Unmanned aerial vehicle networking remote sensing planning method and system

Abstract

The invention provides an unmanned aerial vehicle networking remote sensing planning method and system, and the method comprises the following steps: optimizing the flight path of each unmanned aerial vehicle, and obtaining the optimal flight path, the optimal flight direction and the optimal task starting point of each unmanned aerial vehicle; and based on the optimal flight paths, the optimal flight directions and the optimal task starting points of all single machines, distributing the multi-machine networking tasks to complete unmanned aerial vehicle networking task remote sensing planning. According to the technical scheme, efficient and collaborative operation of the unmanned aerial vehicle in a large area is achieved, the acquisition efficiency and utilization value of remote sensing data are improved, the operation cost and risk are reduced, and the method has wide application prospects and popularization value.

Description

Background Art

[0002] At present, the problems faced by UAV network remote sensing planning mainly include the following aspects:

[0003] 1. Problems with UAV flight platforms and airborne sensors

[0004] Insufficient stability: UAV flight platforms are prone to stability problems in complex environments, affecting the quality of remote sensing data collection.

[0005] Short battery life: The limitation of battery life makes it difficult for drones to work continuously in long-term remote sensing monitoring tasks. Frequent battery replacement or charging is required, which reduces work efficiency.

[0006] Insufficient payload: The payload capacity of UAV platforms is limited and they cannot carry a sufficient number and weight of sensors, which limits the diversity and complexity of remote sensing monitoring tasks.

[0007] Poor sensor adaptability: Existing drone-mounted sensors cannot fully adapt to complex external environments, and the quality of remote sensing data acquired is often affected by environmental differences.

[0008] 2. Issues in Data Processing and Application

[0009] Data acquisition and processing are difficult: UAV network remote sensing observations can obtain ultra-high-resolution data over a large area, but data processing and analysis require a lot of time and computing resources.

[0010] Data interpretation lag: Delayed interpretation of remote sensing monitoring data will not be able to guide relevant decisions and actions in a timely manner, reducing the practicality and timeliness of remote sensing monitoring.

[0011] Limited applicability of algorithms and models: Currently, most algorithms or models are only applicable to specific research or scenarios and lack stability, universality and versatility, which limits their large-scale application and promotion.

[0012] 3. Air Traffic Management and Safety Issues

[0013] Unregulated airspace management: Remote sensing observations using drone networks require rational planning of airspace resources, but the current air traffic management mechanism is not yet perfect and lacks unified planning and effective management.

[0014] Flight safety risks: UAVs may be affected by severe weather such as strong winds, rain, etc. during flight, and may collide with other aircraft or obstacles, posing safety risks.

[0015] The quality of operators varies greatly: UAV operators need to have a sense of safe flight and comply with local laws and regulations, but the quality of operators is currently uneven, which increases flight safety risks.

[0016] 4. Collaborative Planning and Task Allocation

[0017] Lack of network coordination planning: Currently, UAV remote sensing is mostly single-machine operation, lacking network coordination planning, resulting in the need to improve operation efficiency.

[0018] Unreasonable task allocation: In UAV network remote sensing observation, how to reasonably allocate tasks to each UAV is a complex issue, which requires consideration of factors such as the UAV's endurance, load capacity, and flight speed. Summary of the invention

[0019] The present application provides a method and system for remote sensing planning of unmanned aerial vehicle networking, which are used to improve the efficiency of acquiring remote sensing data and the utilization value, and reduce operating costs and risks.

[0020] In a first aspect, a method for remote sensing planning of a UAV network is provided, comprising the following steps:

[0021] Optimize the flight path of each drone to obtain the optimal flight path, optimal flight direction and optimal mission starting point for each drone;

[0022] Based on the optimal flight path, optimal flight direction and optimal mission starting point of all single aircraft, the multi-aircraft networking tasks are allocated to complete the remote sensing planning of UAV networking tasks.

