Route planning method and device based on grid map, equipment and medium

Abstract

The invention discloses a path planning method and device based on a raster map, equipment and a medium, and the method comprises the steps: obtaining scanning data corresponding to a target region, and determining the raster map of the target region according to the scanning data; generating a navigation path point set corresponding to the target area according to a path planning algorithm and the grid map; acquiring a path control parameter corresponding to the target object, and determining a control point set from the navigation path point set according to the path control parameter; and performing path smoothing processing based on the control point set to determine a target navigation path corresponding to the target area. Based on the technical scheme, the navigation path points are determined from the grid map and the navigation path points are screened to obtain the control points, and the navigation path is determined according to the control points, so that the accuracy of the path near the obstacle is ensured, the calculation amount and the path complexity of the area far away from the obstacle are reduced, and the navigation efficiency is improved. And the path planning efficiency and quality are improved.

Description

Technical Field

[0001] This invention relates to the field of path planning technology, and in particular to a path planning method, apparatus, device and medium based on a grid map. Background Technology

[0002] With the continuous development of autonomous driving technology, in order to ensure the accuracy of navigation during autonomous driving or navigation, navigation paths are planned based on the collected scanning data.

[0003] However, existing path planning methods do not handle obstacles precisely enough, and do not fully consider the robot's own size and the potential risk areas around the obstacles. This results in the planned path being too close to the obstacles, posing a collision risk. Furthermore, the generated path has defects in smoothness and curvature control, and may have a curvature radius that is too small, failing to meet the robot's kinematic constraints and making the path difficult to execute. Summary of the Invention

[0004] This invention provides a path planning method, apparatus, device, and medium based on a grid map. By determining navigation path points from the grid map and filtering them to obtain control points, and then determining the navigation path based on the control points, the accuracy of the path near obstacles is ensured, while reducing the amount of calculation and path complexity in areas far from obstacles, thereby improving the efficiency and quality of path planning.

[0005] According to one aspect of the present invention, a path planning method based on a grid map is provided, comprising:

[0006] Acquire scan data corresponding to the target area, and determine a raster map of the target area based on the scan data;

[0007] A navigation path point set corresponding to the target area is generated based on the path planning algorithm and the grid map;

[0008] Obtain the path control parameters corresponding to the target object, and determine the control point set from the navigation path point set based on the path control parameters;

[0009] Based on the control point set, path smoothing processing is performed to determine the target navigation path corresponding to the target area.

[0010] According to another aspect of the present invention, a path planning device based on a grid map is provided, comprising:

[0011] The raster map determination module is used to acquire scan data corresponding to the target area and determine the raster map corresponding to the target area based on the scan data;

[0012] The waypoint determination module is used to generate a set of navigation waypoints corresponding to the target area based on the path planning algorithm and the grid map;

[0013] The control point selection module is used to obtain path control parameters corresponding to the target object, and determine a set of control points from the navigation path point set based on the path control parameters;

[0014] The navigation path determination module is used to determine the target navigation path corresponding to the target area based on the control point set through path smoothing processing.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] At least one processor; and

[0017] A memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the grid map-based path planning method according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the grid map-based path planning method according to any embodiment of the present invention.

[0020] The technical solution of this invention involves acquiring scan data corresponding to a target area and determining a grid map of the target area based on the scan data; generating a navigation path point set corresponding to the target area based on a path planning algorithm and the grid map; acquiring path control parameters corresponding to the target object and determining a control point set from the navigation path point set based on the path control parameters; and performing path smoothing processing based on the control point set to determine a target navigation path corresponding to the target area. Based on this technical solution, by determining navigation path points from the grid map and filtering them to obtain control points, and then determining the navigation path based on the control points, the accuracy of the path near obstacles is ensured, while reducing the computational load and path complexity in areas far from obstacles, thus improving the efficiency and quality of path planning.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart of a path planning method based on a grid map provided in an embodiment of the present invention;

