Path planning method and device for airport special vehicle and electronic equipment
By combining the path planning method of A-star algorithm and dynamic window algorithm, the path planning of unmanned special vehicles at the airport is optimized, the problems of low path planning efficiency and dynamic obstacle avoidance are solved, and the flight punctuality and safety are improved.
Patent Information
- Application Number
- CN202411167948.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-23
- Publication Date
- 2024-11-12
AI Technical Summary
The route planning efficiency of unmanned special vehicles at the airport is low, resulting in unbalanced task allocation and unreasonable route planning, which increases flight delay rate and is difficult to avoid dynamic obstacles, affecting safety.
Using a path planning method combining A-star algorithm and dynamic window algorithm, the path planning area is determined by obtaining airport environment model and target task information, and using preset coefficients and obstacle information to optimize path planning, and dynamically update the task path to avoid obstacles. .
It improves the efficiency and safety of path planning, reduces flight delay rate, reduces airport management costs, and ensures the navigation accuracy of airport special vehicles in complex environments.
Smart Images

Figure CN118938930A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of airport special vehicles, and in particular to a path planning method, device and electronic equipment for airport special vehicles. Background Art
[0002] With the rapid development of the civil aviation industry, more and more airports are gradually expanding in size, and the daily throughput of airports is also increasing, which puts higher requirements on airport ground operations and the services provided by airports. Improving the efficiency of airport ground operations and services can effectively reduce flight delays. The flight punctuality rate is one of the important indicators for evaluating the quality of aviation services.
[0003] There are many types of unmanned special vehicles at airports, each with its own duties, jointly ensuring the normal operation of aircraft. At present, ground support services at airports still need to rely on manual scheduling. Manual scheduling is inefficient, and one unmanned special vehicle can only serve one flight at a time, which will lead to uneven distribution of vehicle tasks, unreasonable route planning, easy errors in the tasks of unmanned special vehicles, and increased ground support service time for flights, further causing flight delays. How to optimize the path planning of unmanned special vehicles at airports, conduct reasonable scheduling, reduce flight delays, and thus reduce airport management costs is particularly important. Obviously, there is an urgent need for a new path planning method for airport special vehicles to solve at least one of the above problems.
[0004] It should be noted that the above content only provides background technical information related to the present application and does not necessarily constitute prior art. Summary of the invention
[0005] In view of the above-mentioned shortcomings of the prior art, the present application provides a path planning method, device and electronic equipment for airport special vehicles to improve the efficiency of path planning, avoid dynamic obstacles, and improve the safety of airport special vehicles.
[0006] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.
[0007] According to one aspect of an embodiment of the present application, a path planning method for airport special vehicles is provided, comprising: obtaining an airport environment model, target task information corresponding to the airport environment model, and a current position of a target vehicle corresponding to the airport environment model, wherein the target task information comprises a global starting point corresponding to the target task and a global target point corresponding to the target task; performing path planning from the global starting point to the global target point by combining a target path algorithm with the airport environment model to obtain a task path, so that the target vehicle performs the target task along the task path, wherein the target path algorithm is obtained by adding a preset coefficient as a weight of a heuristic function in a preset A-star algorithm; determining a path planning area according to the current position of the target vehicle, using the path planning area as a dynamic window, and planning the task path within the path planning area according to a preset dynamic window algorithm, so as to update the task path according to the planning result.
[0008] In one embodiment of the present application, based on the aforementioned scheme, an airport environment model is obtained, including: dividing the airport scene area into multiple sub-areas; obtaining obstacle information corresponding to each of the sub-areas, and determining an obstacle area and a driving area from each of the sub-areas based on the obstacle information; and generating an airport environment model based on the obstacle area and the driving area.
[0009] In one embodiment of the present application, based on the aforementioned scheme, a path planning is performed from the global starting point to the global target point through a target path algorithm combined with the airport environment model to obtain a task path, including: determining the driving area where the global starting point is located as the starting node, and determining the driving area where the global target point is located as the final node; adding the starting node to the set of nodes to be processed; calculating the total cost of each node in the set of nodes to be processed, so as to determine the driving area with the smallest total cost as the current node; in response to determining the current node, determining the adjacent nodes corresponding to the current node from each of the driving areas; and using the current node as the parent node of the adjacent nodes. , and add the adjacent nodes corresponding to the current node to the set of nodes to be processed; respectively calculate the actual cost of each adjacent node corresponding to the current node, if the calculated actual cost of the adjacent node is less than the stored actual cost of the adjacent node, then update the stored actual cost of the adjacent node according to the calculated actual cost of the adjacent node; if any adjacent node is the final node, then generate the task path according to all parent nodes corresponding to the current node; if the actual cost of each adjacent node is greater than the actual cost of the current node, then move the current node into the set of processed nodes, and determine the node with the smallest total cost in the set of nodes to be processed as the new current node.
[0010] In one embodiment of the present application, based on the aforementioned scheme, the target path algorithm is obtained by adding a preset coefficient as the weight of the heuristic function in the preset A-star algorithm, including: counting the number of sub-areas between the starting node and the final node, and the number of obstacle areas between the current node and the final node; determining the preset coefficient based on the number of sub-areas and the number of obstacle areas, and using the preset coefficient as the weight of the heuristic function in the preset A-star algorithm to obtain the target path algorithm.