[0023] In the above technical scheme, the optimal flight path, optimal flight direction and optimal mission starting point of a single UAV are obtained by optimizing the flight track of each UAV; based on the optimal flight paths, optimal flight directions and optimal mission starting points of all single UAVs, multi-machine networking tasks are allocated to complete the remote sensing planning of UAV networking tasks; efficient and collaborative operation of UAVs in large areas is achieved, which not only improves the efficiency of acquiring remote sensing data and the utilization value, but also reduces operating costs and risks, and has broad application prospects and promotion value.

[0024] In a specific implementation scheme, the steps of optimizing the flight path of each UAV to obtain the optimal flight path, optimal flight direction and optimal mission starting point of a single UAV include:

[0025] Using path planning algorithms and combining path planning factors, the optimal flight path for each drone is calculated;

[0026] The optimal flight direction of each drone is calculated through the minimum span algorithm;

[0027] The optimal mission starting point for each UAV is determined according to the station-based mission starting point selection criteria.

[0028] In a specific implementation scheme, the path planning algorithm includes an A* algorithm and an RRT algorithm.

[0029] In a specific implementation scheme, the path planning factors include terrain factors and obstacle factors.

[0030] In a specific implementation plan, based on the optimal flight path, optimal flight direction and optimal mission starting point of all single aircraft, the multi-aircraft networking tasks are allocated to complete the steps of remote sensing planning of UAV networking tasks, specifically including:

[0031] Based on the optimal flight path, optimal flight direction and optimal mission starting point of all single aircraft, combined with the round-trip range of each UAV to the station, a station-based UAV networking task allocation algorithm is used to allocate multi-machine networking tasks to complete the remote sensing planning of UAV networking tasks.

[0032] In a specific implementation scheme, the station-based UAV networking task allocation algorithm includes clustering method, distributed task allocation method, Monte Carlo algorithm, and particle swarm algorithm.

[0033] In a specific implementation plan, the steps of allocating multi-machine networking tasks using a station-based UAV networking task allocation algorithm include:

[0034] Based on the multi-machine networking task factors, formulate the multi-machine networking task allocation strategy;

[0035] Based on the multi-machine networking task allocation strategy, the task allocation for collaborative operations between UAVs is carried out by dynamically adjusting the operation area and task sequence of UAVs;

[0036] The task allocation is optimized using the station-based UAV networking task allocation algorithm.

[0037] In a specific embodiment, it also includes:

[0038] Process the remote sensing data collected by drones to generate digital results.

[0039] In a specific implementation scheme, the multi-machine networking mission factors include the UAV's endurance, operating efficiency and mission requirements.

[0040] In the second aspect, a UAV network remote sensing planning system is provided, including:

[0041] The single-machine optimization module is used to optimize the trajectory of each UAV to obtain the optimal flight path, optimal flight direction and optimal mission starting point of the single aircraft;

[0042] The networking allocation module is used to allocate multi-machine networking tasks based on the optimal flight path, optimal flight direction and optimal mission starting point of all single machines, and complete the remote sensing planning of UAV networking tasks.

[0043] In the above technical scheme, the optimal flight path, optimal flight direction and optimal mission starting point of a single UAV are obtained by optimizing the flight track of each UAV; based on the optimal flight paths, optimal flight directions and optimal mission starting points of all single UAVs, multi-machine networking tasks are allocated to complete the remote sensing planning of UAV networking tasks; efficient and collaborative operation of UAVs in large areas is achieved, which not only improves the efficiency of acquiring remote sensing data and the utilization value, but also reduces operating costs and risks, and has broad application prospects and promotion value. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A method block diagram of a remote sensing planning method for a UAV network provided in an embodiment of the present application;

[0045] Figure 2 This is a structural block diagram of the UAV network remote sensing planning system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] The present application is further described in detail below through the accompanying drawings and embodiments. Through these descriptions, the characteristics and advantages of the present application will become clearer and more specific.

[0047] The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration." Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments. Although various aspects of the embodiments are shown in the drawings, the drawings are not necessarily drawn to scale unless otherwise noted.