[0024] Figure 2 This is a flowchart of a path planning method based on a grid map provided in an embodiment of the present invention;

[0025] Figure 3 This is a schematic diagram of a grid map provided in an embodiment of the present invention;

[0026] Figure 4 This is a schematic diagram of the original path generated based on a raster map according to an embodiment of the present invention;

[0027] Figure 5 This is a schematic diagram of control points selected based on the original path, provided in an embodiment of the present invention;

[0028] Figure 6 This is a schematic diagram of the target navigation path generated after path smoothing based on control points, provided in an embodiment of the present invention.

[0029] Figure 7 A schematic diagram of a path planning device based on a grid map provided in an embodiment of the present invention;

[0030] Figure 8 This is a schematic diagram of the structure of the electronic device provided in an embodiment of the present invention. Detailed Implementation

[0031] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0033] Figure 1 This is a flowchart illustrating a path planning method based on a grid map, provided in an embodiment of the present invention. This embodiment is applicable to situations where navigation paths are automatically generated during robot automatic pathfinding. The method can be executed by a grid map-based path planning device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method specifically includes the following steps:

[0034] S110. Obtain scan data corresponding to the target area, and determine a raster map of the target area based on the scan data.

[0035] The target area can be the region where path planning is required. For example, in the case of a robot being navigated, it can be understood as the area the robot needs to traverse. Scanning data can be sensor data corresponding to the target area collected by scanning equipment. For instance, a LiDAR scanner can scan the target area to obtain corresponding 3D point cloud data. A grid map can be a map representation obtained by discretizing a continuous space into regular grid cells. It should be noted that a grid map can store information such as obstacle states, terrain height, and cost weights.

[0036] Specifically, the process involves acquiring scan data corresponding to the target area and determining a grid map of the target area based on this scan data. For example, sensors such as LiDAR, depth cameras, or multi-line scanners can be used to scan the target area, acquiring its 3D point cloud data or 2D contour information. Point cloud processing algorithms are then used to preprocess the raw scan data, eliminating noise interference and improving data quality. Based on the processed data, the target area is divided into several equally spaced grid units, and the spatial coordinates of each point in the scan data are mapped to the corresponding grid. Simultaneously, information such as terrain height and obstacle distribution within the grid is recorded. Finally, a grid map is generated.

[0037] S120. Generate a set of navigation path points corresponding to the target area based on the path planning algorithm and the grid map.

[0038] The path planning algorithm can be a routing algorithm used for path planning, such as Dijkstra's algorithm or A* algorithm. The navigation path point set can be understood as the set of navigation path points selected by the path planning algorithm.

[0039] Specifically, a navigation path point set corresponding to the target area is generated based on the path planning algorithm and the grid map. For example, based on the grid map, each grid cell is labeled with attributes, indicating the accessibility of each cell, such as free space, obstacles, and semi-accessible areas, as well as the corresponding cost weight, forming a weighted topology. After labeling, a path planning algorithm such as A*, Dijkstra, or RRT is used, with the start and end points as input, to search for the optimal or suboptimal path in the grid map. The algorithm dynamically evaluates the cost function of adjacent cells, gradually expanding the path tree until the target point is reached, thus forming a navigation path point set. For example, by setting the start and end points, the cost array of the nodes (initial value set to positive infinity), the parent node array, etc., are initialized. At the same time, open and closed sets used for searching are initialized. The open set stores the mapping between the index value and cost value of the node to be searched, and the closed set stores the mapping between the index value and potential field value of each cell in the grid map. Define the cost function: Considering the impact of obstacles on the path, design a cost function such that the cost value of a grid cell farther away from an obstacle is lower, and the cost value of a grid cell closer to an obstacle is higher.

[0040] S130. Obtain the path control parameters corresponding to the target object, and determine the control point set from the navigation path point set according to the path control parameters.

