Station UAV Charging Control Method, System and Medium Based on Cooperative Communication

Abstract

The present invention discloses a method, system and medium for controlling the charging of platform drones based on collaborative communication; it relates to the technical field of drone control; through the collaborative communication between the rail platform and the drone, combined with global path planning and local path planning, high-precision positioning and docking are achieved; and the environment of the rail platform is detected in real time, the flight path of the drone is corrected in real time, the flight path of the drone is dynamically adjusted, sudden interference from moving obstacles is avoided, and accurate docking is ensured; through the collaborative communication between the rail platform and the drone, the multi-objective optimization algorithm, the collaboration of global and local path planning, and intelligent charging management, the limitations of existing drone positioning and alignment methods in complex environments such as rail transit platforms are effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle (UAV) control, and particularly to a charging control method, system and medium for UAVs at a platform based on cooperative communication. Background Art

[0002] With the rapid development of UAV technology, UAVs are increasingly widely used in fields such as logistics, inspection, and security. However, the endurance of UAVs is limited, and the charging problem has become one of the key bottlenecks restricting their large-scale application. To solve this problem, researchers have proposed a solution to provide charging services for UAVs at fixed locations such as rail transit platforms. Rail transit platforms usually have fixed infrastructure and power supply, which are suitable as charging stations for UAVs. However, the environment of rail transit platforms is complex, with dynamic obstacles (such as pedestrians, vehicles, flying animals, equipment, etc.) and electromagnetic interference, which pose severe challenges to the precise positioning and docking of UAVs.

[0003] Traditional UAV positioning and alignment methods mainly rely on the Global Positioning System (GPS) and Inertial Navigation System (INS). However, GPS signals are easily blocked and affected by multipath effects in closed or semi-closed environments such as rail transit platforms, resulting in a decrease in positioning accuracy. In addition, the inertial navigation system will generate cumulative errors after long-term operation, making it difficult to meet the high-precision docking requirements. Although technologies such as visual positioning and Light Detection and Ranging (LiDAR) have improved the positioning accuracy to a certain extent, in a dynamic environment, these technologies still have the following disadvantages:

[0004] Interference from dynamic obstacles: There are a large number of dynamic obstacles (such as moving pedestrians, flying birds, vehicles, etc.) in the environment of rail transit platforms. Traditional positioning methods are difficult to perceive and respond to these obstacles in real time, resulting in the possibility of collision or deviation from the target position during the landing of UAVs.

[0005] Environmental complexity: Rail transit platforms usually have complex structures and diverse equipment (such as signal lights, billboards, cables, etc.). These static obstacles may block the field of view of sensors, affecting the accuracy of positioning and path planning.

[0006] Electromagnetic interference: There is strong electromagnetic interference (such as the electromagnetic field generated by train operation) in the environment of rail transit platforms, which may affect the communication and sensor performance of UAVs, further reducing the positioning accuracy.

[0007] Traditional path planning and control algorithms are usually based on the assumption of a static environment and are difficult to achieve fast response and real-time adjustment in a dynamic environment, resulting in the inability of UAVs to avoid obstacles in time or respond to environmental changes during the landing process.

[0008] Traditional positioning and docking methods usually rely only on the sensors and computing capabilities of the drone itself, lacking collaborative communication with charging stations or other devices, and it is difficult to achieve high-precision docking and efficient charging management.

[0009] In summary, the existing drone positioning and alignment methods have obvious limitations in complex environments such as rail transit platforms and cannot meet the high-precision and high-reliability charging requirements. Therefore, there is an urgent need for a drone positioning and docking solution that can adapt to complex environments, sense dynamic obstacles in real time, and work in collaboration with charging stations to improve the safety and efficiency of drone charging at rail transit platforms. Summary of the Invention

[0010] The technical problem to be solved by the present invention is that the existing drone positioning and alignment methods have obvious limitations in complex environments such as rail transit platforms and cannot meet the high-precision and high-reliability charging requirements. This solution provides a charging control method, system and medium for platform drones based on collaborative communication. Through the collaborative communication between the rail transit platform and the drone, combined with global path planning and local path planning, high-precision positioning and docking are achieved; and the environment of the rail transit platform is detected in real time, the flight path of the drone is corrected in real time, the flight path of the drone is dynamically adjusted, and sudden interference from moving obstacles is avoided to ensure accurate docking; through the collaborative communication between the rail transit platform and the drone, the multi-objective optimization algorithm, the collaboration of global and local path planning, and intelligent charging management, the limitations of the existing drone positioning and alignment methods in complex environments such as rail transit platforms are effectively solved.

