Path planning method, device and equipment based on multi-target unmanned aerial vehicle, and storage medium

Abstract

The invention discloses a path planning method, device and equipment based on a multi-target unmanned aerial vehicle, and a storage medium, and the method comprises the steps: collecting the geographic information data of an inspection region, building a planning path database according to the collected data, and carrying out the preprocessing and optimization of the data; solving an unmanned aerial vehicle path planning model based on a particle swarm algorithm according to maneuvering characteristics, safety constraint conditions and routing inspection target priorities of unmanned aerial vehicle flight; unconventional obstacles are detected in real time based on an unmanned aerial vehicle visual system, and local safety adjustment of a path is achieved; and the updated path is synchronously sent to a remote client, and path evaluation and manual intervention are carried out. According to the method, the flight duration, the path smoothness and the path effectiveness are comprehensively considered, the method can adapt to complex environments and inspection requirements, the particle swarm optimization and the binocular distance measurement technology are comprehensively applied, the intelligence and the real-time performance of path planning are improved, the flight risk is reduced, and the safe work of the inspection requirements of the unmanned aerial vehicle is guaranteed.

Description

Technical Field

[0001] The present invention relates to a method, a device, a equipment and a storage medium based on multi-target unmanned aerial vehicle path planning, and belongs to the technical field of unmanned aerial vehicle inspection. Background Art

[0002] With the rapid development of drone technology in various fields, such as logistics distribution, agricultural plant protection, environmental monitoring and other related applications, it has also injected new blood into the power grid industry. Traditionally, the inspection and maintenance of power facilities usually require manual operation, which is not only time-consuming and labor-intensive, but also has certain safety risks. As an autonomous flying robot system, drones have the advantages of strong mobility, high reliability and low cost. They can effectively replace manual inspection, maintenance and monitoring of power facilities; at the same time, path planning is the key to ensure that drones can complete tasks efficiently and safely during execution.

[0003] Path planning is of great significance in UAV applications. Reasonable path planning can enable UAVs to visit all target points in the shortest path during the mission execution, thereby improving mission efficiency, reducing energy consumption and reducing flight time. In addition, path planning also needs to consider the topological structure and safety constraints of power facilities to ensure that UAVs avoid obstacles and comply with flight restrictions during flight to ensure the smooth completion of the mission. At present, the methods of UAV path planning have achieved remarkable research results. The main methods include graph search algorithms, heuristic algorithms, intelligent optimization algorithms and artificial intelligence algorithms. By comprehensively considering the energy efficiency, safety, optimal path and other issues existing in the UAV flight process, the execution efficiency and safety of the task are improved, and more intelligent and efficient path planning is achieved. At the same time, considering that UAV tasks often involve multiple target points in practical applications, traditional single-target path planning methods cannot meet the needs of multi-target tasks well. In the prior art, some proposed multi-target UAV path planning methods still have some problems. Some methods only consider the optimality of a single target and ignore the importance of other targets, resulting in poor comprehensive performance of the path planning results; while some methods fix the trade-off relationship between targets when considering multiple targets, and cannot flexibly adapt to different task requirements and priorities. Summary of the invention

[0004] In response to the problems existing in the above-mentioned prior art, the present invention provides a method, device, equipment and storage medium based on multi-objective UAV path planning, taking into account the complexity of UAV route planning, and comprehensively considering the maximum flight time and minimum path length while ensuring safe flight. Taking into account that the computing power of three-dimensional environment modeling cannot keep up with the real-time requirements, the preset auxiliary route is dynamically adjusted according to flight requirements to ensure the efficiency and high quality of the inspection path.

[0005] A first aspect of the present invention provides a method for multi-target UAV path planning, comprising the following steps:

[0006] S1. Collect geographic information data of the inspection area, establish a planning path database based on the collected data, and pre-process and optimize the data;

[0007] S2. According to the maneuverability characteristics, safety constraints and inspection target priorities of the UAV flight, the UAV path planning model is solved based on the particle swarm algorithm;

[0008] S3, based on the UAV vision system, real-time detection of unconventional obstacles can be achieved to achieve local safety adjustments to the path;

[0009] S4. The updated path is synchronously sent to the remote client for path evaluation and manual intervention.