[0041] The target object can be an object requiring automatic pathfinding, such as a vehicle or robot with autonomous driving capabilities. Path control parameters are parameters used to filter path points, and may include a safety radius and a preset cost threshold. It should be noted that the safety radius is associated with the target object and can be 1.2 times the radius of the target object.

[0042] Specifically, the method involves acquiring path control parameters corresponding to the target object, and determining a control point set from the navigation path point set based on these parameters. For example, based on the kinematic model of the target object, such as the joint parameters and dynamic constraints of a wheeled robot, drone, or robotic arm, including maximum speed, acceleration, and turning radius, path control parameters are extracted. These parameters include velocity planning curves, heading angle change rate, and curvature radius thresholds, ensuring that the parameters match the object's physical capabilities. Control points are then selected from the navigation path points based on the path control parameters corresponding to the target object to obtain the control point set. The technical solution of this application not only guarantees the accuracy and stability of path tracking but also adapts to the dynamic characteristics of different target objects, improving the system's robustness in complex environments.

[0043] Based on the above technical solution, the step of determining the control point set from the navigation path point set according to the path control parameters includes: extracting the path start point and the path end point from the navigation path point set, and determining the intermediate path point set from the navigation path point set based on the extracted path start point and the path end point; adding the path start point and the path end point to the control point set, and determining the control point set from the intermediate path point set according to the path control parameters.

[0044] Here, the path start point can be the starting point of the navigation path, and the corresponding path end point is the ending point of the navigation path. It should be noted that the path start point and path end point can be pre-set starting points. For example, when the robot needs to perform periodic work, the path start point and path end point can be pre-set for the robot. The intermediate path point set is the set of path points after removing the path start point and path end point from the navigation path point set.

[0045] Specifically, the starting and ending points are analyzed from the complete navigation path point set as the path start and end points. The path start and end points are forcibly included in the control point set as the basic framework. Then, for the intermediate path point set, a secondary screening is performed in combination with preset path control parameters (such as maximum curvature, speed fluctuation threshold, sampling frequency, etc.): by dynamically evaluating the curvature continuity, speed smoothness and safe distance from obstacles of each point, points that meet the constraints are preferentially retained as candidate control points, and interpolation is performed to complete them according to the control cycle or motion accuracy requirements.

[0046] Based on the above technical solution, the final generated control point set not only includes critical path nodes, but also conforms to the kinematic characteristics of the target object, effectively improving the stability and adaptability of path tracking.

[0047] Based on the above technical solution, the step of determining the control point set from the intermediate path point set according to the path control parameters includes: obtaining the three-dimensional world coordinates of each intermediate path point in the intermediate path point set, and converting the three-dimensional world coordinates into raster map coordinates; determining a second intermediate path point set from the intermediate path point set based on the raster map coordinates and the raster map, and determining the control point set according to the second intermediate path point set and the path control parameters.

[0048] Here, 3D world coordinates can be coordinates of points in the world coordinate system corresponding to intermediate path points. Raster map coordinates can be coordinate representations corresponding to a raster map. The second intermediate path point set can be the set of path points obtained by filtering the intermediate path point set. Path control parameters include the safety radius and the number of sampling intervals.

[0049] Specifically, the 3D world coordinates of each intermediate path point in the intermediate path point set are obtained and converted into raster map coordinates. A second intermediate path point set is determined from the intermediate path point set based on the raster map coordinates and the raster map. A control point set is then determined based on the second intermediate path point set and the path control parameters. For example, the 3D world coordinates (X, Y, Z) of each intermediate path point can be converted into raster map coordinates (i, j) by traversing the intermediate path point set and using sensor calibration parameters or the pose transformation matrix provided by the SLAM system. Here, i and j correspond to the row and column indices of the raster map, respectively. It should be noted that the conversion process needs to consider map origin offset and resolution scaling. For example, when the map resolution is 0.1m / raster, the world coordinates need to be divided by 0.1 and rounded down. After the coordinate conversion is completed, the second intermediate path point set is determined from the intermediate path point set based on the raster map coordinates and the raster map. Finally, the control point set is determined based on the second intermediate path point set and the path control parameters.