[0011] In one embodiment of the present application, based on the above scheme, the total cost of each driving area is calculated according to the actual cost and the expected cost, wherein the actual cost is determined according to the path length from the driving area to the starting node, and the expected cost is determined according to the distance between the driving area and the final node; wherein the calculation formula of the total cost includes: f(n)=g(n)+e P / Q (h(n)+h(p)-kcosβ); where f(n) is the total cost of each current node, g(n) is the actual cost from the starting node to the current node, e P / Q (h(n)+h(p)-kcosβ) is the estimated cost of the current node, Q is the number of sub-regions from the starting node to the final node, P is the number of obstacle regions from the current node to the final node, e P / Q is the weight of the heuristic function, h(n) is the estimated cost from the current node to the final node, h(p) is the estimated cost from the parent node of the current node to the final node, β is the angle between the first straight line and the second straight line, wherein the first straight line is composed of the current node and the starting node, the second straight line is composed of the current node and the final node, and k is a preset weight coefficient including the cosine of the angle.
[0012] In one embodiment of the present application, based on the aforementioned scheme, a path planning area is determined according to the current position of the target vehicle, the path planning area is used as a dynamic window, and the task path within the path planning area is planned according to a preset dynamic window algorithm to update the task path according to the planning result, including: obtaining the speed interval and time interval of the target vehicle; calculating according to the speed interval and the time interval to obtain the expected moving radius of the target vehicle; determining the path planning area according to the expected moving radius and the current position, and monitoring obstacles in the path planning area; determining the intersection of the path planning area and the task path that has not been traveled as an intermediate target point; determining the optimal path between the current position and the intermediate target point according to the obstacles through the dynamic window algorithm to update the task path according to the optimal path.
[0013] In one embodiment of the present application, based on the aforementioned scheme, the optimal path between the current position and the intermediate target point is determined according to the obstacle through the dynamic window algorithm, including: establishing a motion model of the target vehicle according to the angular velocity and linear velocity of the target vehicle through the dynamic window algorithm; predicting the simulated motion trajectory of the target vehicle according to the motion model, and determining one or more moving speeds at the next moment according to the speed limit, deceleration limit, and speed range of the target vehicle; using the heading angle, linear velocity, and the shortest distance between the end of the simulated motion trajectory and the obstacle as evaluation function indicators of the dynamic window algorithm, and determining the optimal path according to the evaluation function indicators.
[0014] In one embodiment of the present application, based on the aforementioned scheme, after taking the heading angle, linear velocity and the shortest distance between the end of the simulated motion trajectory and the obstacle as evaluation function indicators of the dynamic window algorithm, the method also includes: normalizing the evaluation function indicators to obtain a normalized trajectory evaluation function, wherein the formula of the trajectory evaluation function includes: G(v,ω)=α·heading(v,ω)+β·dist(v,ω)+γ·vel(v,ω); wherein α, β, γ are three weight coefficients, and α+β+γ=q; heading(v,ω) represents the angle between the heading and the intermediate target point; dist(v,ω) is the distance between the end of the simulated motion trajectory and the nearest obstacle; vel(v,ω) is the speed of the current simulated motion trajectory.
[0015] According to one aspect of an embodiment of the present application, a path planning device for airport special vehicles is provided, including: an acquisition module, used to acquire an airport environment model, target task information corresponding to the airport environment model and a current position of a target vehicle corresponding to the airport environment model, wherein the target task information includes a global starting point corresponding to the target task and a global target point corresponding to the target task; a first planning module, used to perform path planning from the global starting point to the global target point through a target path algorithm in combination with the airport environment model to obtain a task path, so that the target vehicle performs the target task along the task path, wherein the target path algorithm is obtained by adding a preset coefficient as the weight of a heuristic function in a preset A-star algorithm; a second planning module, used to determine a path planning area according to the current position of the target vehicle, use the path planning area as a dynamic window, and plan the task path within the path planning area according to a preset dynamic window algorithm, so as to update the task path according to the planning result.
[0016] According to one aspect of an embodiment of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the electronic device implements a path planning method for airport special vehicles as described in any one of the above embodiments.
[0017] The beneficial effects of the present application are as follows: the present application obtains an airport environment model, target task information corresponding to the airport environment model, and the current position of the target vehicle corresponding to the airport environment model, and plans a path from a global starting point to a global target point through a target path algorithm in combination with the airport environment model to obtain a task path, so that the target vehicle performs the target task along the task path, wherein the target path algorithm is obtained by adding a preset coefficient as the weight of the heuristic function in the preset A-star algorithm, and path planning through the target path algorithm can make task allocation more reasonable, path planning more reasonable, reduce the time for executing the target task, improve the efficiency of path planning, and thereby reduce flight delay rate and airport management costs; determine the path planning area according to the current position of the target vehicle, use the path planning area as a dynamic window, and plan the task path within the path planning area according to the preset dynamic window algorithm, so as to update the task path according to the planning results, and perform local path planning through the preset dynamic window algorithm to avoid dynamic obstacles, meet the navigation requirements of airport special vehicles in complex environments, and improve the driving safety of airport special vehicles.
[0018] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:
[0020] Figure 1 is a schematic diagram of an exemplary system architecture shown in an exemplary embodiment of the present application;
[0021] Figure 2 is a flow chart of a path planning method for airport special vehicles shown in an exemplary embodiment of the present application;
[0022] Figure 3 is a schematic diagram of an initial airport environment model of a path planning method for airport special vehicles shown in an exemplary embodiment of the present application;
[0023] Figure 4 is a schematic diagram of a motion model of a path planning method for a special vehicle for an airport, shown in an exemplary embodiment of the present application;
[0024] Figure 5 is a schematic diagram of maximum deceleration of a path planning method for airport special vehicles shown in an exemplary embodiment of the present application;
[0025] Figure 6 is a schematic diagram of a path planning result of a path planning method for a special vehicle at an airport, shown in an exemplary embodiment of the present application;
[0026] Figure 7 is a block diagram of a path planning device for airport special vehicles shown in an exemplary embodiment of the present application;
[0027] Figure 8 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION
[0028] The following will describe the implementation methods of the present application with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for illustrating the present application, not for limiting the scope of protection of the present application.