[0011] The present invention is realized through the following technical solutions:

[0012] This solution provides a charging control method for platform drones based on collaborative communication, including:

[0013] The drone sends a charging request and identity information to the rail transit platform; the identity information includes drone ID, mission information, battery status information, and position and attitude information;

[0014] After receiving the charging request and identity information, the rail transit platform performs idle interface matching and global path planning on the drone, and sends the idle interface matching result and the global path planning result to the drone;

[0015] The drone flies according to the global path planning result and sends position information to the rail transit station in real time. When the drone reaches the preset position, the rail transit station starts to detect the environment of the target interface area and generates a local path planning result for the target interface area according to the environment detection result;

[0016] The orbital platform compares the part of the local path planning result and the global path planning result regarding the target interface area. If they are inconsistent, the local path planning result is sent to the UAV.

[0017] After the UAV enters the target interface area, it executes the global path planning result or the local path planning result.

[0018] A further optimization solution is that the method for matching idle interfaces includes:

[0019] Obtain the identity information of the UAV requesting charging, as well as the positions and statuses of all idle interfaces of the orbital platform.

[0020] Perform multi-objective sorting on all UAVs and idle interfaces respectively, and record the sorting numbers of each UAV or idle interface under different objective sortings; the larger the sorting number, the more forward the position of the UAV; the multi-objective sorting of the UAV includes: taking a high task importance level as the goal, taking a high urgency degree of power demand as the goal, and taking a long battery usage time of the UAV as the goal; the multi-objective sorting of the idle interface includes: taking a low utilization rate of the idle interface as the goal, taking a low load of the idle interface as the goal, and taking the closest distance to the UAV as the goal.

[0021] Arbitrarily combine UAVs and idle interfaces to obtain multiple UAV and idle interface pairs, and determine the equilibrium objective values of all UAV and idle interface pairs based on the sorting numbers.

[0022] Find the Pareto optimal solution set from the multi-UAV and idle interface pairs based on the non-dominated sorting method.

[0023] Determine the final interface matching solution from the Pareto optimal solution set.

[0024] A further optimization solution is that the method for determining the equilibrium objective values of all UAV and idle interface pairs based on the sorting numbers includes:

[0025] The equilibrium objective value H of UAV i and idle interface j ij is calculated according to the following formula:

[0026] ;

[0027] where e represents the natural base; ln[] represents the logarithmic function; Z i represents the sorting number of UAV i in the sorting with a high task importance level as the goal; X i represents the sorting number of UAV i in the sorting with a high urgency degree of power demand as the goal; N represents the sum of the sorting numbers of the idle interfaces; a represents the idle interface utilization rate coefficient; Yj Denote the sorting number of the idle interface in the sorting aiming at low interface utilization rate j ; b represents the load factor of the idle interface S j Denote the sorting number of the idle interface j in the sorting aiming at low load of the idle interface; L ij Denote the sorting number of the idle interface j in the sorting aiming at the closest distance to the UAV i

[0028] The further optimization scheme is that the Pareto optimal solution set is found from the multi-UAV and idle interface pairs based on the non-dominated sorting method; the method includes:

[0029] Randomly generate an initial population, and each individual represents a possible UAV and idle interface pair

[0030] Perform non-dominated sorting on the individuals in the current population, and divide the individuals into multiple fronts; among them, the individuals in the latter front are dominated by the individuals in the former front, and the individuals in the first front are non-dominated solutions; the objective functions of the non-dominated sorting include: high task importance level, high urgency degree of power demand, long battery usage time of the UAV, low utilization rate of the idle interface, low load of the idle interface, and the closest distance between the idle interface and the UAV

