Path planning method and device and storage medium

Abstract

The invention relates to the technical field of path planning, in particular to a path planning method and device and a storage medium. Comprising the following steps: constructing a first region and a second region; determining a first path cost of each first sampling point in the first area, and determining a first target node; determining a second path cost of each second sampling point in the second area, and determining a second target node; and under the condition that the first target node and the second target node are different, determining the first target node as a new first node, determining the second target node as a new second node, and returning to the step of constructing the first region according to the first node and the preset length and constructing the second region according to the second node and the preset length. The first target node and the second target node are the same; and according to all the first target nodes and the second target nodes, determining the running path of the automatic equipment moving from the current position to the target end point position, thereby improving the path planning efficiency and improving the path quality.

Description

Technical Field

[0001] This application relates to the field of path planning technology, specifically to a path planning method, apparatus, and storage medium. Background Technology

[0002] Open-pit mines have complex terrain, numerous obstacles, and frequent path conflicts, thus requiring extremely high efficiency and quality in planning the operating paths of automated equipment. Existing path planning methods mainly rely on the A* algorithm or artificial potential field method, which cannot detect dynamic obstacles in real time, resulting in long path generation times and high failure rates. The artificial potential field method has poor adaptability, cannot adapt to complex terrain, and has poor dynamic processing capabilities, leading to poor path quality and affecting the safe operation of automated equipment. Summary of the Invention

[0003] The purpose of this application is to provide a path planning method, apparatus, and storage medium to solve the problems of low efficiency and poor quality in path planning in the prior art.

[0004] To achieve the above objectives, the first aspect of this application provides a path planning method, the method comprising: The current position of the automated device is determined as the first node of the starting point tree, and the target endpoint position of the automated device is determined as the second node of the target tree; Construct a first region based on the first node and a preset length, and construct a second region based on the second node and a preset length; Determine the first path cost between each first sampling point and the first node in the first region, and determine the first sampling point corresponding to the first path cost with the smallest value as the first target node; Determine the second path cost between each second sampling point and the second node in the second region, and determine the second sampling point corresponding to the second path cost with the smallest value as the second target node; If the first target node and the second target node are different, the first target node is determined as the new first node, the second target node is determined as the new second node, and the process returns to the steps of constructing the first region based on the first node and the preset length, and constructing the second region based on the second node and the preset length, until the first target node and the second target node are the same. The path for the automated equipment to move from its current position to the target endpoint is determined based on all first and second target nodes.

[0005] In this embodiment of the application, determining the first path cost between each first sampling point and the first node in the first region includes: for each first sampling point, determining the path length cost between the first sampling point and the first node; for each first sampling point, determining the slope angle of the first sampling point, and determining the slope cost of the first sampling point based on the slope angle and the path length; and determining the first path cost of each first sampling point based on the path length cost and the slope cost.

[0006] In this embodiment of the application, the method further includes: acquiring real-time point cloud data of the environment surrounding the automated device before constructing the first region based on the first node and the preset length; generating a sampling domain based on the current position and the target endpoint position; dividing the surrounding environment into grids and determining the real-time point cloud density of each grid based on the real-time point cloud data of each grid; determining the real-time target offset probability based on the real-time point cloud density; generating multiple sampling points in the sampling domain based on the real-time target offset probability when the real-time target offset probability is greater than a preset value; and performing random sampling in the sampling domain to obtain multiple sampling points when the real-time target offset probability is less than or equal to the preset value.

[0007] In this embodiment of the application, generating a sampling domain based on the current position and the target endpoint position includes: determining the distance between the current position and the target endpoint position; determining a first length based on the distance and a first coefficient, and determining a second length based on the first length and a second coefficient; generating a sampling domain with the current position as the starting point, the first length, the second length, and a preset offset angle.

[0008] In this embodiment of the application, generating a sampling domain based on the current position and the target endpoint position includes: acquiring a real-time image of the surrounding environment; determining the working scene of the automatic device at the current moment based on the real-time image; updating a first length or a preset offset angle based on the working scene to obtain an updated first length or an updated preset offset angle; generating a sampling domain with the current position as the starting point, the updated first length, the second length, and the preset offset angle; or generating a sampling domain with the current position as the starting point, the first length, the second length, and the updated preset offset angle.