[0029] It should be noted that the illustrations provided in the following embodiments are only used to illustrate the basic concept of the present application in a schematic manner, and therefore the illustrations only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.
[0030] In the following description, a large number of details are discussed to provide a more thorough explanation of the embodiments of the present application. However, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present application difficult to understand.
[0031] First of all, it should be explained that the A* algorithm (A*search algorithm, pronounced as A-star), also known as the A* search algorithm, is a heuristic search algorithm. It is an algorithm used to solve the lowest cost from the starting point to the end point on the graph plane. It combines the advantages of breadth-first search (BFS) and heuristic search, and determines the search priority by evaluating the function f(n), so as to efficiently find the shortest path. The core idea of the A* algorithm is to use the heuristic function h(n) to estimate the cost from the current node n to the target node, and combine the actual cost g(n) from the starting point to the current node to determine the search priority by evaluating the function f(n) = g(n) + h(n). The algorithm maintains an open list to store the nodes to be examined and sorts them according to the priority of the f(n) value. In each step, the node with the smallest f(n) value in the open list is selected for exploration, and the f(n) value of the adjacent node is updated.
[0032] The DWA (Dynamic Window Approach) algorithm is an algorithm used for path planning of mobile machines, especially in local path planning. It is a suboptimal method of predictive control theory, which can avoid obstacles safely and effectively in unknown environments, and has the characteristics of small computational complexity, rapid response, and strong operability. The DWA algorithm mainly samples multiple groups of speeds in the speed space (v, ω), simulates the motion trajectories of these speeds within a certain period of time, and then scores these trajectories through an evaluation function. The speed corresponding to the optimal trajectory is selected and sent to the machine. This method takes into account the dynamic characteristics of the machine and the obstacles in the environment, enabling the machine to autonomously avoid obstacles and reach the target position in a complex environment.
[0033] Figure 1 It is a schematic diagram of an exemplary system architecture shown in an exemplary embodiment of the present application.
[0034] Reference Figure 1As shown, the system architecture may include a data acquisition device 101 and a computer device 102. The computer device 102 may be at least one of a desktop graphics processing unit (GPU) computer, a GPU computing cluster, a neural network computer, etc. The data acquisition device 101 is used to collect the airport environment model, the target task information corresponding to the airport environment model, and the current position of the target vehicle corresponding to the airport environment model, wherein the target task information includes the global starting point corresponding to the target task and the global target point corresponding to the target task. In this embodiment, the data acquisition device 101 obtains the above data and provides it to the computer device 102 for processing. Relevant technicians can use the computer device 102 to plan the path from the global starting point to the global target point through the target path algorithm combined with the airport environment model to obtain the task path, so that the target vehicle performs the target task along the task path, wherein the target path algorithm is obtained by adding a preset coefficient as the weight of the heuristic function in the preset A star algorithm; the path planning area is determined according to the current position of the target vehicle, the path planning area is used as a dynamic window, and the task path in the path planning area is planned according to the preset dynamic window algorithm, so as to update the task path according to the planning result. It should be noted that the data acquisition device 101 and the computer device 102 provided in this embodiment are merely examples and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0035] It should be noted that the path planning method for airport special vehicles provided in the embodiment of the present application is generally executed by the computer device 102, and accordingly, the path planning device for airport special vehicles is generally set in the computer device 102.
[0036] Figure 2 is a flow chart of a path planning method for a special vehicle at an airport according to an exemplary embodiment of the present application. The path planning method for a special vehicle at an airport can be executed by a computing and processing device. The computing and processing device can be Figure 1 The computer device 102 shown in FIG. Figure 2 As shown, the path planning method for airport special vehicles at least includes steps S210 to S230, which are described in detail as follows:
[0037] In step S210, the airport environment model, target task information corresponding to the airport environment model, and the current position of the target vehicle corresponding to the airport environment model are obtained.
[0038] In one embodiment of the present application, the process of obtaining the airport environment model includes: dividing the airport scene area into multiple sub-areas; obtaining obstacle information corresponding to each sub-area, and determining an obstacle area and a driving area from each sub-area according to the obstacle information; and generating the airport environment model according to the obstacle area and the driving area. The above obstacle information is preferably static obstacle information.
[0039] In this embodiment, the airport special vehicle is taken as an example of an airport unmanned special vehicle. The airport scene information is obtained, and the airport scene information includes information such as airport road surface information, airport building information, and airport apron information. The unmanned special vehicle working scene is updated according to the airport scene information, so that the entire airport is divided into three types of areas: obstacle area, driving area, and unknown area. Among them, the obstacle area is an area where special vehicles are prohibited from driving due to obstacles, the driving area is the driving area of the airport unmanned special vehicle, and the unknown area is an area that cannot be determined as an obstacle area or a driving area based on the currently collected airport scene information. Set the obstacle area to a black grid area, the driving area to a white grid area, and the unknown area to a recycled grid area to obtain the initial airport environment model, and refer to Figure 3 As shown, Figure 3 It is a schematic diagram of an initial airport environment model of a path planning method for airport special vehicles shown in an exemplary embodiment of the present application.
[0040] In this embodiment, after obtaining the initial airport environment model, the current scene information is obtained. The current scene information can be obtained by using the camera and sensor of the airport unmanned special vehicle. According to the obstacle information in the obtained current scene information, it is determined whether there is a static obstacle in the unknown area. If there is a static obstacle, the unknown area is determined as an obstacle area; if there is no static obstacle, the unknown area is determined as a driving area. The airport environment model is generated according to the obstacle area and the driving area, so as to plan the mission path of the airport unmanned special vehicle according to the airport environment model.