[0031] Calculate the crowding degree of the individuals in each front, and select individuals for crossover and mutation operations according to non-dominated sorting and crowding degree to generate the next generation population: give priority to selecting individuals with a higher front level, and give priority to selecting individuals with a larger crowding degree in the same front

[0032] Merge the current population with the next generation population, and select the optimal individuals from them as the next generation population

[0033] Repeat the above steps until the maximum iteration number or the convergence condition is reached

[0034] The further optimization scheme is that the calculation of the crowding degree of the individuals in each front includes the method:

[0035] Obtain the multi-objective sorting results of each individual

[0036] Calculate the crowding degree of each individual based on the multi-objective sorting results

[0037] The crowding degree En of the individual n is calculated according to the following formula

[0038] ;

[0039] Among them, fmax represents the maximum equilibrium target value; fmin represents the minimum equilibrium target value; f(n + 1) represents the equilibrium target value of the individual located immediately after individual n in the multi-objective sorting result; M represents the total number of individuals in the multi-objective sorting result; f(n - 1) represents the equilibrium target value of the individual located immediately before individual n in the multi-objective sorting result.

[0040] A further optimization solution is to determine the final interface matching solution from the Pareto optimal solution set; the method includes:

[0041] Obtain the task importance levels of the UAVs in the Pareto optimal solution set;

[0042] Use the UAV with the highest task importance level and the idle interface pair as the final interface matching solution.

[0043] A further optimization solution is that the method of local path planning includes:

[0044] Obtain the starting point, the target point, and the set of obstacle points;

[0045] Initialize the Open list and the Close list;

[0046] Write the starting point into the Open list and the obstacle points into the Close list for path search:

[0047] S21, determine whether the current Open list is an empty set. If so, the iterative loop ends; otherwise, proceed to step S22;

[0048] S22, remove the node c with the smallest g(c) value from the Open list and write it into the Close list; determine whether the node c is the target point. If so, the path search ends; otherwise, proceed to step S23; where the g(c) value represents the cost estimation function for the UAV to pass through the node c from the starting point to the target point;

[0049] S23, determine whether the node c has new child nodes. If so, use the coordinates obtained by advancing a step vector along the UAV's traveling direction from the new child nodes as the obstacle; write the new child nodes without the obstacle in the obstacle point set into the Open list, write the new child nodes with the obstacle in the obstacle point set into the Close list, and return to step S21.

[0050] A further optimization solution is that the method for determining the step vector includes:

[0051] Obtain the volume and moving direction of the obstacle;

[0052] Determine the size Dm of the step vector according to the volume of the obstacle:

[0053] ;

[0054] D = KVz / V;

[0055] Wherein, D represents the reference size; K represents the product of the maximum width and the minimum width of the projection shape of the obstacle, Dmin represents the minimum width of the projection shape of the obstacle; Vz represents the volume of the obstacle; V represents the volume of the target interface area;

[0056] Determine the direction of the stepping vector according to the moving direction of the obstacle: the angle between the direction of the stepping vector and the direction when the UAV enters the target interface area is less than 90°, and the angle between the direction of the stepping vector and the moving direction of the obstacle is greater than 90°.

[0057] This solution also provides a charging control system for a platform UAV based on cooperative communication, which is used to implement the above-mentioned charging control method for a platform UAV based on cooperative communication. The system includes:

[0058] A first communication module, which is used to enable the UAV to send a charging request and identity information to the rail platform; the identity information includes the UAV ID, mission information, battery status information, and position and attitude information;

[0059] A calculation module, which is used to perform idle interface matching and global path planning on the UAV after the rail platform receives the charging request and identity information, and send the idle interface matching result and the global path planning result to the UAV; the UAV flies according to the global path planning result and sends position information to the rail station in real time;

[0060] A real-time detection module, which is used to start environmental detection of the target interface area by the rail station when the UAV reaches a preset position, and generate a local path planning result of the target interface area according to the environmental detection result;

[0061] A comparison module, which is used to compare the local path planning result with the part of the global path planning result regarding the target interface area by the rail platform. If they are inconsistent, the local path planning result is sent to the UAV;

[0062] An execution module, which is used to implement the global path planning result or the local path planning result after the UAV enters the target interface area.