[0050] Based on the above technical solution, the step of determining the second intermediate path point set from the intermediate path point set based on the grid map coordinates and the grid map includes: adding the intermediate path point corresponding to the grid map coordinates to the control point set when the grid map coordinates do not match the grid map; and adding the intermediate path point corresponding to the grid map coordinates to the second intermediate path point set when the grid map coordinates are located within the grid map.

[0051] Specifically, if the raster map coordinates do not match the raster map, the intermediate path point corresponding to the raster map coordinates is added to the control point set; if the raster map coordinates are within the raster map, the intermediate path point corresponding to the raster map coordinates is added to the second intermediate path point set. For example, a coordinate consistency detection algorithm, such as boundary range verification or raster index validity verification, is used to determine whether the current raster map coordinates match the predefined map range: if the coordinates exceed the map boundary or correspond to an invalid raster, the intermediate path point associated with the coordinates is directly added to the control point set as a forced pass point to ensure path continuity; if the coordinates are within the valid map range, the corresponding path point is temporarily stored in the second intermediate path point set.

[0052] Based on the above technical solution, the step of determining the control point set according to the second intermediate path point set and the path control parameters includes: for each intermediate path point in the second intermediate path point set, establishing a safety scanning area corresponding to the intermediate path point according to the safety radius; obtaining the obstacle cost of each grid in the safety scanning area, and determining the control point set based on the obstacle cost and the number of sampling intervals.

[0053] The safe scanning area can be a circular region centered at the intermediate path point with a safe radius. The obstacle cost can be a cost set during the grid map creation process based on the relationship between the grid and the obstacles.

[0054] Specifically, for each intermediate path point in the second intermediate path point set, a safety scanning area corresponding to the intermediate path point is established according to the safety radius; the obstacle cost of each grid in the safety scanning area is obtained, and the control point set is determined based on the obstacle cost and the sampling interval number. For example, a circular or square safety scanning area is generated with each intermediate path point as the center and combined with a preset safety radius to ensure coverage of potential collision risk range. Then, the obstacle annotation information of the grid map is used to query the cost of each grid in the safety scanning area, and the control point set is determined according to the obstacle cost and the sampling interval number.

[0055] Based on the above technical solution, determining the control point set based on the obstacle cost and the number of sampling intervals includes: adding the intermediate path point to the control point set and initializing the sampling counter when the obstacle cost of any grid in the safe scanning area is greater than a preset cost threshold; and determining the control point set based on the sampling counter and the number of sampling intervals when the obstacle cost of all grids in the safe scanning area is less than the preset cost threshold.

[0056] The preset cost threshold can be a pre-set threshold used for judgment. The sampling counter can be a counter used to perform technical analysis on path points.

[0057] Specifically, a safe scanning area is constructed centered on each intermediate path point, and obstacle costs are calculated grid by grid. When the obstacle cost of any grid within the scanning area exceeds a preset threshold, such as 0.8, it represents a high-risk area, and the current path point is determined to have a potential collision risk. It is then directly added to the control point set as a forced obstacle avoidance node, and the sampling counter is initialized. If the cost of all grids within the scanning area is below the threshold, and the counter has not reached the required interval, the point is skipped; if the counter meets the interval requirement, the point is added to the control point set and the counter is reset.

[0058] Based on the above technical solution, both path safety and sampling efficiency can be taken into account, and an optimized control point set adapted to complex environments can be generated.

[0059] Based on the above technical solution, determining the control point set based on the sampling counter and the sampling interval number includes: adding the intermediate path point to the control point set and initializing the sampling counter when the sampling count of the sampling counter is equal to the sampling interval number; and accumulating the sampling counter and determining whether the next intermediate path point is a control point when the sampling count of the sampling counter is less than the sampling interval number.

