Vehicle-machine cooperative task allocation and path planning method for complex environment

Abstract

The invention discloses a vehicle-aircraft cooperative task allocation and path planning method for a complex environment, and belongs to the technical field of vehicle-aircraft cooperative operation, and the method comprises the following steps: S1, respectively allocating a ground target point and an aerial target point to an unmanned vehicle and an unmanned aerial vehicle, and determining a convergence point of the unmanned vehicle and the unmanned aerial vehicle as an end point, starting point, target point and terminal point information of each unmanned vehicle and each unmanned aerial vehicle are obtained; s2, searching an initial path based on the starting point, target point and terminal point information of each unmanned vehicle and unmanned aerial vehicle; s3, establishing a safety corridor based on the initial search path of each unmanned vehicle and unmanned aerial vehicle; s4, performing path optimization based on the searched initial path and the established safety corridor; the unmanned vehicle and the unmanned aerial vehicle have independent heuristic function search initial paths, meanwhile, double path optimization is achieved, and the method can be suitable for the complex environment where the unmanned vehicle and the unmanned aerial vehicle work cooperatively.

Description

Technical Field

[0001] The present invention belongs to the technical field of vehicle-computer collaborative operation, and specifically relates to a vehicle-computer collaborative task allocation and path planning method for complex environments. Background Art

[0002] The vehicle-machine collaborative task allocation and path planning method refers to a method that uses a series of strategies and technical means to reasonably allocate tasks and plan the movement paths of unmanned vehicles and drones in scenarios where unmanned vehicles and drones work together, so as to achieve the goals of optimizing task execution efficiency, reducing resource waste and ensuring operation safety.

[0003] Current vehicle-machine collaborative task allocation and path planning methods are generally targeted at a single intelligent entity, that is, unmanned vehicles or drones of the same type, and cannot be directly applied to complex environments where unmanned vehicles and drones work together.

[0004] In view of this, a vehicle-machine collaborative task allocation and path planning method for complex environments is designed to solve the above problems. Summary of the invention

[0005] To solve the problems raised in the above background technology, the present invention provides a vehicle-machine collaborative task allocation and path planning method for complex environments, which has the characteristics of being suitable for complex environments where unmanned vehicles and unmanned aerial vehicles work together.

[0006] To achieve the above object, the present invention provides the following technical solution: a vehicle-machine collaborative task allocation and path planning method for complex environments, comprising the following steps:

[0007] S1: Assign ground target points and aerial target points to unmanned vehicles and drones respectively, and determine the meeting point of the unmanned vehicle and drone as the end point to obtain the starting point, target point and end point information of each unmanned vehicle and drone;

[0008] S2: Searching for the initial path based on the starting point, target point, and end point information of each unmanned vehicle and drone;

[0009] S3: Establishing a safe corridor based on the search initial path of each unmanned vehicle and drone;

[0010] S4: Path optimization based on the searched initial path and the established safe corridor.

[0011] Furthermore, in step S1, the specific steps of assigning the ground target points and the aerial target points to the unmanned vehicle and the unmanned aerial vehicle respectively include:

[0012] S11: In each round, the nearest target point is assigned to the unmanned vehicle and the drone, and the positions of the unmanned vehicle and the drone are updated. In this process, if the same target point is assigned to multiple unmanned vehicles or drones at the same time, it is considered a conflict, and new constraints are added and reallocated according to the new constraints;

[0013] S12: Repeat step S11 until the number of remaining target points is 0;

[0014] S13: The current position of all unmanned vehicles, i.e., the ground target point, is taken as the end point;

[0015] S14: According to the current positions of all drones, the nearest ground target point is assigned as the end point;

[0016] S15: Repeat step S14 until all drones reach the end point.