[0041] In one embodiment of the present application, after obtaining the airport environment model, the target task information and the current position of the target vehicle are obtained, and the target task information and the current position are converted into the airport environment model to obtain the target task information corresponding to the airport environment model and the current position of the target vehicle corresponding to the airport environment model, wherein the target task information includes the global starting point corresponding to the target task and the global target point corresponding to the target task.
[0042] In one embodiment of the present application, corresponding sub-databases are established in the dispatch system of the dispatch center for vehicles with different purposes, and the corresponding sub-databases are used to collect and store relevant parameters of corresponding vehicles with the same purpose.
[0043] In one embodiment of the present application, the simulation space is divided into continuous non-intersecting grid networks, i.e., sub-regions, according to a preset ratio, and such grids are used to construct an airport environment model for unmanned special vehicles. Assuming that the airport environment model for unmanned special vehicles at the airport is composed of m×n grids with a side length of a, the size of the environment composed of all grids is x×y, and the position corresponding to the i-th grid is expressed as follows:
[0044]
[0045] In formula (1), x i is the horizontal coordinate of the i-th grid, y i is the ordinate of the i-th grid, a is the side length of the grid, which is determined by a preset ratio, i is the number of the grid, y is the length of the airport scene in the airport scene information, and x is the width of the airport scene in the airport scene information.
[0046] In this embodiment, the two sides of the grid diagram are used to establish the coordinate axis, the horizontal direction is regarded as the x-axis, and the vertical direction is regarded as the y-axis. Figure 3 Then mark the coordinates of each grid in the format of (x,y). The value of each grid is "0" or "1", where "1" means the grid is occupied, i.e., the obstacle area, and "0" means the grid is idle, i.e., the driving area.
[0047] In step S220, a target path algorithm is combined with an airport environment model to plan a path from the global starting point to the global target point to obtain a task path, so that the target vehicle performs the target task along the task path.
[0048] In one embodiment of the present application, a path is planned from a global starting point to a global target point by combining a target path algorithm with an airport environment model, and the process of obtaining a task path may include the following steps: determining the driving area where the global starting point is located as the starting node, and determining the driving area where the global target point is located as the final node; adding the starting node to the set of nodes to be processed; calculating the total cost of each node in the set of nodes to be processed to determine the driving area with the smallest total cost as the current node; in response to determining the current node, determining the adjacent nodes corresponding to the current node from each driving area; taking the current node as the parent node of the adjacent nodes, and adding the adjacent nodes corresponding to the current node to the set of nodes to be processed; calculating the actual cost of each adjacent node corresponding to the current node respectively, if the calculated actual cost of the adjacent node is less than the actual cost of the stored adjacent node, then updating the actual cost of the stored adjacent node according to the calculated actual cost of the adjacent node; if any adjacent node is the final node, generating a task path according to all parent nodes corresponding to the current node; if the actual cost of each adjacent node is greater than the actual cost of the current node, then moving the current node into the set of processed nodes, and determining the node with the smallest total cost in the set of nodes to be processed as the new current node. Among them, the target path algorithm is obtained by adding a preset coefficient as the weight of the heuristic function in the preset A* algorithm. Using the improved A* algorithm, namely the target path algorithm, to calculate the global planning route of the unmanned special vehicle not only reduces the calculation cost, but also is more in line with the actual application scenario.
[0049] In one embodiment of the present application, the process of obtaining a target path algorithm by adding a preset coefficient as the weight of a heuristic function in a preset A-star algorithm may include the following steps: counting the number of sub-areas between the starting node and the final node, and the number of obstacle areas between the current node and the final node; determining the preset coefficient based on the number of sub-areas and the number of obstacle areas, and using the preset coefficient as the weight of the heuristic function in the preset A-star algorithm to obtain the target path algorithm.
[0050] In this embodiment, the A* algorithm is improved to achieve reasonable path planning for unmanned special vehicles at airports. On the basis of the traditional A* algorithm, an adaptive exponential coefficient is added as the weight of the heuristic function. The weight of the heuristic function can be flexibly allocated according to the current environment of the unmanned special vehicle at the airport, thereby reducing the traversal of invalid nodes. Use an adaptive exponential coefficient as the weight of the heuristic function. The adaptive exponential coefficient combines the ratio of the number of obstacles around the current node to the total number of obstacles. During the algorithm search process, the calculation of the estimated cost of the parent node of the current node is added to reduce the probability of the node traversing to both sides. Angle information is added when calculating the estimated cost of the current node to make the planned road more directional. The heuristic function of the improved A* algorithm, i.e., the target path algorithm, is as follows:
[0051] h A (n) = e P / Q (h(n)+h(p)-kcosβ) Formula (2)
[0052] In formula (2), the number of grids between the starting position of the airport unmanned special vehicle and the working aircraft is defined as Q, the number of grid obstacles within the search range from the current node to the target point is P, and e P / Q is the weight coefficient of the heuristic function of the improved A* algorithm; h(n) and h(p) are the estimated cost of the current node and the estimated cost of the parent node of the current node respectively; β is the angle between the straight line between the current node and the starting node and the straight line between the current node and the target point, and the value range is [0°, 180°]; k is the weight coefficient of the cosine of the included angle, which is determined by the environmental range. It can also be understood as, in formula (2), is the heuristic function of the target path algorithm, Q is the number of sub-areas from the global starting point to the global target point, P is the number of obstacle areas from the current node to the global target point, is the preset coefficient, is the estimated cost from the current node to the global target point, is the estimated cost from the parent node of the current node to the global target point, is the angle between the first straight line and the second straight line, where the first straight line is composed of the current node and the global starting point, the second straight line is composed of the current node and the global target point, and is the preset weight coefficient of the cosine of the included angle.