[0048] In addition, the technical features involved in different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0049] To facilitate understanding of the UAV network remote sensing planning method and system provided in the embodiment of the present application, its application scenario is first explained. The UAV network remote sensing planning method and system provided in the embodiment of the present application are used to improve the acquisition efficiency and utilization value of remote sensing data, and reduce operating costs and risks. At present, the problems currently faced by UAV network remote sensing planning mainly include the following aspects: 1. Problems with UAV flight platforms and airborne sensors: Insufficient stability: UAV flight platforms are prone to stability problems in complex environments, affecting the collection quality of remote sensing data. Short endurance: The limitation of endurance makes it difficult for UAVs to continue working in long-term remote sensing monitoring tasks, and batteries need to be frequently replaced or charged, which reduces work efficiency. Insufficient load: The load capacity of the UAV platform is limited, and it is impossible to carry a sufficient number and weight of sensors, which limits the diversity and complexity of remote sensing monitoring tasks. Poor sensor adaptability: Existing UAV airborne sensors cannot fully adapt to complex external environments, and the quality of remote sensing data obtained is often affected by environmental differences. 2. Problems with data processing and application: Difficulty in data acquisition and processing: UAV network remote sensing observation can obtain ultra-high resolution data over a large range, but data processing and analysis require a lot of time and computing resources. Data interpretation lags: Delayed interpretation of remote sensing monitoring data will not be able to guide relevant decisions and actions in a timely manner, reducing the practicality and timeliness of remote sensing monitoring. Limited applicability of algorithms and models: At present, most algorithms or models are only applicable to specific research or scenarios, and cannot have stability, universality and versatility, which limits their large-scale application and promotion. 3. Air traffic management and safety issues: Irregular airspace management: UAV network remote sensing observation requires reasonable planning of airspace resources, but the current air traffic management mechanism is not perfect, lacking unified planning and effective management. Flight safety risks: UAVs may be affected by severe weather such as strong winds, rain and other weather during flight, and may collide with other aircraft or obstacles, posing safety risks. The quality of operators is uneven: UAV operators need to have a sense of safe flight and the quality of abiding by local laws and regulations, but the current quality of operators is uneven, increasing flight safety risks. 4. Collaborative planning and task allocation issues: Lack of networking collaborative planning: Currently, most UAV remote sensing operations are single-machine operations, lacking networking collaborative planning, resulting in operational efficiency that needs to be improved. Unreasonable task allocation: In the UAV network remote sensing observation, how to reasonably allocate tasks to each UAV is a complex issue, which requires consideration of factors such as the UAV's endurance, load capacity, and flight speed. To this end, the present application embodiment provides a UAV network remote sensing planning method and system to improve the acquisition efficiency and utilization value of remote sensing data and reduce operating costs and risks. The following is a detailed description of the embodiment in conjunction with specific drawings.

[0050] refer to Figure 1 and Figure 2 , Figure 1A method block diagram of a remote sensing planning method for a UAV network provided in an embodiment of the present application; Figure 2 This is a structural block diagram of the UAV network remote sensing planning system provided in an embodiment of the present application.

[0051] exist Figure 1 In the embodiment of the present application, a method for remote sensing planning of a drone network is provided, comprising the following steps:

[0052] Optimize the flight path of each drone to obtain the optimal flight path, optimal flight direction and optimal mission starting point for each drone;

[0053] Based on the optimal flight path, optimal flight direction and optimal mission starting point of all single aircraft, the multi-aircraft networking tasks are allocated to complete the remote sensing planning of UAV networking tasks.

[0054] In the above technical scheme, the optimal flight path, optimal flight direction and optimal mission starting point of a single UAV are obtained by optimizing the flight track of each UAV; based on the optimal flight paths, optimal flight directions and optimal mission starting points of all single UAVs, multi-machine networking tasks are allocated to complete the remote sensing planning of UAV networking tasks; efficient and collaborative operation of UAVs in large areas is achieved, which not only improves the efficiency of acquiring remote sensing data and the utilization value, but also reduces operating costs and risks, and has broad application prospects and promotion value.

[0055] In a specific implementation scheme, the steps of optimizing the flight path of each UAV to obtain the optimal flight path, optimal flight direction and optimal mission starting point of a single UAV include:

[0056] Using path planning algorithms and combining path planning factors, the optimal flight path for each drone is calculated;

[0057] The optimal flight direction of each drone is calculated through the minimum span algorithm;

[0058] The optimal mission starting point for each UAV is determined according to the station-based mission starting point selection criteria.