[0060] Specifically, for each path point in the second set of intermediate path points, the current value of the sampling counter is checked. If the cumulative number of samples collected by the sampling counter is exactly equal to the preset sampling interval (e.g., sampling once every 5 path points), the counter will trigger when it reaches 5. In this case, the intermediate path point will be added to the control point set, and the sampling counter will be immediately reset to 0 to start a new sampling cycle. If the current value of the sampling counter is less than the sampling interval, no sampling operation will be performed on that point. The counter value will be incremented by 1, and the next intermediate path point will continue to be processed. At this time, it is necessary to simultaneously determine whether subsequent path points have been marked as mandatory control points due to safety risks (such as obstacle costs exceeding the threshold). If so, they will be preferentially added to the control point set, and the counter will be reset.

[0061] Based on the above technical solution, the sampling density can be precisely controlled while ensuring coverage of key points along the path, effectively balancing path tracking accuracy and system computational load.

[0062] S140. Based on the control point set, perform path smoothing processing to determine the target navigation path corresponding to the target area.

[0063] Among them, path smoothing can be done by processing control points according to a path smoothing algorithm.

[0064] Specifically, the path smoothing process based on the control point set determines the target navigation path corresponding to the target area. This can be achieved by initially fitting the discrete control point set using a cubic spline interpolation algorithm, constructing a piecewise cubic polynomial function to ensure the continuity of the first derivative (velocity) and second derivative (acceleration) of the path, and eliminating abrupt changes in the polygonal path. Curvature optimization constraints are introduced, and the path curvature distribution is analyzed based on the Frynet coordinate system. Local path segments with excessive curvature (e.g., exceeding the curvature corresponding to the robot's minimum turning radius) are adjusted secondaryly, replacing high-curvature areas with Bézier curves or spirals to ensure motion feasibility. Finally, considering the actual obstacle distribution in the target area, collision detection and fine-tuning are performed on the smoothed path using the Dynamic Window Method (DWA), iteratively optimizing the path point positions within a safe distance threshold. It should be noted that before path smoothing, the control points can be sorted by time according to their timestamps to ensure temporal continuity.

[0065] Based on the above technical solutions, target navigation paths that combine smoothness, dynamic feasibility, and safety can be generated, significantly improving the navigation efficiency and stability of mobile robots in complex environments.

[0066] The technical solution of this invention involves acquiring scan data corresponding to a target area and determining a grid map of the target area based on the scan data; generating a navigation path point set corresponding to the target area based on a path planning algorithm and the grid map; acquiring path control parameters corresponding to the target object and determining a control point set from the navigation path point set based on the path control parameters; and performing path smoothing processing based on the control point set to determine a target navigation path corresponding to the target area. Based on this technical solution, by determining navigation path points from the grid map and filtering them to obtain control points, and then determining the navigation path based on the control points, the accuracy of the path near obstacles is ensured, while reducing the computational load and path complexity in areas far from obstacles, thus improving the efficiency and quality of path planning.

[0067] In one possible implementation of the present invention Figure 2 A flowchart of a path planning method based on a grid map provided in an embodiment of the present invention is shown below. Figure 2 As shown, the path planning method based on a grid map in this embodiment further includes:

[0068] Raster map construction: Abstracting the real-world environment into a raster map, such as... Figure 3 As shown, each grid has specific attributes, including whether it is an obstacle and its distance from obstacles.

[0069] Determine the initial navigation path: Initialize Dijkstra's algorithm parameters, set the start and end points, and initialize the cost array of nodes (initialized to positive infinity), the parent node array, etc. Simultaneously, initialize the open and closed sets used for searching. The open set stores the mapping between the index value and cost value of the node to be searched, and the closed set stores the mapping between the index value and potential field value of each grid cell in the raster map. Considering the influence of obstacles on the path, design a cost function so that the cost value of grid cells farther from obstacles is lower, and the cost value of grid cells closer to obstacles is higher. This yields the initial path after pathfinding using Dijkstra's algorithm, such as... Figure 4 As shown.