[0053] In one embodiment of the present application, the total cost of each driving area is calculated based on the actual cost and the expected cost, wherein the actual cost is determined based on the path length from the driving area to the starting node, and the expected cost is determined based on the distance between the driving area and the final node; wherein the calculation formula of the total cost includes formula (1):
[0054] f(n)=g(n)+e P / Q (h(n)+h(p)-kcosβ) Formula (3)
[0055] In formula (1), f(n) is the total cost of each current node, g(n) is the actual cost from the starting node to the current node, and e P / Q (h(n)+h(p)-kcosβ) is the estimated cost of the current node, Q is the number of sub-regions from the starting node to the final node, P is the number of obstacle regions from the current node to the final node, e P / Q is the weight of the heuristic function, h(n) is the estimated cost from the current node to the final node, h(p) is the estimated cost from the parent node of the current node to the final node, β is the angle between the first straight line and the second straight line, where the first straight line is composed of the current node and the starting node, and the second straight line is composed of the current node and the final node, and k is the preset weight coefficient of the cosine of the included angle.
[0056] In step S230, the path planning area is determined according to the current position of the target vehicle, the path planning area is used as a dynamic window, and the task path in the path planning area is planned according to a preset dynamic window algorithm to update the task path according to the planning result.
[0057] In one embodiment of the present application, the path planning area is determined according to the current position of the target vehicle, the path planning area is used as a dynamic window, and the task path in the path planning area is planned according to the preset dynamic window algorithm, so that the process of updating the task path according to the planning result may include the following steps: obtaining the speed interval and time interval of the target vehicle; calculating according to the speed interval and time interval to obtain the expected moving radius of the target vehicle; determining the path planning area according to the expected moving radius and the current position, and monitoring the obstacles in the path planning area; determining the intersection of the path planning area and the task path that has not been traveled as the intermediate target point; determining the optimal path between the current position and the intermediate target point according to the obstacles by the dynamic window algorithm, so as to update the task path according to the optimal path. On the basis of the task path obtained by the improved A* algorithm, the task path is updated by fusing the dynamic window algorithm (DWA), so that the airport unmanned special vehicle can run on a more reasonable global planning path, thereby avoiding dynamic obstacles and completing the navigation task safely and efficiently. This can further improve the execution efficiency of path planning and the smoothness of the task path, making the global path planning system of the airport unmanned special vehicle more perfect.
[0058] In one embodiment of the present application, the process of determining the optimal path between the current position and the intermediate target point based on obstacles through a dynamic window algorithm may include the following steps: establishing a motion model of the target vehicle based on the angular velocity and linear velocity of the target vehicle through a dynamic window algorithm; predicting the simulated motion trajectory of the target vehicle based on the motion model, and determining one or more moving speeds at the next moment based on the speed limit, deceleration limit, and speed range of the target vehicle; using the heading angle, linear velocity, and the shortest distance between the end of the simulated motion trajectory and the obstacle as evaluation function indicators of the dynamic window algorithm, and determining the optimal path based on the evaluation function indicators.
[0059] In this embodiment, the airport unmanned special vehicle integrated with the dynamic window algorithm (DWA) runs on a planned global path, namely the mission path, to avoid dynamic obstacles, thereby completing the navigation task safely and efficiently. This can further improve the execution efficiency of the target path algorithm and the smoothness of the planned path, making the global path planning system of the airport unmanned special vehicle more perfect. The dynamic window method converts the position control of the airport unmanned special vehicle into speed control. When using the speed model to predict the motion trajectory of the airport unmanned special vehicle, it is first necessary to analyze the motion model of the airport unmanned special vehicle. Use the in-vehicle sensors to collect vehicle-related information in real time to establish a motion model of the unmanned special vehicle, so as to grasp the status and position of the unmanned special vehicle in real time. According to the dynamic window algorithm, a kinematic model of the target vehicle is established according to the angular velocity and linear velocity of the target vehicle, and reference is made to the angular velocity and linear velocity of the target vehicle. Figure 4 , Figure 4 This is a schematic diagram of a motion model of a path planning method for a special vehicle at an airport, shown in an exemplary embodiment of the present application. The kinematic model expression is:
[0060]
[0061] In formula (4), x(t), y(t), θ(t) are the position and posture of the unmanned special vehicle at the airport at time t, v(t), ω(t) are the linear velocity and angular velocity of the unmanned special vehicle per unit time, respectively, and Δt is the preset unit sampling time. Preferably, the unit sampling time is set to be smaller. It should be noted that the position and posture refer to the position and direction of the posture or gesture of an object, robot or person in three-dimensional space. It consists of two basic elements: position and direction. Among them, the position represents the coordinates of the center or reference point of the object in three-dimensional space, usually represented by three real numbers (such as X, Y, Z coordinates); the direction represents the orientation or posture of the object in three-dimensional space, which can usually be described by rotation matrix, Euler angle or quaternion. The efficiency of the improved A* algorithm is improved by establishing a kinematic model of unmanned special vehicles.