[0059] In a specific implementation scheme, the path planning algorithm includes an A* algorithm and an RRT algorithm.

[0060] In a specific implementation scheme, the path planning factors include terrain factors and obstacle factors.

[0061] In a specific implementation plan, based on the optimal flight path, optimal flight direction and optimal mission starting point of all single aircraft, the multi-aircraft networking tasks are allocated to complete the steps of remote sensing planning of UAV networking tasks, specifically including:

[0062] Based on the optimal flight path, optimal flight direction and optimal mission starting point of all single aircraft, combined with the round-trip range of each UAV to the station, a station-based UAV networking task allocation algorithm is used to allocate multi-machine networking tasks to complete the remote sensing planning of UAV networking tasks.

[0063] In a specific implementation scheme, the station-based UAV networking task allocation algorithm includes clustering method, distributed task allocation method, Monte Carlo algorithm, and particle swarm algorithm.

[0064] In a specific implementation plan, the steps of allocating multi-machine networking tasks using a station-based UAV networking task allocation algorithm include:

[0065] Based on the multi-machine networking task factors, formulate the multi-machine networking task allocation strategy;

[0066] Based on the multi-machine networking task allocation strategy, the task allocation for collaborative operations between UAVs is carried out by dynamically adjusting the operation area and task sequence of UAVs;

[0067] The task allocation is optimized using the station-based UAV networking task allocation algorithm.

[0068] In a specific embodiment, it also includes:

[0069] Process the remote sensing data collected by drones to generate digital results.

[0070] In a specific implementation scheme, the multi-machine networking mission factors include the UAV's endurance, operating efficiency and mission requirements.

[0071] Specifically, the UAV network remote sensing planning method aims to solve the problem of UAV network remote sensing operation trajectory planning during large-area remote sensing operations. The algorithm combines single-machine trajectory optimization and multi-machine network task allocation to achieve efficient and coordinated operation of UAVs in a large area.

[0072] First, the present invention optimizes the flight path of a single drone, and uses a path planning algorithm (A algorithm, or RRT algorithm) to calculate the optimal flight path for each drone, combined with factors such as terrain and obstacles. On this basis, the optimal flight direction is found through the minimum span algorithm, and the optimal mission starting point is determined according to the mission starting point selection criteria based on the station, so as to ensure that the drone can minimize the flight time and energy consumption during the operation.

[0073] Specifically, the single-machine trajectory optimization includes the following steps:

[0074] Using advanced path planning algorithms, combined with factors such as terrain and obstacles, the optimal flight path of the drone is calculated;

[0075] Apply the minimum span algorithm to determine the optimal flight direction, ensuring that the drone can maintain efficient heading adjustment during flight;

[0076] The optimal mission starting point for each UAV is determined according to the station-based mission starting point selection criteria.

[0077] Next, the present invention takes the optimized single-machine trajectory as the basis, considers the round-trip flight distance of each drone to the station, and adopts a station-based drone networking task allocation algorithm. This algorithm fully utilizes the drone's endurance under the premise of ensuring the highest single-machine operation efficiency, and allocates tasks with the minimum number of operating drones as the goal. By dynamically adjusting the drone's operating area and task sequence, collaborative operations between drones are achieved, improving overall operating efficiency.

[0078] Specifically, multi-machine networking task allocation includes:

[0079] Comprehensively consider the UAV's endurance, operating efficiency and mission requirements, and formulate a multi-machine networking task allocation strategy;

[0080] By dynamically adjusting the operation area and task sequence of drones, collaborative operations between drones can be achieved;

[0081] Use optimization algorithms (such as genetic algorithms or particle swarm algorithms) to optimize task allocation and allocate tasks with the minimum number of operating drones as the goal;

[0082] It also includes: data processing and results generation: processing the remote sensing data collected by drones, including data calibration, splicing, fusion and other steps; generating two-dimensional digital results and three-dimensional digital results to provide high-quality remote sensing data support for subsequent applications.