[0070] Control point selection: Obtaining the original path: Receives the original path data `path` from the upper-level path planning module. This path is stored in the `nav_msgs::msg::Path` message format and contains a series of ordered `PoseStamped` points. Receives the raster map data `map`, which is stored in the `nav_msgs::msg::OccupancyGrid` message format. The map data contains obstacle information about the environment; the value of each raster cell represents the probability that the location is occupied by an obstacle.

[0071] By setting two key parameters: `obstacle_radius` (safety radius): Defines a circular region centered on a waypoint to determine whether that point is close to an obstacle. This radius is typically determined based on the robot's size, motion characteristics, and environmental safety margin. `occupancy_threshold`: Defines the occupancy probability threshold at which a cell in the grid map is considered an "obstacle." For example, a cell is considered an obstacle if its data value is greater than 50. `sampling_interval`: Defines how many original waypoints are reserved as control points in an open area without obstacles.

[0072] Create an empty list of control points, `control_points`, to store the final selected control points. Force the retention of the starting point: Add the first point of the original path, `path.poses[0]`, to the `control_points` collection as the initial control point. This ensures that the starting point of the smoothed path is consistent with the planned path. Also force the retention of the last point of the original path, `path.poses.back()`, to the `control_points` collection beforehand. This ensures that the ending point of the smoothed path is consistent with the planned path.

[0073] Initialize a counter `non_obstacle_count` to record the number of consecutive pathpoints without surrounding obstacles. Starting from the second point on the original path and ending at the second-to-last point, iterate through each intermediate pathpoint `current_pose`: Extract location information: Obtain the 3D coordinates (x, y, z) of the current pathpoint `current_pose` in the world coordinate system. Obstacle proximity detection: Call an auxiliary function (such as `has_obstacle_nearby`) to determine if there are obstacles around `current_pose`. The implementation logic of this auxiliary function is as follows: Coordinate transformation: Convert the world coordinates (x, y) of `current_pose` to its corresponding grid coordinates (grid_x, grid_y) in the grid map `map`. Boundary check: Check if (grid_x, grid_y) is within the valid range of the map. If it is outside the range, it can be considered a potential danger and determined as "obstacles nearby". Region scan: Scan a circular region centered at (grid_x, grid_y) with a radius equal to the number of grid cells corresponding to `obstacle_radius`. Obstacle detection: Within the scanned area, check the value of each grid cell. If the value of any grid cell is greater than or equal to `occupancy_threshold`, immediately determine that there is an obstacle near `current_pose`. Filter based on the detection results: Case A: Obstacle nearby: Add the current path point `current_pose` to the `control_points` set. This is because this point is in a complex environment and is a key feature point for ensuring path safety. Reset counter: Clear `non_obstacle_count` to zero. This means recalculating consecutive non-obstacle points starting from the current point. Case B: No obstacles nearby: Increment counter: Increment the value of `non_obstacle_count` by one. Interval sampling judgment: Check if the value of `non_obstacle_count` has reached the preset `sampling_interval`. If it has, add the current path point `current_pose` to the `control_points` set and clear `non_obstacle_count` to zero. If it has not, skip the current path point and do not add it to the `control_points` set.

[0074] After traversing all intermediate path points, the `control_points` set will contain all the intelligently selected control points. The `control_points` set will then be finalized to ensure that the order of its points matches the original path. The finalized `control_points` set will be output, as shown below. Figure 5 As shown.

[0075] Path smoothing: such as Figure 6 As shown, a global smooth path is generated based on the retained control points using a suitable smoothing algorithm.