[0062] The DWA algorithm is used to select the speed at the next moment based on the prediction of the trajectory of the airport unmanned special vehicle. The process includes: controlling the sampling speed within a specific range according to the airport unmanned special vehicle and environmental restrictions. The maximum speed of the airport unmanned special vehicle itself is as follows:
[0063] V m ={v∈[v min ,v max ],ω∈[ω min ,ω max Formula (5)
[0064] In formula (5), V mis the maximum speed of the airport unmanned special vehicle itself, v is the linear speed of the airport unmanned special vehicle, ω is the angular velocity of the airport unmanned special vehicle, and v min is the minimum linear speed of the airport unmanned special vehicle, v max is the maximum linear speed of the airport unmanned special vehicle, ω min is the minimum angular velocity of the airport unmanned special vehicle, ω max is the maximum angular velocity of the airport's unmanned special vehicle.
[0065] Since the motor torque of the airport unmanned special vehicle is limited, there is a maximum acceleration and deceleration limit. In the simulation cycle of the unmanned special vehicle's motion trajectory, there is a dynamic window, and the speed value in this window is the actual speed that the vehicle can reach during operation:
[0066]
[0067] In formula (6), V d To consider the actual speed of the airport unmanned special vehicle limited by the motor torque within the control cycle, v is the linear speed of the airport unmanned special vehicle, ω is the angular velocity of the airport unmanned special vehicle, and v c is the given current linear velocity, ω c is the given current angular velocity, is the maximum linear deceleration of the airport unmanned special vehicle, is the maximum angular deceleration of the airport unmanned special vehicle, The maximum linear acceleration of unmanned special vehicles at airports, The maximum angular acceleration of the airport unmanned special vehicle, Δt is the preset unit sampling time.
[0068] refer to Figure 5 , Figure 5 This is a schematic diagram of the maximum deceleration of a path planning method for airport special vehicles shown in an exemplary embodiment of the present application. In order to enable the mobile machinery to obtain a suitable deceleration distance under the maximum deceleration condition, the speed has a range:
[0069]
[0070] Where v is the linear velocity of the airport unmanned special vehicle, ω is the angular velocity of the airport unmanned special vehicle, dist(v,ω) is the closest distance to the obstacle on the trajectory corresponding to the velocity, V a In order to maintain the sampling speed at this distance, is the maximum linear deceleration of the airport unmanned special vehicle, It is the maximum angular deceleration of the airport unmanned special vehicle.
[0071] The heading angle, linear velocity and the shortest distance between the end of the simulated trajectory and the obstacle of the airport unmanned special vehicle are used as evaluation function indicators of the DWA algorithm.
[0072] In one embodiment of the present application, the process after taking the heading angle, the linear velocity and the shortest distance between the end of the simulated motion trajectory and the obstacle as the evaluation function index of the dynamic window algorithm may include the following steps: normalizing the evaluation function index to obtain a normalized trajectory evaluation function, wherein the formula of the trajectory evaluation function includes formula (8):
[0073] G(v,ω)=α·heading(v,ω)+β·dist(v,ω)+γ·vel(v,ω) Equation (8)
[0074] In formula (8), α, β, and γ are three weight coefficients, and α+β+γ=1; heading(v,ω) represents the angle between the heading and the intermediate target point; dist(v,ω) is the distance between the end of the simulated motion trajectory and the nearest obstacle; vel(v,ω) is the speed of the current simulated motion trajectory. In order to avoid a certain value being too large or the proportion being too large, each indicator is normalized.
[0075] In one embodiment of the present application, the hybrid path planning system mainly includes two parts: global planning and local planning. First, the global planning system uses an improved A* algorithm to obtain the global path of the unmanned special vehicle. Then, during the forward simulation trajectory time of the DWA algorithm, the intersection of the local map range and the current global path is used as the intermediate target point. Under the local path planner, the DWA algorithm is used to plan a local path with the intermediate target point as the temporary end point. In the local path planner, the DWA algorithm completes the avoidance of dynamic obstacles in the environment. Finally, the global target point is reached by continuously updating the intermediate target point. When the DWA planner plans the local path, if unknown obstacles on the current global path are to be avoided, the local path may deviate from the global direction. The A* algorithm is now improved to perform dynamic path replanning. Reference Figure 6 , Figure 6 FIG. 1 is a schematic diagram of a path planning result of a path planning method for a special vehicle at an airport, shown in an exemplary embodiment of the present application. Figure 6 In the figure, the circle is the starting point, the five-pointed star is the end point, the black square area is the obstacle area, the white square area is the driving area, and the line between the starting point and the end point is the task path.
[0076] In one embodiment of the present application, the operating environment is updated in real time by coordinating the driving status and the environment of multiple types of vehicles. The rationality of the task path is further achieved. By upgrading the planning of a single vehicle, the simultaneous path planning of multiple types of vehicles is achieved, and the operating environment is updated in real time through the sensors of various vehicles. The rationality of the driving path is further achieved.
[0077] The present application plans the path of an airport unmanned special vehicle through a path planning method for an airport unmanned special vehicle based on the fusion of the A* algorithm and DWA. Although the traditional path planning method based on the A* algorithm takes into account the starting point and static obstacles and improves the efficiency of global path planning, it still cannot avoid unknown obstacles in the environment. Since the actual airport scene changes rapidly, there may be a risk of obstacles in unknown areas, which increases the driving risk of unmanned special vehicles at the airport. In order to solve this problem and improve the planning efficiency of the global algorithm, the present application improves the heuristic function of the A* algorithm and integrates the DWA algorithm to form a new path planning method. A path planning method for an airport unmanned special vehicle based on the fusion of the A* algorithm and DWA is proposed. The present application uses the intersection of the local path planning range and the global path as the intermediate target point to perform local path planning. The trajectory similarity evaluation coefficient is added to the heuristic function. When the original global path needs to be reopened due to unknown obstacles, the local planning function will be fed back to the improved A* algorithm for dynamic path replanning. In this way, the hybrid path algorithm can avoid dynamic environmental obstacles. At the same time, when encountering unknown obstacles, local planning can be adopted and the global path can be adjusted to meet the navigation requirements of airport unmanned special vehicles in real-time complex environments.