[0009] In this embodiment of the application, the method further includes: after determining the running path of the automatic device from the current position to the target endpoint position based on all first target nodes and second target nodes, determining the real-time steering angle of the automatic device; and controlling the automatic device to move according to the running path based on the real-time steering angle.

[0010] In this embodiment of the application, determining the real-time steering angle of the automated equipment includes: obtaining the curvature of the running path; determining the real-time turning radius of the automated equipment based on the curvature; and determining the real-time steering angle based on the real-time turning radius and the wheelbase of the automated equipment.

[0011] In this embodiment of the application, the method further includes: after determining the running path of the automatic device from the current position to the target endpoint position based on all first target nodes and second target nodes, acquiring real-time images of the surrounding environment of the automatic device; determining the real-time working scene of the automatic device based on the real-time images; and determining the real-time driving strategy of the automatic device when moving along the running path based on the real-time working scene.

[0012] A second aspect of this application provides a path planning apparatus, comprising: The memory is configured to store instructions; The processor is configured to retrieve instructions from memory and, when executing instructions, to implement the aforementioned path planning method.

[0013] A third aspect of this application provides a machine-readable storage medium storing instructions that cause a machine to perform the path planning method described above.

[0014] The above technical solution determines the current position of the automated equipment as the first node of the starting point tree and the target destination position of the automated equipment as the second node of the target tree. A first region is constructed based on the first node and a preset length, and a second region is constructed based on the second node and a preset length. The first path cost between each first sampling point and the first node in the first region is determined, and the first sampling point corresponding to the smallest first path cost is determined as the first target node. The second path cost between each second sampling point and the second node in the second region is determined, and the second sampling point corresponding to the smallest second path cost is determined as the second target node. If the first target node and the second target node are different, the first target node is determined as the new first node, and the second target node is determined as the new second node. The process of constructing the first region based on the first node and the preset length, and the second region based on the second node and the preset length, is repeated until the first target node and the second target node are the same. Based on all the first and second target nodes, the operating path for the automated equipment to move from its current position to the target destination position is determined, shortening the path search time, improving path planning efficiency, enhancing path quality, and improving the driving safety of subsequent automated equipment.

[0015] Other features and advantages of the embodiments of this application will be described in detail in the following detailed description section. Attached Figure Description

[0016] The accompanying drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the following detailed description to explain the embodiments of this application, but do not constitute a limitation on the embodiments of this application. In the drawings: Figure 1This schematically illustrates a first flowchart of a path planning method according to an embodiment of the present application; Figure 2 A schematic diagram of a sampling field according to an embodiment of this application is shown; Figure 3 This illustration schematically shows a second flowchart of a path planning method according to an embodiment of the present application; Figure 4 This schematically illustrates a third flowchart of a path planning method according to an embodiment of this application; Figure 5 The diagram illustrates the internal structure of a computer device according to an embodiment of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for illustration and explanation of the embodiments of this application and are not intended to limit the embodiments of this application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0018] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0019] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0020] Figure 1 The illustration schematically shows a first flowchart of a path planning method according to an embodiment of this application. For example... Figure 1 As shown in the figure, this application provides a path planning method, which may include the following steps.

[0021] Step 101: Determine the current position of the automatic device as the first node of the starting point tree, and determine the target endpoint position of the automatic device as the second node of the target tree.

[0022] Step 102: Construct a first region based on the first node and the preset length, and construct a second region based on the second node and the preset length.

[0023] The processor can determine the current position of the automated equipment as the first node of the starting point tree and the target endpoint position of the automated equipment as the second node of the target tree. The automated equipment includes AGVs, robots, autonomous vehicles, and other automated mobile devices capable of planning their own paths. Furthermore, the automated equipment includes traditional automated vehicles as well as new energy vehicles used in the field of automated equipment, such as new energy mixer trucks, new energy pump trucks, and new energy excavators. In addition, the automated vehicles in this embodiment are also intelligent connected vehicles. These vehicles include sensing systems and communication systems. The in-vehicle sensing system collects vehicle operation data and information about the vehicle's surrounding environment, while the communication system enables network connections with other vehicles and the cloud. The collected vehicle operation data and surrounding environment information are shared with the cloud and other authorized vehicles to achieve data sharing, remote analysis, and intelligent driving operations. The processor can construct a first region based on a first node and a preset length, and a second region based on a second node and a preset length. In an optional embodiment, the preset length can be determined based on actual conditions, such as 2 meters. That is, the first region can be a circle with the first node as the origin and a preset length of 2 meters as the radius. The second region can be a circle with the second node as the origin and a preset length of 2 meters as the radius.