[0063] This solution also provides a computer-readable medium, on which a computer program is stored. The computer program can be executed by a processor to implement the above-mentioned charging control method for a platform UAV based on cooperative communication.

[0064] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0065] 1. This solution provides a charging control method, system, and medium for platform UAVs based on cooperative communication. Through the cooperative communication between the rail platform and the UAV, combined with global path planning and local path planning, high-precision positioning and docking are achieved; and the environment of the rail platform is detected in real time, the flight path of the UAV is corrected in real time, the flight path of the UAV is dynamically adjusted, and sudden interference from moving obstacles is avoided to ensure precise docking.

[0066] 2. This solution provides a charging control method, system, and medium for platform UAVs based on cooperative communication. Through the cooperative communication between the rail platform and the UAV, the multi-objective optimization algorithm, the cooperation of global and local path planning, and intelligent charging management, the limitations of existing UAV positioning and alignment methods in complex environments such as rail transit platforms are effectively solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] To more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following will briefly introduce the drawings required in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and thus should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts. In the drawings:

[0068] Figure 1 is a schematic flow chart of the charging control method for platform UAVs based on cooperative communication;

[0069] Figure 2 is a schematic structural diagram of the charging control system for platform UAVs based on cooperative communication. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0070] To make the purpose, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the embodiments and the drawings. The illustrative embodiments and descriptions of the present invention are only used to explain the present invention and do not limit the present invention.

[0071] Existing UAV positioning and alignment methods have obvious limitations in complex environments such as rail transit platforms and cannot meet the high-precision and high-reliability charging requirements; in view of this, this solution provides the following embodiments to solve the above technical problems:

[0072] Embodiment 1: This embodiment provides a charging control method for platform UAVs based on cooperative communication, as Figure 1 shown, including:

[0073] Step 1: The UAV sends a charging request and identity information to the rail platform; the identity information includes the UAV ID, mission information, battery status information, and position and attitude information.

[0074] Step 2: After receiving the charging request and identity information, the orbital platform performs idle interface matching and global path planning for the UAV, and sends the idle interface matching result and the global path planning result to the UAV;

[0075] In this step, the method of idle interface matching includes:

[0076] S201, obtain the identity information of the UAV requesting charging, as well as the positions and statuses of all idle interfaces of the orbital platform;

[0077] S202, perform multi-objective sorting on all UAVs and idle interfaces respectively, and record the sorting numbers of each UAV or idle interface under different objective sortings; the larger the sorting number, the more forward the position of the UAV; the multi-objective sorting of the UAVs includes: aiming at high task importance level, aiming at high urgency of power demand, and aiming at long battery usage time of the UAV; the multi-objective sorting of the idle interfaces includes: aiming at low utilization rate of the idle interface, aiming at low load of the idle interface, and aiming at the closest distance to the UAV;

[0078] S203, obtain multiple UAV and idle interface pairs by arbitrarily combining UAVs and idle interfaces, and determine the equilibrium objective values of all UAV and idle interface pairs based on the sorting numbers; the specific method of this step includes:

[0079] The equilibrium objective value H of UAV i and idle interface j ij is calculated according to the following formula:

[0080] ;

[0081] where e represents the natural base; ln[] represents the logarithmic function; Z i represents the sorting number of UAV i in the sorting aiming at high task importance level; X i represents the sorting number of UAV i in the sorting aiming at high urgency of power demand; N represents the sum of the sorting numbers of the idle interfaces; a represents the idle interface utilization rate coefficient; Y j represents the sorting number of idle interface j in the sorting aiming at low utilization rate of the interface; b represents the idle interface load coefficient; S j represents the sorting number of idle interface j in the sorting aiming at low load of the idle interface; L ij represents the sorting number of idle interface j in the sorting aiming at the closest distance to UAV i.