[0078] Figure 3 is a block diagram of a path planning device for airport special vehicles shown in an exemplary embodiment of the present application. The device can be applied to Figure 1 The implementation environment shown in the figure is specifically configured in the computer device 102. The device can also be applied to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment to which the device is applied.
[0079] like Figure 7 As shown, the exemplary path planning device for airport special vehicles includes: an acquisition module 710, a first planning module 720 and a second planning module 730.
[0080] Among them, the acquisition module 710 is used to obtain the airport environment model, the target task information corresponding to the airport environment model and the current position of the target vehicle corresponding to the airport environment model, wherein the target task information includes the global starting point corresponding to the target task and the global target point corresponding to the target task; the first planning module 720 is used to plan the path from the global starting point to the global target point through the target path algorithm combined with the airport environment model to obtain the task path, so that the target vehicle performs the target task along the task path, wherein the target path algorithm is obtained by adding a preset coefficient as the weight of the heuristic function in the preset A-star algorithm; the second planning module 730 is used to determine the path planning area according to the current position of the target vehicle, use the path planning area as a dynamic window, and plan the task path within the path planning area according to the preset dynamic window algorithm to update the task path according to the planning results.
[0081] It should be noted that the path planning device for airport special vehicles provided in the above embodiment and the path planning method for airport special vehicles provided in the above embodiment belong to the same concept, wherein the specific manner in which each module and unit performs operations has been described in detail in the method embodiment and will not be repeated here. In actual applications, the path planning device for airport special vehicles provided in the above embodiment can allocate the above functions to different functional modules as needed, that is, divide the internal structure of the device into different functional modules to complete all or part of the functions described above, and this is not limited here.
[0082] An embodiment of the present application also provides an electronic device, comprising: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by one or more processors, the electronic device implements the path planning method for airport special vehicles provided in the above-mentioned embodiments.
[0083] Figure 8 The structure diagram of the computer system suitable for implementing the electronic device of the embodiment of the present application is shown. It should be noted that: Figure 8 The computer system 800 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0084] like Figure 8As shown, the computer system 800 includes a central processing unit (CPU) 801, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 802 or the program loaded from the storage part 808 to the random access memory (RAM) 803, such as executing the methods provided in the above-mentioned various embodiments. In the RAM 803, various programs and data required for system operation are also stored. The CPU 801, the ROM 802 and the RAM 803 are connected to each other through the bus 804. The input / output (I / O) interface 805 is also connected to the bus 804.
[0085] The following components are connected to the I / O interface 805: an input section 806 including a keyboard, a mouse, etc.; an output section 807 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 808 including a hard disk, etc.; and a communication section 809 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the I / O interface 805 as needed. A removable medium 811, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 810 as needed so that a computer program read therefrom is installed into the storage section 808 as needed.
[0086] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 809, and / or installed from a removable medium 811. When the computer program is executed by a central processing unit (CPU) 801, various functions defined in the system of the present application are executed.
[0087] It should be noted that the computer-readable medium shown in the embodiment of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable computer program is carried. This propagated data signal can take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. A computer program contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.
[0088] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0089] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.
[0090] Another aspect of the present application provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer executes the path planning method for airport special vehicles provided in the above embodiments. The computer-readable storage medium may be included in the electronic device described in the above embodiments, or may exist independently without being assembled into the electronic device.
[0091] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.
[0092] Another aspect of the present application also provides a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device reads the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the path planning method for airport special vehicles provided in the above-mentioned various embodiments.
[0093] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation methods of the present application.
[0094] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application.
[0095] The above embodiments are merely illustrative of the principles and effects of the present application, and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.
Claims
1. A path planning method for airport special vehicles, characterized in that: include: Acquire an airport environment model, target task information corresponding to the airport environment model, and a current position of a target vehicle corresponding to the airport environment model, wherein the target task information includes a global starting point corresponding to the target task and a global target point corresponding to the target task; A target path algorithm is used in combination with the airport environment model to plan a path from the global starting point to the global target point, so as to obtain a task path, so that the target vehicle performs the target task along the task path, wherein the target path algorithm is obtained by adding a preset coefficient to the preset A-star algorithm as a weight of the heuristic function; A path planning area is determined according to the current position of the target vehicle, the path planning area is used as a dynamic window, and a task path within the path planning area is planned according to a preset dynamic window algorithm, so as to update the task path according to the planning result.
2. The path planning method for airport special vehicles according to claim 1, characterized in that: Access to airport environment models, including: Divide the airport scene area into multiple sub-areas; Obtaining obstacle information corresponding to each of the sub-areas, and determining an obstacle area and a driving area from each of the sub-areas according to the obstacle information; An airport environment model is generated according to the obstacle area and the driving area.
3. The path planning method for airport special vehicles according to claim 2, characterized in that: The path planning from the global starting point to the global target point is performed by combining the target path algorithm with the airport environment model to obtain the task path, including: Determine the driving area where the global starting point is located as the starting node, and determine the driving area where the global target point is located as the final node; Adding the starting node to a set of nodes to be processed; Calculating the total cost of each node in the set of nodes to be processed, so as to determine the driving area with the minimum total cost as the current node; In response to determining the current node, determining an adjacent node corresponding to the current node from each of the driving areas; Taking the current node as the parent node of the adjacent nodes, and adding the adjacent nodes corresponding to the current node to the set of nodes to be processed; Calculate the actual cost of each adjacent node corresponding to the current node respectively, and if the calculated actual cost of the adjacent node is less than the stored actual cost of the adjacent node, update the stored actual cost of the adjacent node according to the calculated actual cost of the adjacent node; If any adjacent node is the final node, the task path is generated according to all parent nodes corresponding to the current node; If the actual cost of each of the adjacent nodes is greater than the actual cost of the current node, the current node is moved into the processed node set, and the node with the smallest total cost in the to-be-processed node set is determined as the new current node.