[0017] Furthermore, the specific steps of step S2 include:

[0018] S21: The unmanned vehicle uses Manhattan distance as a heuristic function, generates a possible set of candidate nodes based on the current node position, heuristic function and mobility, evaluates each node in the generated candidate node set, and selects the path with the lowest cost as the initial path;

[0019] S22: The drone uses Euclidean distance as a heuristic function, generates a possible set of candidate nodes based on the current node position, heuristic function and mobility, evaluates each node in the generated set of candidate nodes, and selects the path with the lowest cost as the initial path;

[0020] S23: During the initial path planning of unmanned vehicles and drones, check whether the initial paths of unmanned vehicles or drones occupy the same node at the same time and whether there is spatiotemporal overlap of the paths. If there is the same node occupied at the same time or the paths have spatiotemporal overlap, it is considered a conflict, and additional constraints are added to the conflicting unmanned vehicles or drones. The unmanned vehicles or drones with the new constraints are returned to the initial path planning to replan the path until there is no conflict.

[0021] Furthermore, the specific steps of step S3 include:

[0022] Each node in the initial search path is extended in two or three dimensions until an obstacle is encountered or the map boundary is stopped during the extension process, thus establishing a safe corridor.

[0023] Furthermore, the specific steps of step S4 include:

[0024] S41: Establish kinematic mathematical models of unmanned vehicles and drones;

[0025] S42: defining an optimization objective function of a kinematic mathematical model, and setting constraint equations, including initial state constraints, kinematic constraints, and time constraints, and setting thresholds of optimization variables;

[0026] S43: Solve the initial path of the optimization search and the established safety corridor based on the Ipopt solver to achieve path optimization.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] The present invention first allocates ground target points and aerial target points to unmanned vehicles and unmanned aerial vehicles, and then determines the meeting point of the unmanned vehicles and unmanned aerial vehicles as the end point to obtain the starting point, target point and end point of the unmanned vehicles and unmanned aerial vehicles, and then searches for initial paths based on the starting point, target point and end point of the unmanned vehicles and unmanned aerial vehicles, respectively defines two heuristic functions and node expansion methods, and can timely add constraints to re-search when conflicts exist, and then establishes a safety corridor based on the searched initial path, and then performs dual path optimization on the searched initial path and the established safety corridor, and outputs the optimized path planning result. Compared with the prior art, the unmanned vehicles and unmanned aerial vehicles have independent heuristic functions to search for initial paths, and have dual path optimization, and can be applicable to complex environments where unmanned vehicles and unmanned aerial vehicles work together. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 The present invention is a flow chart of the vehicle-machine collaborative task allocation and path planning method for complex environments. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] A vehicle-machine collaborative task allocation and path planning method for complex environments includes the following steps:

[0032] S1: Assign ground target points and aerial target points to unmanned vehicles and drones respectively, and determine the meeting point of the unmanned vehicle and drone as the end point to obtain the starting point, target point and end point information of each unmanned vehicle and drone;

[0033] The specific steps of assigning ground target points and aerial target points to unmanned vehicles and drones respectively include:

[0034] S11: In each round, the nearest target point is assigned to the unmanned vehicle and the drone, and the positions of the unmanned vehicle and the drone are updated. In this process, if the same target point is assigned to multiple unmanned vehicles or drones at the same time, it is considered a conflict, and new constraints are added and reallocated according to the new constraints;

[0035] S12: Repeat step S11 until the number of remaining target points is 0;

[0036] S13: The current position of all unmanned vehicles, i.e., the ground target point, is taken as the end point;

[0037] S14: According to the current positions of all drones, the nearest ground target point is assigned as the end point;

[0038] S15: Repeat step S14 until all drones reach the end point;

[0039] S2: Searching for the initial path based on the starting point, target point, and end point information of each unmanned vehicle and drone;

[0040] S21: The unmanned vehicle uses Manhattan distance as a heuristic function, generates a possible set of candidate nodes based on the current node position, heuristic function and mobility, evaluates each node in the generated candidate node set, and selects the path with the lowest cost as the initial path;

[0041] S22: The drone uses Euclidean distance as a heuristic function, generates a possible set of candidate nodes based on the current node position, heuristic function and mobility, evaluates each node in the generated set of candidate nodes, and selects the path with the lowest cost as the initial path;

[0042] S23: During the initial path planning of the unmanned vehicle and the unmanned aerial vehicle, it is detected whether the initial path of the unmanned vehicle or the unmanned aerial vehicle occupies the same node at the same time and whether the path has a spatiotemporal overlap. If the same node is occupied at the same time or the path has a spatiotemporal overlap, it is considered a conflict, and additional constraints are added to the conflicting unmanned vehicle or unmanned aerial vehicle. The unmanned vehicle or unmanned aerial vehicle with the new constraints is returned to the initial path planning to re-plan the path until there is no conflict;