[0010] In combination with the first aspect, the maneuverability characteristics in the above step S2 include the flight speed, minimum step length, maximum yaw angle and maximum flight time of the drone:

[0011]

[0012] Among them, v t is the flight speed of the UAV at time t, v max is the maximum flight speed of the UAV, S step is the minimum step length of the drone, f(θ (t+1)-t ) is the difference in deflection angle from time t to time t+1, θ max is the maximum deviation angle between adjacent waypoints of the UAV, T is the flight time of the UAV, and E B is the current battery power of the drone, η dc is the conversion efficiency of the drone battery discharge, F UAV is the pulling force of the drone, f w is the friction force of wind.

[0013] In combination with the first aspect, the safety constraint condition in the above step S2 is a dynamic random obstacle threat:

[0014] d min ≤d UAV-obs ;

[0015] Among them, d UAV-obs is the distance between the drone and the obstacle, d min is the minimum safe distance between the drone and obstacles.

[0016] In combination with the first aspect, the inspection target priority in the above step S2 is based on the current flight range of the drone, and the inspection target with the highest priority is selected as the required waypoint for this path planning, and the inspection target with the next highest priority is selected as the auxiliary waypoint for this inspection requirement.

[0017] In combination with the first aspect, in the above step S2, the UAV path planning model is solved based on the particle swarm algorithm, and the fitness function solved by the particle swarm algorithm is set from multiple aspects such as flight time, path smoothness and path effectiveness, and the dynamic random obstacle threat, minimum step length and standby time are used as the constraint conditions for path planning. Among them, the multi-objective fitness function F fitness It is expressed as:

[0018] F fitness =αf(t)+βf(θ)+δf(l);

[0019] Among them, α, β, and δ are the weight coefficients of the flight time f(t), path smoothness f(θ), and path effectiveness f(l), respectively.

[0020] In combination with the first aspect, the above step S3 specifically includes:

[0021] S301, the UAV performs target inspection on the preset path, and at the same time, the camera equipment based on the visual system completes the recording of inspection requirements and the monitoring of the real-time flight environment, and analyzes the safety and feasibility of the current path planning based on the real-time monitoring data;

[0022] S302: If it is determined that there is no obstacle threat on the current flight path, perform inspection according to the planned path;

[0023] If the monitoring data determines that the current path needs to be dynamically adjusted, the distance and direction of the obstacle are calculated based on the binocular camera carried by the drone, and a new local path plan is generated based on the trained particle swarm algorithm to meet the drone's inspection objectives and flight safety;

[0024] S303: Apply the adjusted path to the drone and send it to the drone remote client system synchronously to update this path and evaluate whether the new solution meets the inspection requirements.

[0025] In combination with the first aspect, the above step S4 specifically includes:

[0026] S401. Design and write remote client APP software to transmit image data collected during drone inspection, remotely monitor the current location of the drone, inspection targets, and planning path information;

[0027] S402, the drone connects to the path planning database and obtains the preset path and the local dynamically adjusted new path plan in real time;

[0028] S403, providing a user interface to allow the user to manually adjust and intervene in the inspection path in real time, and send human control instructions to the UAV remote client to achieve remote adjustment.

[0029] A second aspect of the present invention provides a device based on multi-target UAV path planning, which is used to implement a method based on multi-target UAV path planning, including:

[0030] The data collection and processing module is used to collect geographic information data of the inspection area, establish a planning path database based on the collected data, and pre-process and optimize the data;

[0031] The UAV path planning module is used to solve the UAV path planning model based on the particle swarm algorithm according to the UAV flight maneuverability, safety constraints and inspection target priority;

[0032] The adjustment module is used to detect unconventional obstacles in real time based on the UAV vision system and realize local safety adjustment of the path;

[0033] The path evaluation and intervention module is used to update the path synchronously and send it to the remote client to perform path evaluation and manual intervention. A third aspect of the present invention provides a device based on multi-target UAV path planning, including: a processor;

[0034] And a memory coupled to the processor, for storing instructions, wherein when the instructions are executed by the processor, the processor executes a method based on multi-target UAV path planning.