[0024] In this embodiment of the application, the method further includes: acquiring real-time point cloud data of the environment surrounding the automated device before constructing the first region based on the first node and the preset length; generating a sampling domain based on the current position and the target endpoint position; dividing the surrounding environment into grids and determining the real-time point cloud density of each grid based on the real-time point cloud data of each grid; determining the real-time target offset probability based on the real-time point cloud density; generating multiple sampling points in the sampling domain based on the real-time target offset probability when the real-time target offset probability is greater than a preset value; and performing random sampling in the sampling domain to obtain multiple sampling points when the real-time target offset probability is less than or equal to the preset value.

[0025] Before constructing the first region based on the first node and a preset length, the processor can acquire real-time point cloud data of the environment surrounding the automated device. The processor can generate a sampling domain based on the current position and the target endpoint position. The processor can divide the surrounding environment into grids and determine the real-time point cloud density of each grid based on the real-time point cloud data of each grid. After determining the real-time point cloud density of each grid, the processor can determine the real-time target bias probability based on the real-time point cloud density. For example, the real-time target bias probability... ,in, , This represents the real-time point cloud density. After obtaining the real-time target bias probability, the processor can determine whether the real-time target bias probability is greater than a preset value. The preset value can be determined based on the actual situation; for example, it can be any number between 0 and 1. If the real-time target bias probability is greater than the preset value, the processor can generate multiple sampling points in the sampling domain based on the real-time target bias probability. If the real-time target bias probability is less than or equal to the preset value, the processor can perform random sampling in the sampling domain to obtain multiple sampling points.

[0026] In an optional embodiment, if the real-time target bias probability is greater than 1, the processor can truncate the real-time target bias probability so that the real-time target bias probability is less than or equal to 1.

[0027] In this embodiment of the application, generating a sampling domain based on the current position and the target endpoint position includes: determining the distance between the current position and the target endpoint position; determining a first length based on the distance and a first coefficient, and determining a second length based on the first length and a second coefficient; generating a sampling domain with the current position as the starting point, the first length, the second length, and a preset offset angle.

[0028] The processor can generate a sampling domain based on the current position and the target endpoint position. Specifically, the processor can determine the distance between the current position and the target endpoint position. After determining this distance, the processor can determine a first length based on the distance and a first coefficient, and determine a second length based on the first length and a second coefficient. The first and second coefficients can be determined based on actual conditions; for example, the first coefficient could be 0.6 and the second coefficient could be 0.3. Specifically, the first length can be the distance... The product of this and the first coefficient 0.6, i.e., the first length L = 0.6. The second length can be the product of the first length and the second coefficient 0.3, i.e., the second length W = 0.3L. After determining the first and second lengths, the processor can generate a sampling domain using the current position as the starting point, the first length, the second length, and a preset offset angle. The preset offset angle can be determined based on actual conditions, such as ±15°. Figure 2The diagram shows the distance between the starting point (current position) and the target point (target endpoint). The first length L = 0.6 The second length W = 0.3L, and the starting point, the first length L, the second length W, and the preset offset angle ±15° form an elliptical sampling domain.

[0029] In this embodiment of the application, generating a sampling domain based on the current position and the target endpoint position includes: acquiring a real-time image of the surrounding environment; determining the working scene of the automatic device at the current moment based on the real-time image; updating a first length or a preset offset angle based on the working scene to obtain an updated first length or an updated preset offset angle; generating a sampling domain with the current position as the starting point, the updated first length, the second length, and the preset offset angle; or generating a sampling domain with the current position as the starting point, the first length, the second length, and the updated preset offset angle.

