, characterized in that The step of performing path planning on the deformed grid map based on the path search algorithm to find the target grid and determine the driving path comprises: Get the starting grid and the target grid; Performing a path search on the deformed grid map based on the path search algorithm, the starting grid and the target grid to determine a current grid; Perform collision detection based on the current grid to mark the obstacle grid and determine the extended grid; The path is reconstructed based on the extended grid and the starting grid to obtain a driving path.

4. The method according to claim 3, characterized in that The step of performing path search on the deformed grid map based on the path search algorithm, the starting grid and the target grid to determine the current grid comprises: Expand adjacent grids based on the path search algorithm, the starting grid, and the target grid to determine an adjacent grid set; Calculate a grid cost value set and a grid heuristic value set based on the adjacent grid set; An extended necessary cost grid is selected based on the grid cost value set and the grid heuristic value set to obtain a current grid.

5. The method according to claim 3, characterized in that The step of performing collision detection based on the current grid to mark the obstacle grid and determining the extended grid comprises: Get the obstacle grid; Detecting obstacle existence status based on the current grid and the obstacle grid, and determining a grid mark; The obstacle avoidance grid is marked based on the grid to obtain an extended grid.

6. The method according to claim 3, characterized in that The step of reconstructing the path based on the extended grid and the starting grid to obtain the driving path comprises: Taking the extended grid as the target grid, determining the backtracking starting point; Determine a backtracking target point based on the starting grid; The target search path is traced back based on the backtracking starting point and the backtracking target point to reconstruct the driving path.

7. The method according to claim 1, characterized in that The step of smoothing the driving path to determine the driving optimization path comprises: Acquire a smoothing algorithm and a vehicle driving condition, wherein the smoothing algorithm includes a spline curve; The driving path is smoothed based on the smoothing algorithm and the vehicle driving conditions to reduce potential interference items and obtain an optimized driving path.

8. A curve position path planning device based on a deformable grid map, characterized in that: The device comprises: An acquisition module, used to obtain a deformed grid map and a path search algorithm; A processing module, used for performing path planning on the deformed grid map based on the path search algorithm to find the target grid and determine the driving path, wherein the path planning includes path search, collision detection and path reconstruction; The execution module is used to smooth the driving path to determine the driving optimization path, and control the vehicle driving based on the driving optimization path to complete the path planning.

9. A curve position path planning device based on a deformable grid map, characterized in that: The device comprises: a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the curve position path planning method based on a deformed grid map as described in any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the curve position path planning method based on a deformed grid map as described in any one of claims 1 to 7 are implemented.

Images