[0035] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method based on multi-target UAV path planning are implemented.

[0036] Compared with the prior art, the beneficial effects of the present invention include:

[0037] 1. The use of drones to replace traditional manual inspection and maintenance work saves manpower, material resources and other related resources. It has the ability to preset paths and dynamically adjust paths locally. It can safely access inspection targets of different demand levels through the best path, reducing flight costs and improving work efficiency.

[0038] 2. The UAV path planning of the present invention comprehensively considers flight duration, path smoothness and path effectiveness, can adapt to complex environments and inspection needs, and comprehensively applies particle swarm algorithm and binocular ranging technology to improve the intelligence and real-time performance of path planning, reduce flight risks, and ensure the safety of UAV inspection needs.

[0039] 3. The remote client of the present invention can provide data transmission, remote monitoring and control functions. The operator can obtain the location and path plan of the drone in real time through the client, and perform manual intervention in a timely manner according to inspection requirements, thereby enhancing the simplicity and operability of drone management. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1 It is a schematic diagram of the method flow of the present invention;

[0042] Figure 2 A schematic diagram of the safety adjustment process of the present invention;

[0043] Figure 3 A schematic diagram of the process of updating the pathway and evaluating and intervening for the present invention;

[0044] Figure 4 It is a schematic diagram of the structure of the device of the present invention;

[0045] Figure 5 It is a schematic diagram of the structure of the device of the present invention. DETAILED DESCRIPTION

[0046] In order to make the objectives, technical solutions and advantages of the present invention more clear, the technical solutions of the present application are described in detail below with the help of accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solutions of the present application, rather than limitations on the technical solutions of the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0047] Example 1

[0048] A power company needs to regularly inspect its high-voltage transmission lines across mountainous areas to check whether the lines are worn, broken or have other potential safety hazards. Since transmission lines are often distributed in areas with complex terrain and few people, the traditional ground manual inspection method is inefficient and has safety hazards. Therefore, an autonomous inspection system for unmanned aerial vehicles based on the present invention is used to improve inspection efficiency and safety. In view of the advance planning of routes at the work site and the possible presence of dynamic obstacles, after the operator enters the starting position of the inspection location and releases the drone, the drone automatically flies from the starting location to the top of the transmission tower, adjusts the drone's attitude, and flies according to the preset planned route. When dynamic obstacles are found, local adjustments are made to the obstacle avoidance route, and information is exchanged with the remote client in a timely manner to complete the inspection of high-voltage transmission lines.

[0049] Combination Figure 1 As shown, a method based on multi-objective UAV path planning includes the following steps:

[0050] S1. Collect geographic information data of the inspection area, including starting point, target location, obstacle data, etc., establish a planning path database based on the collected data, and pre-process and optimize the data;

[0051] S2, considering the maneuverability characteristics, safety constraints and inspection target priorities of the UAV flight, design and implement path planning based on the particle swarm algorithm;

[0052] The maneuverability characteristics include the flight speed, minimum step length, maximum yaw angle, and maximum flight time of the drone:

[0053]

[0054] Among them, v t is the flight speed of the UAV at time t, v max is the maximum flight speed of the UAV, S step is the minimum step length of the drone, f(θ (t+1)-t ) is the difference in deflection angle from time t to time t+1, θ max is the maximum deviation angle between adjacent waypoints of the UAV, T is the flight time of the UAV, and E B is the current battery power of the drone, η dc is the conversion efficiency of the drone battery discharge, F UAV is the pulling force of the drone, f w is the friction force of wind;

[0055] The safety constraints are mainly dynamic random obstacle threats:

[0056] d min ≤d UAV-obs ;

[0057] Among them, d UAV-obs ,d min is the distance between the drone and the obstacle, and the minimum safe distance;

[0058] The inspection target priority is based on the current flight range of the UAV, and the inspection target with the highest priority is selected as the required waypoint for this path planning, and the inspection target with the second highest priority is selected as the auxiliary waypoint for this inspection requirement. Specifically, the inspection target set is R = {r1, r2, ..., r n}, each inspection target r i There is a priority value P(r i );

[0059] Assume that the UAV can fly a range of D = v t ×T, inspection target r i The distance to the current position is d(r i );

[0060] Define the selection function K(r i ):

[0061] When K(r i )=1, r i Selected as a required waypoint for this route planning; otherwise, it is not a required waypoint.