[0030] The processor can generate a sampling domain based on the current position and the target endpoint position. Specifically, the processor can acquire real-time images of the surrounding environment. After obtaining the real-time images of the surrounding environment, the processor can determine the working scenario of the automated device at the current moment based on the real-time images. For example, the working scenario may include an ice surface scenario and a loading area scenario. After determining the working scenario of the automated device, the processor can update a first length or a preset offset angle based on the working scenario to obtain an updated first length or an updated preset offset angle. For example, if the working scenario is an ice surface scenario, the processor can control the first length to shorten, such as reducing a first coefficient, for example, to 0.5, to obtain an updated first length. If the working scenario is a loading area scenario, the processor can control the preset offset angle to achieve an offset towards the target endpoint position. After obtaining the updated first length, the processor can generate a sampling domain with the current position as the starting point, the updated first length, a second length, and the preset offset angle. Alternatively, after obtaining the updated preset offset angle, the processor can generate a sampling domain with the current position as the starting point, the first length, the second length, and the updated preset offset angle.

[0031] Step 103: Determine the first path cost between each first sampling point and the first node in the first region, and determine the first sampling point corresponding to the first path cost with the smallest value as the first target node.

[0032] After constructing the first region, the processor can determine the first path cost between each first sampling point and the first node in the first region. After determining the first path cost between each first sampling point and the first node in the first region, the processor can determine the first sampling point corresponding to the minimum first path cost as the first target node.

[0033] In this embodiment of the application, determining the first path cost between each first sampling point and the first node in the first region includes: for each first sampling point, determining the path length cost between the first sampling point and the first node; for each first sampling point, determining the slope angle of the first sampling point, and determining the slope cost of the first sampling point based on the slope angle and the path length; and determining the first path cost of each first sampling point based on the path length cost and the slope cost.

[0034] The processor can determine the first path cost between each first sampling point and a first node in the first region. Specifically, for each first sampling point, the processor can determine the path length cost between that first sampling point and the first node. For each first sampling point, the processor can determine the slope angle of that first sampling point and determine the slope cost of that first sampling point based on the slope angle and the path length. In a specific embodiment, the slope angle of the first sampling point... ,in, This represents the vertical acceleration component measured by the IMU (Inertial Measurement Unit), where g is the acceleration due to gravity. After obtaining the path length cost and slope cost for each first sampling point, the processor can determine the first path cost for each first sampling point based on these costs.

[0035] Step 104: Determine the second path cost between each second sampling point and the second node in the second region, and determine the second sampling point corresponding to the second path cost with the smallest value as the second target node.

[0036] Step 105: If the first target node and the second target node are different, determine the first target node as the new first node, determine the second target node as the new second node, and return to the steps of constructing the first region based on the first node and the preset length, and constructing the second region based on the second node and the preset length, until the first target node and the second target node are the same.

[0037] Step 106: Determine the running path for the automated equipment to move from its current position to the target endpoint position based on all first and second target nodes.

[0038] After constructing the second region, the processor can determine the second path cost between each second sampling point and the second node within the second region. After determining the second path cost between each second sampling point and the second node, the processor can identify the second sampling point with the smallest second path cost as the second target node. After determining the first target node and the second target node, the processor can determine whether the first target node and the second target node are the same. If the first target node and the second target node are different, the processor can identify the first target node as the new first node, identify the second target node as the new second node, and return to the steps of constructing the first region based on the first node and a preset length, and constructing the second region based on the second node and a preset length, until the first target node and the second target node are the same. After the first target node and the second target node are the same, the processor can determine the running path for the automated device to move from the current position to the target endpoint position based on all the first target nodes and the second target node.

[0039] In the embodiments of this application, such as Figure 3 As shown, in the map and positioning layer, RTK positioning (differential positioning) is obtained through GNSS (Global Navigation Satellite System) positioning, a local map is obtained through visual SLAM (Simultaneous Localization to Map Building), and IMU (Inertial Measurement Unit) data is obtained through dynamic error compensation, thus generating a global coordinate system. The map and positioning layer sends the high-precision map to the environmental perception layer and simultaneously sends real-time positioning to the algorithm decision layer. In the environmental perception layer, dynamic obstacle detection is performed through multi-sensor fusion using LiDAR, millimeter-wave radar, and visual sensors, and semantic map is constructed using terrain elevation and loading / unloading point coordinates from the BIM (Building Information Modeling) map. The environmental perception layer sends obstacle data to the algorithm decision layer. The algorithm decision layer receives real-time positioning, obstacle data, and scene switching instructions from a multi-scene strategy library. In the algorithm decision layer, the improved RRT* (Rapidly-exploring Random Tree Star, a sampling-based path planning algorithm) core performs bidirectional search in the elliptical sampling domain and combines multi-scene strategies to provide loading area parameters and ice surface parameters for global path generation. The algorithm decision layer sends the optimized path to the control execution layer. At the control execution layer, path tracking, such as through the Ackerman model, and emergency braking, such as collision warning, are performed to complete vehicle control.