[0082] S204. Find the Pareto optimal solution set from multiple UAVs and idle interface pairs based on the non - dominated sorting method; the specific steps of this method are as follows:

[0083] S2041. Randomly generate an initial population, where each individual represents a possible UAV and idle interface pair;

[0084] S2042. Perform non - dominated sorting on the individuals in the current population and divide the individuals into multiple fronts; among them, the individuals in the latter front are dominated by the individuals in the previous front, and the individuals in the first front are non - dominated solutions; the objective functions for non - dominated sorting include: high task importance level, high urgency degree of power demand, long battery usage time of UAVs, low utilization rate of idle interfaces, low load of idle interfaces, and the closest distance between the idle interface and the UAV;

[0085] S2043. Calculate the crowding degree of individuals in each front, and select individuals for crossover and mutation operations according to non - dominated sorting and crowding degree to generate the next generation population: preferentially select individuals with a higher front level, and within the same front, preferentially select individuals with a larger crowding degree; the method for calculating the crowding degree of individuals in each front includes:

[0086] Obtain the multi - objective sorting results of each individual;

[0087] Calculate the crowding degree of each individual based on the multi - objective sorting results:

[0088] The crowding degree En of individual n is calculated according to the following formula:

[0089] ;

[0090] where fmax represents the maximum equilibrium objective value; fmin represents the minimum equilibrium objective value; f(n + 1) represents the equilibrium objective value of the individual located after individual n in the multi - objective sorting result; M represents the total number of individuals in the multi - objective sorting result; f(n - 1) represents the equilibrium objective value of the individual located before individual n in the multi - objective sorting result.

[0091] S2044. Combine the current population and the next generation population, and select the optimal individuals from them as the next generation population;

[0092] S2045. Repeat the above steps until the maximum number of iterations or the convergence condition is reached.

[0093] S205. Determine the final interface matching solution from the Pareto optimal solution set; the specific steps of this method are as follows:

[0094] Obtain the task importance levels of each UAV in the Pareto optimal solution set;

[0095] Take the UAV and idle interface pair with the highest task importance level as the final interface matching solution.

[0096] Global path planning mainly refers to planning an optimal or sub-optimal path from the starting point to the ending point for the UAV in the case of a known environmental map, starting point, and ending point. Global path planning methods usually rely on the static information of the environmental map and do not consider dynamic obstacles; path planning methods based on search can find the optimal or sub-optimal path from the starting point to the ending point by searching for feasible paths in the environmental map; or path planning methods based on mathematical optimization can generate the optimal path; and path planning methods based on graph search represent the environmental map as a graph structure and generate a path through graph search algorithms, etc.

[0097] Step 3: The UAV flies according to the global path planning result and sends position information to the orbital station in real time. When the UAV reaches the preset position, the orbital station starts environmental detection of the target interface area and generates a local path planning result for the target interface area according to the environmental detection result;

[0098] In this step, the preset position mainly refers to starting to enter the target interface area, which is mainly the spatial area where the UAV starts to align with the target charging interface.

[0099] The method of the local path planning includes:

[0100] Obtain the starting point, target point, and obstacle point set;

[0101] Initialize the Open list and Close list;

[0102] Write the starting point into the Open list and the obstacle points into the Close list for path search:

[0103] S21, judge whether the current Open list is an empty set. If so, the loop iteration ends; otherwise, go to step S22;

[0104] S22, remove the node c with the smallest g(c) value in the Open list and write it into the Close list; judge whether the node c is the target point. If so, the path search ends; otherwise, go to step S23; where the g(c) value represents the cost estimation function of the UAV from the starting point passing through the node c to the target point; the g(c) value is set according to the actual situation;

[0105] S23, whether the node c has new child nodes. If so, use the coordinates of the new child node advancing one step vector along the UAV's traveling direction as the obstacle; write the new child node without the obstacle in the obstacle point set into the Open list, write the new child node with the obstacle in the obstacle point set into the Close list, and return to step S21.