[0062] Similarly, for auxiliary waypoints, define an auxiliary selection function:

[0063]

[0064] When A(r i )=1, r i Selected as an auxiliary waypoint for this path planning; if not, it is not an auxiliary waypoint.

[0065] Among them, the priority value P(r i ) is given according to the importance and urgency of the inspection target, and the distance d(r i ) is calculated based on the coordinate position distance.

[0066] The particle swarm algorithm is used to solve the UAV path planning model. The fitness function of the particle swarm algorithm is set from multiple aspects, including flight time, path smoothness, and path effectiveness. Dynamic random obstacle threats, minimum step length, and standby time are used as constraint conditions for path planning. The multi-objective fitness function F fitness It is expressed as:

[0067] F fitness =αf(t)+βf(θ)+δf(l);

[0068] Among them, α, β, and δ are the weight coefficients of flight time f(t), path smoothness f(θ), and path effective value f(l), respectively;

[0069] The present invention uses a particle swarm algorithm to solve a multi-objective path planning model for a UAV, wherein the objective in the multi-objective path planning model is the final optimal path to be solved; in order to better use the algorithm to solve the planning model, it is quantified into a mathematical relationship, and the "multi-objective" is reflected in the total cost of the three parts of the UAV dynamic obstacle threat cost, step length cost and standby time cost, which is quantified into the minimum cost (multi-objective fitness function) as the objective of solving the optimal path model;

[0070] In the algorithm solving process, the planned path and the flight parameters of the UAV need to meet the path safety and flight requirements, as well as the inspection priority designed in combination with the application direction; the path planning model of the present invention is to build a model with the goal of minimizing the cost and the constraints of path safety and flight requirements. Based on the search mechanism of the particle swarm algorithm, under the premise of satisfying the path safety and flight requirements as constraints, it continuously searches for the value that minimizes the multi-objective fitness function (that is, the optimal path);

[0071] S3, based on the UAV vision system, avoid unconventional obstacles in real time and achieve local safety adjustments, such as Figure 2 As shown, it also includes:

[0072] S301, the UAV performs target inspection on the preset path, and at the same time completes the recording of inspection requirements and the monitoring of the real-time flight environment based on the camera equipment, and analyzes the safety and feasibility of the current path planning based on the real-time monitoring data;

[0073] S302: If it is determined that there is no obstacle threat on the current flight path, the inspection is carried out according to the planned path; if the monitoring data determines that the current path needs to be dynamically adjusted, the distance and direction of the obstacle are calculated according to the binocular camera carried by the drone, and a new local path plan is generated based on the trained particle swarm algorithm to meet the inspection objectives and flight safety of the drone;

[0074] S303, applying the adjusted path to the drone and synchronously sending it to the drone remote client, updating this path, and evaluating whether the new solution meets the inspection requirements;

[0075] S4, the updated path is synchronously sent to the remote client for path evaluation and manual intervention, e.g. Figure 3 As shown, it also includes:

[0076] S401. Design and write remote client APP software to transmit image data collected during drone inspection, remotely monitor the current location of the drone, inspection targets, planned paths and other information;

[0077] S402, the drone connects to the path planning database and obtains the preset path and the local dynamically adjusted new path plan in real time;

[0078] S403, providing a user interface to allow the user to manually adjust and intervene in the inspection path in real time, and send human control instructions to the UAV remote client to achieve remote adjustment.