[0040] In this embodiment of the application, the method further includes: after determining the running path of the automatic device from the current position to the target endpoint position based on all first target nodes and second target nodes, determining the real-time steering angle of the automatic device; and controlling the automatic device to move according to the running path based on the real-time steering angle.

[0041] After determining the running path of the automated equipment from its current position to the target endpoint based on all the first and second target nodes, the processor can determine the real-time steering angle of the automated equipment. After determining the real-time steering angle, the processor can control the automated equipment to move along the running path based on the real-time steering angle.

[0042] In this embodiment of the application, determining the real-time steering angle of the automated equipment includes: obtaining the curvature of the running path; determining the real-time turning radius of the automated equipment based on the curvature; and determining the real-time steering angle based on the real-time turning radius and the wheelbase of the automated equipment.

[0043] The processor can determine the real-time steering angle of the automated vehicle. Specifically, the processor can obtain the curvature k of the operating path. After obtaining the curvature k, the processor can determine the real-time turning radius R of the automated vehicle, i.e., R = 1 / k. After determining the real-time turning radius R, the processor can determine the real-time steering angle based on the real-time turning radius R and the wheelbase X of the automated vehicle. , In an optional embodiment, the real-time steering angle ,in, This indicates the yaw rate of the automated equipment. This indicates the longitudinal speed of the engineering vehicle.

[0044] In this embodiment of the application, the method further includes: after determining the running path of the automatic device from the current position to the target endpoint position based on all first target nodes and second target nodes, acquiring real-time images of the surrounding environment of the automatic device; determining the real-time working scene of the automatic device based on the real-time images; and determining the real-time driving strategy of the automatic device when moving along the running path based on the real-time working scene.

[0045] After determining the path for the automated equipment to move from its current position to the target endpoint based on all first and second target nodes, the processor can acquire real-time images of the equipment's surrounding environment. After obtaining these images, the processor can determine the real-time operating scenario of the automated equipment. Based on this scenario, the processor can then determine a real-time driving strategy for the automated equipment as it moves along the operating path. For example, if the real-time operating scenario is a loading area, the processor can generate a spiral trajectory during movement to improve safety. If the real-time operating scenario is an ice surface, the processor can constrain the automated equipment's movement using curvature and speed. If the real-time operating scenario involves uphill or downhill slopes, the processor can control the automated equipment's movement using gradient and torque energy consumption to improve operational safety.

[0046] In the embodiments of this application, such as Figure 4As shown, the input data source obtains LiDAR point clouds, visual semantic segmentation, and IMU attitude angles through the environment perception layer. The processor can calculate point cloud density based on the LiDAR point clouds, thereby outputting density. The processor performs visual classification based on visual semantic segmentation, thereby outputting labels. The processor can calculate slope based on IMU attitude angles, thereby outputting slope. The processor can classify the scene based on density, labels, and slope, and determine whether it is a safe scene. If it is determined to be an ice surface or obstacle avoidance scenario, the corresponding safety strategy is triggered, such as curvature and velocity constraints. If it is not a safe scene, it further determines whether it is a functional scene. If it is determined to be a loading or unloading scene, the functional strategy is triggered, such as spiral trajectory and communication protocol control. If it is not a functional scene, the normal strategy is triggered.

[0047] The above technical solutions shorten path search time, improve path planning efficiency, enhance path quality, and improve the driving safety of subsequent automated equipment.

[0048] Figure 1 , Figure 3 as well as Figure 4 This is a flowchart illustrating a path planning method in one embodiment. It should be understood that, although... Figure 1 , Figure 3 as well as Figure 4 The steps in the flowchart are shown sequentially as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order in which these steps are executed, and they can be performed in other orders. Figure 1 , Figure 3 as well as Figure 4 At least some of the steps in the process may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least some of the sub-steps or stages of other steps.

[0049] This application embodiment also provides a path planning device, including: The memory is configured to store instructions; The processor is configured to retrieve instructions from memory and, when executing instructions, to implement the aforementioned path planning method.