4. The path planning method for airport special vehicles according to claim 3 is characterized in that: The target path algorithm is obtained by adding a preset coefficient as the weight of the heuristic function to the preset A-star algorithm, including: Counting the number of sub-areas between the starting node and the final node, and the number of obstacle areas between the current node and the final node; The preset coefficient is determined based on the number of sub-areas and the number of obstacle areas, and the preset coefficient is used as the weight of the heuristic function in the preset A-star algorithm to obtain the target path algorithm.
5. The path planning method for airport special vehicles according to claim 4, characterized in that: Calculating the total cost of each of the driving areas according to the actual cost and the estimated cost, wherein the actual cost is determined according to the path length from the driving area to the starting node, and the estimated cost is determined according to the distance between the driving area and the final node; The calculation formula of the total cost includes: f(n)=g(n)+e P / Q (h(n)+h(p)-kcosβ); Wherein, f(n) is the total cost of each current node, g(n) is the actual cost from the starting node to the current node, and e P / Q (h(n)+h(p)-kcosβ) is the estimated cost of the current node, Q is the number of sub-regions from the starting node to the final node, P is the number of obstacle regions from the current node to the final node, e P / Q is the weight of the heuristic function, h(n) is the estimated cost from the current node to the final node, h(p) is the estimated cost from the parent node of the current node to the final node, β is the angle between the first straight line and the second straight line, wherein the first straight line is composed of the current node and the starting node, the second straight line is composed of the current node and the final node, and k is a preset weight coefficient including the cosine of the angle.
6. The path planning method for airport special vehicles according to claim 1, characterized in that: Determining a path planning area according to the current position of the target vehicle, taking the path planning area as a dynamic window, and planning a task path within the path planning area according to a preset dynamic window algorithm, so as to update the task path according to the planning result, including: Obtain the speed range and time range of the target vehicle; Calculating according to the vehicle speed interval and the time interval to obtain the expected moving radius of the target vehicle; Determining the path planning area according to the expected moving radius and the current position, and monitoring obstacles in the path planning area; Determine an untraveled intersection point among the intersection points of the path planning area and the task path as an intermediate target point; The optimal path between the current position and the intermediate target point is determined according to the obstacle by the dynamic window algorithm, so as to update the task path according to the optimal path.
7. The path planning method for airport special vehicles according to claim 6, characterized in that: Determining the optimal path from the current position to the intermediate target point according to the obstacle by using the dynamic window algorithm includes: Establishing a motion model of the target vehicle according to the angular velocity and linear velocity of the target vehicle by using the dynamic window algorithm; Predicting a simulated motion trajectory of the target vehicle according to the motion model, and determining one or more moving speeds at the next moment according to a speed limit, a deceleration limit, and a speed range of the target vehicle; The heading angle, linear velocity and the shortest distance between the end of the simulated motion trajectory and the obstacle are used as evaluation function indicators of the dynamic window algorithm, and the optimal path is determined according to the evaluation function indicators.
8. The path planning method for airport special vehicles according to claim 7, characterized in that: After taking the heading angle, the linear velocity and the shortest distance between the end of the simulated motion trajectory and the obstacle as evaluation function indicators of the dynamic window algorithm, the method further includes: Normalizing the evaluation function index to obtain a normalized trajectory evaluation function; Wherein, the formula of the trajectory evaluation function includes: G(v,ω)=α·heading(v,ω)+β·dist(v,ω)+γ·vel(v,ω); Where α, β, and γ are three weight coefficients, and α+β+γ=1; heading(v,ω) represents the angle between the heading and the intermediate target point; dist(ν,ω) is the distance between the end of the simulated motion trajectory and the nearest obstacle; vel(ν,ω) is the speed of the current simulated motion trajectory.
9. A path planning device for special vehicles at an airport, characterized in that: include: An acquisition module, used to acquire an airport environment model, target task information corresponding to the airport environment model, and a current position of a target vehicle corresponding to the airport environment model, wherein the target task information includes a global starting point corresponding to the target task and a global target point corresponding to the target task; A first planning module is used to plan a path from the global starting point to the global target point by combining a target path algorithm with the airport environment model to obtain a task path so that the target vehicle performs the target task along the task path, wherein the target path algorithm is obtained by adding a preset coefficient to a preset A-star algorithm as a weight of a heuristic function; The second planning module is used to determine a path planning area according to the current position of the target vehicle, use the path planning area as a dynamic window, and plan the task path within the path planning area according to a preset dynamic window algorithm to update the task path according to the planning result.
10. An electronic device, characterized in that: The electronic device comprises: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, enables the electronic device to implement the path planning method for airport special vehicles as described in any one of claims 1 to 8.
Citation Information
Patent Citations
Global dynamic path planning algorithm for multiple virtual target points based on dynamic window
CN110018689A
Method and equipment for fusing global path planning and local path planning of mobile robot
CN113359718A
Unmanned aerial vehicle optimal path planning method and system based on hybrid algorithm, and medium
CN114625162A
Mixed path planning method based on improved A* algorithm and dynamic window method
CN117451068A
Global path planning method and apparatus, terminal, and readable storage medium
WO2022007350A1
Cited By
Rodless aircraft tractor automatic deviation correction method and system based on machine vision
CN119148746A