[0079] The UAV path planning of the present invention comprehensively considers flight duration, path smoothness and path effectiveness, can adapt to complex environments and inspection needs, and comprehensively applies particle swarm algorithm and binocular ranging technology to improve the intelligence and real-time performance of path planning, reduce flight risks, and ensure the safety of UAV inspection needs.

[0080] Example 2

[0081] Combination Figure 4 As shown, a device based on multi-target UAV path planning is used to implement the method based on multi-target UAV path planning described in Example 1, including:

[0082] The data collection and processing module 51 is used to collect geographic information data of the inspection area, establish a planning path database based on the collected data, and pre-process and optimize the data;

[0083] The UAV path planning module 52 is used to solve the UAV path planning model based on the particle swarm algorithm according to the UAV flight maneuverability, safety constraints and inspection target priority;

[0084] An adjustment module 53, used to detect unconventional obstacles in real time based on the UAV vision system and realize local safety adjustment of the path;

[0085] The path evaluation and intervention module 54 is used to update the path synchronously and send it to the remote client to perform path evaluation and manual intervention.

[0086] The UAV path planning module 52 is configured to perform preset path planning based on a particle swarm algorithm, mainly by collecting geographic information data of the inspection area, and considering the maneuverability characteristics of the UAV flight, safety constraints and inspection target priorities, and designing and implementing path planning based on the particle swarm algorithm;

[0087] The adjustment module 53 is configured to avoid unconventional obstacles based on the real-time detection data of the UAV visual system and realize local safety adjustment of the path; mainly, the UAV performs target inspection on the preset path, and at the same time completes the recording of inspection requirements and the monitoring of the real-time flight environment based on the binocular camera, analyzes the safety and feasibility of the current path planning based on the real-time monitoring data, and generates a new local path plan based on the trained particle swarm algorithm when the path needs to be dynamically adjusted to meet the inspection target and flight safety of the UAV;

[0088] The path assessment intervention module 54 is configured to provide remote monitoring and control functions, including a data transmission unit, a command control unit and an operation interface. The data transmission unit transmits image data collected during the drone inspection process, remotely monitors the current position of the drone, the inspection target, the planned path and other information. Through the command control unit and the operation interface, the user is allowed to manually adjust and intervene in the inspection path in real time, send human control instructions to the drone control system, and realize remote adjustment. The path assessment intervention module of the present invention can provide data transmission, remote monitoring and control functions, and the operator can obtain the location and path plan of the drone in real time, and perform human intervention in a timely manner according to the inspection requirements, thereby enhancing the simplicity and operability of drone management.

[0089] The present invention adopts unmanned aerial vehicles to replace traditional manual inspection and maintenance work, saving manpower, material resources and other related resources. It has the ability to preset paths and dynamically adjust paths locally, and can safely visit inspection targets of different demand levels with the best path, reducing flight costs and improving work efficiency.

[0090] Example 3

[0091] A device based on multi-objective UAV path planning, such as Figure 5 As shown, it includes: a processor 61;

[0092] And a memory 62 coupled to the processor 61 is used to store instructions. When the instructions are executed by the processor 61, the processor 61 executes the method based on multi-target UAV path planning; the processor 61 and the memory 62 transmit data through a bus 63.

[0093] In addition, the present invention also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method based on multi-target UAV path planning are implemented.

[0094] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0095] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0096] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0097] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the enlightenment of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the purpose of the present invention and the claims, which all fall within the protection of the present invention.

Claims

1. A method based on multi-target UAV path planning, characterized in that: The following steps are involved: S1. Collect geographic information data of the inspection area, establish a planning path database based on the collected data, and pre-process and optimize the data; S2. According to the maneuverability characteristics, safety constraints and inspection target priorities of the UAV flight, the UAV path planning model is solved based on the particle swarm algorithm; S3, based on the UAV vision system, real-time detection of unconventional obstacles can be achieved to achieve local safety adjustments to the path; S4. The updated path is synchronously sent to the remote client for path evaluation and manual intervention.