[0050] This application also provides a machine-readable storage medium storing instructions that cause a machine to execute the path planning method described above.

[0051] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 5 As shown, the computer device includes a processor A01, a network interface A02, memory (not shown), and a database (not shown) connected via a system bus. The processor A01 provides computational and control capabilities. The memory includes internal memory A03 and a non-volatile storage medium A04. The non-volatile storage medium A04 stores an operating system B01, a computer program B02, and a database (not shown). The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 stored in the non-volatile storage medium A04. The database stores data such as a first node, a second node, a first region, a second region, a first path cost, a second path cost, a first target node, a second target node, and the running path. The network interface A02 communicates with external terminals via a network connection. When the computer program B02 is executed by the processor A01, it implements a path planning method.

[0052] Those skilled in the art will understand that Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0053] This application provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs the following steps: determining the current position of the automated device as a first node of a starting point tree and determining the target endpoint position of the automated device as a second node of a target tree; constructing a first region based on the first node and a preset length, and constructing a second region based on the second node and a preset length; determining the first path cost between each first sampling point in the first region and the first node, and determining the first sampling point corresponding to the smallest first path cost as the first target node; determining the second path cost between each second sampling point in the second region and the second node, and determining the second sampling point corresponding to the smallest second path cost as the second target node; if the first target node and the second target node are different, determining the first target node as a new first node, determining the second target node as a new second node, and returning to the steps of constructing the first region based on the first node and the preset length, and constructing the second region based on the second node and the preset length, until the first target node and the second target node are the same; determining the running path for the automated device to move from its current position to the target endpoint position based on all the first target nodes and the second target nodes.

[0054] In one embodiment, determining the first path cost between each first sampling point and a first node in the first region includes: for each first sampling point, determining the path length cost between the first sampling point and the first node; for each first sampling point, determining the slope angle of the first sampling point, and determining the slope cost of the first sampling point based on the slope angle and path length; and determining the first path cost of each first sampling point based on the path length cost and slope cost of each first sampling point.

[0055] In one embodiment, the method further includes: acquiring real-time point cloud data of the environment surrounding the automated device before constructing the first region based on the first node and a preset length; generating a sampling domain based on the current position and the target endpoint position; dividing the surrounding environment into grids and determining the real-time point cloud density of each grid based on the real-time point cloud data of each grid; determining the real-time target offset probability based on the real-time point cloud density; generating multiple sampling points in the sampling domain based on the real-time target offset probability if the real-time target offset probability is greater than a preset value; and performing random sampling in the sampling domain to obtain multiple sampling points if the real-time target offset probability is less than or equal to the preset value.

[0056] In one embodiment, generating a sampling domain based on the current position and the target endpoint position includes: determining the distance between the current position and the target endpoint position; determining a first length based on the distance and a first coefficient, and determining a second length based on the first length and a second coefficient; generating a sampling domain with the current position as the starting point, the first length, the second length, and a preset offset angle.

[0057] In one embodiment, generating a sampling domain based on the current position and the target endpoint position includes: acquiring a real-time image of the surrounding environment; determining the working scene of the automated device at the current moment based on the real-time image; updating a first length or a preset offset angle based on the working scene to obtain an updated first length or an updated preset offset angle; generating a sampling domain with the current position as the starting point, the updated first length, the second length, and the preset offset angle; or generating a sampling domain with the current position as the starting point, the first length, the second length, and the updated preset offset angle.

[0058] In one embodiment, the method further includes: after determining the running path of the automatic device from its current position to the target endpoint position based on all first target nodes and second target nodes, determining the real-time steering angle of the automatic device; and controlling the automatic device to move along the running path based on the real-time steering angle.

[0059] In one embodiment, determining the real-time steering angle of an automated device includes: acquiring the curvature of the operating path; determining the real-time turning radius of the automated device based on the curvature; and determining the real-time steering angle based on the real-time turning radius and the wheelbase of the automated device.

[0060] In one embodiment, the method further includes: after determining the running path of the automated device from its current position to the target endpoint position based on all first target nodes and second target nodes, acquiring a real-time image of the surrounding environment of the automated device; determining the real-time operating scenario of the automated device based on the real-time image; and determining a real-time driving strategy for the automated device as it moves along the running path based on the real-time operating scenario.