[0106] The method for determining the step vector includes:

[0107] Obtain the volume and moving direction of the obstacle;

[0108] Determine the magnitude Dm of the step vector according to the volume of the obstacle:

[0109] ;

[0110] D = KVz / V;

[0111] where D represents the reference size; K represents the product of the maximum width and the minimum width of the projected shape of the obstacle, Dmin represents the minimum width of the projected shape of the obstacle; Vz represents the volume of the obstacle; V represents the volume of the target interface area;

[0112] Determine the direction of the step vector according to the moving direction of the obstacle: The included angle between the direction of the step vector and the direction when the UAV enters the target interface area is less than 90°, and the included angle between the direction of the step vector and the moving direction of the obstacle is greater than 90°.

[0113] This solution effectively solves the problem of the UAV colliding with surrounding moving obstacles when aligning with the track charging interface by setting up an obstacle detection process and integrating it with the traditional A* algorithm. The traditional A* algorithm only performs path planning based on a static environment map and cannot handle the interference of dynamic obstacles (such as pedestrians, birds, vehicles), which may cause the UAV to collide during the alignment flight. This solution can sense dynamic obstacles in the surrounding environment in real time through the obstacle detection process, incorporate obstacle information into the path planning of the A* algorithm, dynamically adjust the flight path, ensure that the UAV avoids moving obstacles, and significantly improve the flight safety of the UAV in a complex environment. This solution effectively solves the problem of the UAV colliding with surrounding moving obstacles when aligning with the track charging interface by setting up an obstacle detection process and integrating it with the traditional A* algorithm. Compared with the existing technology, this solution has significant advantages such as improving the safety of path planning, enhancing the environmental adaptability, optimizing the real-time performance, improving the alignment accuracy and success rate, reducing the collision risk and maintenance cost, supporting multi-UAV collaborative operations, and realizing intelligence and automation. These beneficial effects enable this solution to meet the high-precision and high-reliability requirements of UAV charging in a complex environment and provide strong technical support for the application of UAVs in scenarios such as rail transit platforms.

[0114] Step 4: The rail platform compares the part related to the target interface area in the local path planning result and the global path planning result. If they are inconsistent, send the local path planning result to the UAV;

[0115] Step 5: After the UAV enters the target interface area, execute the global path planning result or the local path planning result.

[0116] Embodiment 2: This embodiment provides a platform UAV charging control system based on collaborative communication for implementing the platform UAV charging control method based on collaborative communication described in Embodiment 1. The system includes:

[0117] A first communication module for enabling the UAV to send a charging request and identity information to the rail platform; the identity information includes the UAV ID, mission information, battery status information, and position and attitude information;

[0118] A calculation module for, after the rail platform receives the charging request and identity information, performing idle interface matching and global path planning on the UAV, and sending the idle interface matching result and the global path planning result to the UAV; the UAV flies according to the global path planning result and sends position information to the rail station in real time;

[0119] A real-time detection module for, when the UAV reaches a preset position, the rail station starts to perform environmental detection on the target interface area and generates a local path planning result for the target interface area according to the environmental detection result;

[0120] A comparison module for the rail platform to compare the part of the local path planning result and the global path planning result regarding the target interface area. If they are inconsistent, the local path planning result is sent to the UAV;

[0121] An execution module for enabling the UAV to execute the global path planning result or the local path planning result after entering the target interface area.

[0122] Embodiment 3: This embodiment provides a computer-readable medium with a computer program stored thereon. The computer program, when executed by a processor, can implement the platform UAV charging control method based on collaborative communication described in Embodiment 1; specifically, the following steps are implemented:

[0123] Step 1: The UAV sends a charging request and identity information to the rail platform; the identity information includes the UAV ID, mission information, battery status information, and position and attitude information;

[0124] Step 2: After the rail platform receives the charging request and identity information, it performs idle interface matching and global path planning on the UAV, and sends the idle interface matching result and the global path planning result to the UAV;

[0125] Step 3: The UAV flies according to the global path planning result and sends position information to the rail station in real time. When the UAV reaches a preset position, the rail station starts to perform environmental detection on the target interface area and generates a local path planning result for the target interface area according to the environmental detection result;

[0126] Step 4: The orbital platform compares the part of the local path planning result and the global path planning result regarding the target interface area. If they are inconsistent, the local path planning result is sent to the UAV.