[0076] The technical solution of this invention uses obstacles as constraints and sets a reasonable cost mechanism to enable the generated global path to effectively avoid obstacles, thereby improving path safety. Furthermore, the method of adjusting the control point density based on the cost of path points ensures the accuracy of the path near obstacles while reducing the computational load and path complexity in areas far from obstacles, thus improving the efficiency and quality of path planning. This results in a globally smooth path that better meets the needs of the moving subject in actual motion, reduces bumps and unnecessary turns during motion, and improves the stability and efficiency of motion. It has broad application prospects and can be applied to multiple fields such as robot navigation, autonomous driving, and logistics transportation.

[0077] Figure 7 This is a schematic diagram of a path planning device based on a grid map, provided as an embodiment of the present invention. Figure 7 As shown, the device includes: a grid map determination module 710, a waypoint determination module 720, a control point selection module 730, and a navigation path determination module 740.

[0078] The raster map determination module 710 is used to acquire scan data corresponding to the target area and determine a raster map of the target area based on the scan data.

[0079] The path point determination module 720 is used to generate a set of navigation path points corresponding to the target area based on the path planning algorithm and the grid map;

[0080] The control point selection module 730 is used to obtain path control parameters corresponding to the target object, and determine a set of control points from the navigation path point set according to the path control parameters;

[0081] The navigation path determination module 740 is used to determine the target navigation path corresponding to the target area based on the control point set through path smoothing processing.

[0082] In the above technical solution, the control point selection module is used to extract the path start point and path end point from the navigation path point set, and determine the intermediate path point set from the navigation path point set based on the extracted path start point and path end point; add the path start point and path end point to the control point set, and determine the control point set from the intermediate path point set according to the path control parameters.

[0083] In the above technical solution, the control point selection module is used to obtain the three-dimensional world coordinates of each intermediate path point in the intermediate path point set, and convert the three-dimensional world coordinates into raster map coordinates; determine a second intermediate path point set based on the raster map coordinates and the raster map, and determine a control point set according to the second intermediate path point set and the path control parameters, wherein the path control parameters include a safety radius and a sampling interval.

[0084] In the above technical solution, the control point selection module is used to add intermediate path points corresponding to the grid map coordinates to the control point set when the grid map coordinates do not match the grid map; and to add intermediate path points corresponding to the grid map coordinates to a second intermediate path point set when the grid map coordinates are located within the grid map.

[0085] In the technical aspect of the above solution, the control point selection module is used to establish a safety scanning area corresponding to each intermediate path point in the second intermediate path point set based on the safety radius; obtain the obstacle cost of each grid in the safety scanning area; and determine the control point set based on the obstacle cost and the number of sampling intervals.

[0086] In the above technical solution, the control point selection module is used to add the intermediate path point to the control point set and initialize the sampling counter when the obstacle cost of any grid in the safe scanning area is greater than a preset cost threshold; and to determine the control point set based on the sampling counter and the number of sampling intervals when the obstacle cost of all grids in the safe scanning area is less than the preset cost threshold.

[0087] In the technical aspect of the above solution, the control point selection module is used to add the intermediate path point to the control point set and initialize the sampling counter when the number of samples of the sampling counter is equal to the number of sampling intervals; and to accumulate the sampling counter and determine whether the next intermediate path point is a control point when the number of samples of the sampling counter is less than the number of sampling intervals.

[0088] The technical solution of this invention involves acquiring scan data corresponding to a target area and determining a grid map of the target area based on the scan data; generating a navigation path point set corresponding to the target area based on a path planning algorithm and the grid map; acquiring path control parameters corresponding to the target object and determining a control point set from the navigation path point set based on the path control parameters; and performing path smoothing processing based on the control point set to determine a target navigation path corresponding to the target area. Based on this technical solution, by determining navigation path points from the grid map and filtering them to obtain control points, and then determining the navigation path based on the control points, the accuracy of the path near obstacles is ensured, while reducing the computational load and path complexity in areas far from obstacles, thus improving the efficiency and quality of path planning.