2. The method for multi-target UAV path planning according to claim 1, characterized in that: The maneuverability characteristics in step S2 include the flight speed, minimum step length, maximum yaw angle and maximum flight time of the drone: Among them, v t is the flight speed of the UAV at time t, v max is the maximum flight speed of the UAV, S step is the minimum step length of the drone, f(θ (t+1)-t ) is the difference in deflection angle from time t to time t+1, θ max is the maximum deviation angle between adjacent waypoints of the UAV, T is the flight time of the UAV, and E B is the current battery power of the drone, η dc is the conversion efficiency of the drone battery discharge, F UAV is the pulling force of the drone, f w is the friction force of wind.

3. The method for multi-target UAV path planning according to claim 1, characterized in that: The safety constraint condition in step S2 is the dynamic random obstacle threat: d min ≤d UAV-obs ; Among them, d UAV-obs is the distance between the drone and the obstacle, d min is the minimum safe distance between the drone and obstacles.

4. The method for multi-target UAV path planning according to claim 1, characterized in that: In step S2, the inspection target priority is based on the current flight range of the UAV, and the inspection target with the highest priority is selected as the required waypoint for this path planning, and the inspection target with the next highest priority is selected as the auxiliary waypoint required for this inspection.

5. The method for multi-target UAV path planning according to claim 1 is characterized in that In step S2, the UAV path planning model is solved based on the particle swarm algorithm, and the fitness function solved by the particle swarm algorithm is set from multiple aspects such as flight time, path smoothness and path effectiveness, and the dynamic random obstacle threat, minimum step length and standby time are used as the constraint conditions of path planning. Among them, the multi-objective fitness function F fitness It is expressed as: F fitness =αf(t)+βf(θ)+δf(l); Among them, α, β, and δ are the weight coefficients of the flight time f(t), path smoothness f(θ), and path effectiveness f(l), respectively.

6. The method for multi-target UAV path planning according to claim 1, characterized in that: The step S3 specifically includes: S301, the UAV performs target inspection on the preset path, and at the same time, the camera equipment based on the visual system completes the recording of inspection requirements and the monitoring of the real-time flight environment, and analyzes the safety and feasibility of the current path planning based on the real-time monitoring data; S302: If it is determined that there is no obstacle threat on the current flight path, perform inspection according to the planned path; If the monitoring data determines that the current path needs to be dynamically adjusted, the distance and direction of the obstacle are calculated based on the binocular camera carried by the drone, and a new local path plan is generated based on the trained particle swarm algorithm to meet the drone's inspection objectives and flight safety; S303: Apply the adjusted path to the drone and send it to the drone remote client synchronously, update this path, and evaluate whether the new solution meets the inspection requirements.

7. The method for multi-target UAV path planning according to claim 1, characterized in that: The step S4 specifically includes: S401. Design and write remote client APP software to transmit image data collected during drone inspection, remotely monitor the current location of the drone, inspection targets and planned path information; S402, the drone connects to a path planning database to obtain a preset path and a new path plan of local dynamic adjustment in real time; S403, providing a user interface to allow the user to manually adjust and intervene in the inspection path in real time, and send human control instructions to the UAV remote client to achieve remote adjustment.

8. A device based on multi-target UAV path planning, characterized in that: The method for implementing the multi-objective UAV path planning according to any one of claims 1 to 7 comprises: The data collection and processing module is used to collect geographic information data of the inspection area, establish a planning path database based on the collected data, and pre-process and optimize the data; The UAV path planning module is used to solve the UAV path planning model based on the particle swarm algorithm according to the UAV flight maneuverability, safety constraints and inspection target priority; The adjustment module is used to detect unconventional obstacles in real time based on the UAV vision system and realize local safety adjustment of the path; The path evaluation and intervention module is used to update the path synchronously and send it to the remote client for path evaluation and manual intervention.

9. A device based on multi-target UAV path planning, characterized in that: include: processor; And a memory coupled to the processor, for storing instructions, wherein when the instructions are executed by the processor, the processor executes the method based on multi-target UAV path planning as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method based on multi-target UAV path planning as described in any one of claims 1 to 7 are implemented.

Images