[0127] Step 5: After the UAV enters the target interface area, it executes the global path planning result or the local path planning result.

[0128] The specific implementation manners described above further elaborate on the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above are only specific implementation manners of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention shall be included in the protection scope of the present invention.

Claims

1. A charging control method for a platform UAV based on collaborative communication, characterized in that Including: The UAV sends a charging request and identity information to the orbital platform; The identity information includes the UAV ID, mission information, battery status information, and position and attitude information; After receiving the charging request and identity information, the orbital platform performs idle interface matching and global path planning on the UAV, and sends the idle interface matching result and the global path planning result to the UAV; The UAV flies according to the global path planning result and sends position information to the orbital station in real time. When the UAV reaches the preset position, the orbital station starts environmental detection of the target interface area and generates a local path planning result for the target interface area according to the environmental detection result; The orbital platform compares the local path planning result with the part of the global path planning result regarding the target interface area. If they are inconsistent, it sends the local path planning result to the UAV; After the UAV enters the target interface area, it executes the global path planning result or the local path planning result; Among them, the method of the idle interface matching includes: Obtaining the identity information of the UAV requesting charging, as well as the positions and statuses of all idle interfaces of the orbital platform; Performing multi-objective sorting on all UAVs and idle interfaces respectively, and recording the sorting numbers of each UAV or idle interface under different objective sortings; the larger the sorting number, the more forward the position of the UAV; the multi-objective sorting of the UAV includes: aiming at a high mission importance level, aiming at a high degree of urgency of power demand, and aiming at a long battery usage time of the UAV; the multi-objective sorting of the idle interface includes: aiming at a low utilization rate of the idle interface, aiming at a low load of the idle interface, and aiming at being the closest to the UAV; Randomly combining UAVs and idle interfaces to obtain multiple UAV and idle interface pairs, and determining the equilibrium objective values of all UAV and idle interface pairs based on the sorting numbers; Finding the Pareto optimal solution set from the multi-UAV and idle interface pairs based on the non-dominated sorting method; Determining the final interface matching solution from the Pareto optimal solution set; The method for determining the equilibrium objective values of all UAV and idle interface pairs based on the sorting numbers; includes the method: The equilibrium target value H of the drone i and the idle interface j ij Calculated according to the following formula: ； Among them, e represents the natural base; ln[] represents the logarithmic function; Z i represents the sorting number of the UAV in the sorting aiming at a high task importance level i ; X i represents the sorting number of UAV i in the sorting aiming at a high urgency degree of power demand; N represents the sum of the sorting numbers of the idle interfaces; a represents the utilization rate coefficient of the idle interfaces; Y j represents the sorting number of the idle interfaces in the sorting aiming at a low utilization rate of the interfaces j ; b represents the load coefficient of the idle interfaces; S j represents the sorting number of the idle interface j in the sorting aiming at a low load of the idle interfaces; L ij represents the sorting number of the idle interface j in the sorting aiming at being the closest to UAV i; The method for finding the Pareto optimal solution set from the multi-UAV and idle interface pairs based on the non-dominated sorting method; includes the method: Randomly generating an initial population, and each individual represents a possible UAV and idle interface pair; Performing non-dominated sorting on the individuals in the current population, and dividing the individuals into multiple fronts; among them, the individuals in the latter front are dominated by the individuals in the former front, and the individuals in the first front are non-dominated solutions; among them, the objective function of the non-dominated sorting includes: high mission importance level, high degree of urgency of power demand, long battery usage time of the UAV, low utilization rate of the idle interface, low load of the idle interface, and the idle interface being the closest to the UAV; Calculating the crowding degree of the individuals in each front, and selecting individuals for crossover and mutation operations according to the non-dominated sorting and crowding degree to generate the next generation population: preferentially selecting individuals with a high front level, and preferentially selecting individuals with a large crowding degree in the same front; Merging the current population with the next generation population, and selecting the optimal individuals from them as the next generation population; Repeating the above steps until the maximum number of iterations or the convergence condition is reached; Calculating the crowding degree of individuals in each front includes the following method: Obtaining the multi-objective sorting results of each individual; Calculating the crowding degree of each individual based on the multi-objective sorting results: The crowding degree En of individual n is calculated according to the following formula: ； where fmax represents the maximum equilibrium objective value; fmin represents the minimum equilibrium objective value; f(n + 1) represents the equilibrium objective value of the individual located immediately after individual n in the multi-objective sorting results; M represents the total number of individuals in the multi-objective sorting results; f(n - 1) represents the equilibrium objective value of the individual located immediately before individual n in the multi-objective sorting results.