[0089] The path planning device based on grid map provided in the embodiments of the present invention can execute the path planning method based on grid map provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0090] Figure 8 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0091] like Figure 8 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0092] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0093] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as path planning methods based on grid maps.

[0094] In some embodiments, the grid-map-based path planning method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the grid-map-based path planning method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the grid-map-based path planning method by any other suitable means (e.g., by means of firmware).

[0095] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0096] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0097] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0098] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0099] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0100] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0101] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0102] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A path planning method based on a grid map, characterized in that, include: Acquire scan data corresponding to the target area, and determine a raster map of the target area based on the scan data; A navigation path point set corresponding to the target area is generated based on the path planning algorithm and the grid map; Obtain the path control parameters corresponding to the target object, and determine the control point set from the navigation path point set based on the path control parameters; Based on the control point set, path smoothing processing is performed to determine the target navigation path corresponding to the target area.

2. The method according to claim 1, characterized in that, The step of determining the control point set from the navigation path point set based on the path control parameters includes: Extract the path start point and path end point from the navigation path point set, and determine the intermediate path point set from the navigation path point set based on the extracted path start point and path end point; The starting point and the ending point of the path are added to the control point set, and the control point set is determined from the intermediate path point set according to the path control parameters.

3. The method according to claim 2, characterized in that, The step of determining the control point set from the intermediate path point set based on path control parameters includes: Obtain the three-dimensional world coordinates of each intermediate path point in the intermediate path point set, and convert the three-dimensional world coordinates into raster map coordinates; Based on the grid map coordinates and the grid map, a second intermediate path point set is determined from the intermediate path point set, and a control point set is determined according to the second intermediate path point set and the path control parameters, wherein the path control parameters include the safety radius and the number of sampling intervals.

4. The method according to claim 3, characterized in that, The step of determining the second intermediate path point set from the intermediate path point set based on the grid map coordinates and the grid map includes: If the grid map coordinates do not match the grid map, the intermediate path points corresponding to the grid map coordinates are added to the control point set; If the grid map coordinates are located within the grid map, the intermediate path points corresponding to the grid map coordinates are added to the second intermediate path point set.

5. The method according to claim 3, characterized in that, The step of determining the control point set based on the second intermediate path point set and the path control parameters includes: For each intermediate path point in the second intermediate path point set, a security scanning area corresponding to the intermediate path point is established according to the security radius; Obtain the obstacle cost for each grid cell in the security scan area, and determine the control point set based on the obstacle cost and the number of sampling intervals.

6. The method according to claim 5, characterized in that, Determining the control point set based on the obstacle cost and the number of sampling intervals includes: If the obstacle cost of any grid in the security scanning area exceeds a preset cost threshold, the intermediate path point is added to the control point set, and the sampling counter is initialized. If the obstacle cost of all grids in the security scanning area is less than the preset cost threshold, the control point set is determined based on the sampling counter and the number of sampling intervals.

7. The method according to claim 6, characterized in that, Determining the control point set based on the sampling counter and the sampling interval number includes: If the number of samples of the sampling counter is equal to the number of sampling intervals, the intermediate path point is added to the control point set, and the sampling counter is initialized. If the number of samples collected by the sampling counter is less than the number of sampling intervals, the sampling counter is incremented, and it is determined whether the next intermediate path point is a control point.

8. A path planning device based on a grid map, characterized in that, include: The raster map determination module is used to acquire scan data corresponding to the target area and determine the raster map corresponding to the target area based on the scan data; The waypoint determination module is used to generate a set of navigation waypoints corresponding to the target area based on the path planning algorithm and the grid map; The control point selection module is used to obtain path control parameters corresponding to the target object, and determine a set of control points from the navigation path point set based on the path control parameters; The navigation path determination module is used to determine the target navigation path corresponding to the target area based on the control point set through path smoothing processing.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the path planning method based on a grid map as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the path planning method based on a grid map as described in any one of claims 1-7.

Images