[0043] S3: Establishing a safe corridor based on the search initial path of each unmanned vehicle and drone;

[0044] Each node in the initial search path is extended in two or three dimensions until it encounters an obstacle or stops at the map boundary during the extension process, thus establishing a safe corridor;

[0045] S4: Path optimization based on the searched initial path and the established safe corridor;

[0046] S41: Establish kinematic mathematical models of unmanned vehicles and drones;

[0047] S42: defining an optimization objective function of a kinematic mathematical model, and setting constraint equations, including initial state constraints, kinematic constraints, and time constraints, and setting thresholds of optimization variables;

[0048] S43: Solve the initial path of the optimization search and the established safety corridor based on the Ipopt solver to achieve path optimization.

[0049] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A vehicle-machine collaborative task allocation and path planning method for complex environments, characterized in that: The following steps are involved: S1: Assign ground target points and aerial target points to unmanned vehicles and drones respectively, and determine the meeting point of the unmanned vehicle and drone as the end point to obtain the starting point, target point and end point information of each unmanned vehicle and drone; S2: Searching for the initial path based on the starting point, target point, and end point information of each unmanned vehicle and drone; S3: Establishing a safe corridor based on the search initial path of each unmanned vehicle and drone; S4: Path optimization based on the searched initial path and the established safe corridor.

2. The method for vehicle-machine collaborative task allocation and path planning for complex environments according to claim 1, characterized in that: In step S1, the specific steps of assigning the ground target points and the aerial target points to the unmanned vehicle and the unmanned aerial vehicle respectively include: S11: In each round, the nearest target point is assigned to the unmanned vehicle and the drone, and the positions of the unmanned vehicle and the drone are updated. In this process, if the same target point is assigned to multiple unmanned vehicles or drones at the same time, it is considered a conflict, and new constraints are added and reallocated according to the new constraints; S12: Repeat step S11 until the number of remaining target points is 0; S13: The current position of all unmanned vehicles, i.e., the ground target point, is taken as the end point; S14: According to the current positions of all drones, the nearest ground target point is assigned as the end point; S15: Repeat step S14 until all drones reach the end point.

3. The method for vehicle-machine collaborative task allocation and path planning for complex environments according to claim 1, characterized in that: The specific steps of step S2 include: S21: The unmanned vehicle uses Manhattan distance as a heuristic function, generates a possible set of candidate nodes based on the current node position, heuristic function and mobility, evaluates each node in the generated candidate node set, and selects the path with the lowest cost as the initial path; S22: The drone uses Euclidean distance as a heuristic function, generates a possible set of candidate nodes based on the current node position, heuristic function and mobility, evaluates each node in the generated set of candidate nodes, and selects the path with the lowest cost as the initial path; S23: During the initial path planning of unmanned vehicles and drones, check whether the initial paths of unmanned vehicles or drones occupy the same node at the same time and whether there is spatiotemporal overlap of the paths. If there is the same node occupied at the same time or the paths have spatiotemporal overlap, it is considered a conflict, and additional constraints are added to the conflicting unmanned vehicles or drones. The unmanned vehicles or drones with the new constraints are returned to the initial path planning to replan the path until there is no conflict.

4. The method for vehicle-machine collaborative task allocation and path planning for complex environments according to claim 1, characterized in that: The specific steps of step S3 include: Each node in the initial search path is extended in two or three dimensions until an obstacle is encountered or the map boundary is stopped during the extension process, thus establishing a safe corridor.

5. The method for vehicle-machine collaborative task allocation and path planning for complex environments according to claim 1, characterized in that: The specific steps of step S4 include: S41: Establish kinematic mathematical models of unmanned vehicles and drones; S42: defining an optimization objective function of a kinematic mathematical model, and setting constraint equations, including initial state constraints, kinematic constraints, and time constraints, and setting thresholds of optimization variables; S43: Solve the initial path of the optimization search and the established safety corridor based on the Ipopt solver to achieve path optimization.

Images