2. The method for controlling the charging of a platform UAV based on collaborative communication according to claim 1, wherein, Determining the final interface matching solution from the Pareto optimal solution set; Including the method: Obtaining the task importance levels of each unmanned aerial vehicle in the Pareto optimal solution set; Taking the unmanned aerial vehicle with the highest task importance level and the idle interface pair as the final interface matching solution.

3. The method for controlling the charging of a platform UAV based on collaborative communication according to claim 1, wherein The method for local path planning includes: Obtaining the starting point, the target point, and the set of obstacle points; Initializing the Open list and the Close list; Writing the starting point into the Open list and the obstacle points into the Close list for path search: S21, judging whether the current Open list is an empty set. If so, the loop iteration ends; otherwise, proceed to step S22; S22, removing the node c with the minimum g(c) value from the Open list and writing it into the Close list; judging whether the node c is the target point. If so, the path search ends; otherwise, proceed to step S23; where the g(c) value represents the cost estimation function of the unmanned aerial vehicle passing through the node c from the starting point to the target point; S23, judging whether the node c has new child nodes. If so, taking the coordinates of the new child nodes advanced by one step vector along the moving direction of the unmanned aerial vehicle as the obstacle; writing the new child nodes without the obstacle in the obstacle point set into the Open list, writing the new child nodes with the obstacle in the obstacle point set into the Close list, and returning to step S21.

4. The method for controlling the charging of a platform UAV based on collaborative communication according to claim 3, wherein The method for determining the step vector includes: Obtaining the volume and moving direction of the obstacle; Determining the size Dm of the step vector according to the volume of the obstacle: ； ； where D represents the reference size; K represents the product of the maximum width and the minimum width of the projected shape of the obstacle; Dmin represents the minimum width of the projected shape of the obstacle; Vz represents the volume of the obstacle; V represents the volume of the target interface area; Determining the direction of the step vector according to the moving direction of the obstacle: the angle between the direction of the step vector and the direction when the unmanned aerial vehicle enters the target interface area is less than 90°, and the angle between the direction of the step vector and the moving direction of the obstacle is greater than 90°.

5. The platform UAV charging control system based on collaborative communication is characterized in that For implementing the method for controlling the charging of a platform unmanned aerial vehicle based on cooperative communication according to any one of claims 1 - 4, the system includes: A first communication module for enabling the unmanned aerial vehicle to send a charging request and identity information to the rail platform; the identity information includes the unmanned aerial vehicle ID, task information, battery status information, and position and attitude information; A calculation module, which is configured to, after the orbital platform receives a charging request and identity information, perform idle interface matching and global path planning for the drone, and send the idle interface matching result and the global path planning result to the drone; the drone flies according to the global path planning result and sends position information to the orbital station in real time; A real-time detection module, which is configured to, when the drone reaches a preset position, the orbital station starts to perform environmental detection on the target interface area, and generate a local path planning result for the target interface area according to the environmental detection result; A comparison module, which is configured to compare the part of the local path planning result and the global path planning result regarding the target interface area by the orbital platform. If they are inconsistent, the local path planning result is sent to the drone; An execution module, which is configured to enable the drone to execute the global path planning result or the local path planning result after entering the target interface area.

6. A computer-readable medium having a computer program stored thereon, characterized in that, The computer program, when executed by a processor, can implement the method for controlling the charging of a drone at a platform based on cooperative communication as described in any one of claims 1-4.

Images