[0061] This application also provides a computer program product that, when executed on a data processing device, is suitable for executing a program with initialization steps of a path planning method.

[0062] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0063] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0064] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0065] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0066] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0067] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0068] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0069] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0070] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A path planning method, characterized in that, The method includes: The current position of the automated device is determined as the first node of the starting point tree, and the target endpoint position of the automated device is determined as the second node of the target tree; A first region is constructed based on the first node and a preset length, and a second region is constructed based on the second node and the preset length; Determine the first path cost between each first sampling point in the first region and the first node, and determine the first sampling point corresponding to the first path cost with the smallest value as the first target node; Determine the second path cost between each second sampling point in the second region and the second node, and determine the second sampling point corresponding to the second path cost with the smallest value as the second target node; If the first target node and the second target node are different, the first target node is determined as the new first node, the second target node is determined as the new second node, and the process returns to the steps of constructing a first region based on the first node and a preset length, and constructing a second region based on the second node and the preset length, until the first target node and the second target node are the same. The path for the automated device to move from its current position to the target endpoint position is determined based on all first and second target nodes.

2. The path planning method according to claim 1, characterized in that, Determining the first path cost between each first sampling point in the first region and the first node includes: For each first sampling point, determine the path length cost between the first sampling point and the first node; For each first sampling point, determine the slope angle of the first sampling point, and determine the slope cost of the first sampling point based on the slope angle and path length; The first path cost for each first sampling point is determined based on the path length cost and slope cost for each first sampling point.

3. The path planning method according to claim 1, characterized in that, The method further includes: Before constructing the first region based on the first node and the preset length, real-time point cloud data of the environment surrounding the automated device is acquired; A sampling domain is generated based on the current position and the target endpoint position; The surrounding environment is divided into grids, and the real-time point cloud density of each grid is determined based on the real-time point cloud data of each grid. The real-time target bias probability is determined based on the real-time point cloud density. If the real-time target bias probability is greater than a preset value, multiple sampling points are generated in the sampling domain based on the real-time target bias probability. If the real-time target bias probability is less than or equal to the preset value, random sampling is performed in the sampling domain to obtain multiple sampling points.

4. The path planning method according to claim 3, characterized in that, The step of generating a sampling domain based on the current position and the target endpoint position includes: Determine the distance between the current position and the target endpoint position; A first length is determined based on the distance and a first coefficient, and a second length is determined based on the first length and a second coefficient. The sampling domain is generated using the current position as the starting point, the first length, the second length, and a preset offset angle.

5. The path planning method according to claim 4, characterized in that, The step of generating a sampling domain based on the current position and the target endpoint position includes: Acquire real-time images of the surrounding environment; The working scenario of the automated device at the current moment is determined based on the real-time image; Update the first length or the preset offset angle according to the work scenario to obtain the updated first length or the updated preset offset angle; The sampling domain is generated using the current position as the starting point, the updated first length, the second length, and the preset offset angle. Alternatively, the sampling domain can be generated using the current position as the starting point, the first length, the second length, and the updated preset offset angle.

6. The path planning method according to claim 1, characterized in that, The method further includes: After determining the running path of the automated device from the current position to the target endpoint position based on all first target nodes and second target nodes, the real-time steering angle of the automated device is determined; The automatic equipment is controlled to move along the operating path based on the real-time steering angle.

7. The path planning method according to claim 6, characterized in that, Determining the real-time steering angle of the automated equipment includes: Obtain the curvature of the running path; The real-time turning radius of the automated device is determined based on the curvature. The real-time steering angle is determined based on the real-time turning radius and the wheelbase of the automated equipment.

8. The path planning method according to claim 1, characterized in that, The method further includes: After determining the running path of the automated device from the current position to the target endpoint position based on all first target nodes and second target nodes, real-time images of the surrounding environment of the automated device are acquired. The real-time operating scenario of the automated equipment is determined based on the real-time image. The real-time driving strategy of the automated equipment is determined based on the real-time working scenario when it moves along the operating path.

9. A path planning device, characterized in that, include: The memory is configured to store instructions; A processor is configured to retrieve the instructions from the memory and, when executing the instructions, to implement the path planning method according to any one of claims 1 to 8.

10. A machine-readable storage medium, characterized in that, The machine-readable storage medium stores instructions for causing the machine to perform the path planning method according to any one of claims 1 to 8.

Images