[0083] In the above technical scheme, by combining single-machine trajectory optimization and multi-machine networking task allocation, the station-based UAV networking trajectory planning results were obtained, achieving efficient and accurate coverage of large-area remote sensing operations; it not only improved the efficiency of acquiring remote sensing data and the utilization value, but also reduced operating costs and risks, and has broad application prospects.

[0084] exist Figure 2 In the embodiment of the present application, a UAV network remote sensing planning system is provided, including:

[0085] The single-machine optimization module is used to optimize the trajectory of each UAV to obtain the optimal flight path, optimal flight direction and optimal mission starting point of the single aircraft;

[0086] The networking allocation module is used to allocate multi-machine networking tasks based on the optimal flight path, optimal flight direction and optimal mission starting point of all single machines, and complete the remote sensing planning of UAV networking tasks.

[0087] In the above technical scheme, the optimal flight path, optimal flight direction and optimal mission starting point of a single UAV are obtained by optimizing the flight track of each UAV; based on the optimal flight paths, optimal flight directions and optimal mission starting points of all single UAVs, multi-machine networking tasks are allocated to complete the remote sensing planning of UAV networking tasks; efficient and collaborative operation of UAVs in large areas is achieved, which not only improves the efficiency of acquiring remote sensing data and the utilization value, but also reduces operating costs and risks, and has broad application prospects and promotion value.

[0088] Those skilled in the art will appreciate that the present application may be implemented as a system, method or computer program product.

[0089] Therefore, the present disclosure may be specifically implemented in the following forms, namely: it may be completely hardware, it may be completely software (including firmware, resident software, microcode, etc.), or it may be a combination of hardware and software, generally referred to herein as a "circuit", "module" or "system". In addition, in some embodiments, the present application may also be implemented in the form of a computer program product in one or more computer-readable media, and the computer-readable medium may contain computer-readable program code.

[0090] Any combination of one or more computer-readable media can be used. Computer-readable media can be computer-readable signal media or computer-readable storage media. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: electrical connections with one or more wires, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this document, computer-readable storage media can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0091] Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art can change, modify, replace and modify the above embodiments within the scope of the present application. On this basis, a variety of replacements and improvements can be made to the present application, all of which fall within the scope of protection of the present application.

Claims

1. A method for remote sensing planning of unmanned aerial vehicle networking, characterized in that: The following steps are involved: Optimize the flight path of each drone to obtain the optimal flight path, optimal flight direction and optimal mission starting point for each drone; Based on the optimal flight path, optimal flight direction and optimal mission starting point of all single aircraft, the multi-aircraft networking tasks are allocated to complete the remote sensing planning of UAV networking tasks.

2. The method for remote sensing planning of UAV networking according to claim 1, characterized in that: The steps to optimize the trajectory of each UAV to obtain the optimal flight path, optimal flight direction and optimal mission starting point for each UAV include: Using path planning algorithms and combining path planning factors, the optimal flight path for each drone is calculated; The optimal flight direction of each drone is calculated through the minimum span algorithm; The optimal mission starting point for each UAV is determined according to the station-based mission starting point selection criteria.

3. The method for remote sensing planning of UAV networking according to claim 2, characterized in that: The path planning algorithms include A* algorithm and RRT algorithm.

4. The method for remote sensing planning of UAV networking according to claim 3, characterized in that: The path planning factors include terrain factors and obstacle factors.

5. The method for remote sensing planning of UAV networking according to claim 4, characterized in that: Based on the optimal flight path, optimal flight direction and optimal mission starting point of all single aircraft, the multi-aircraft networking tasks are allocated to complete the steps of remote sensing planning of UAV networking tasks, including: Based on the optimal flight path, optimal flight direction and optimal mission starting point of all single aircraft, combined with the round-trip range of each UAV to the station, a station-based UAV networking task allocation algorithm is used to allocate multi-machine networking tasks to complete the remote sensing planning of UAV networking tasks.

6. The method for remote sensing planning of UAV networking according to claim 5, characterized in that: The station-based UAV networking task allocation algorithms include clustering method, distributed task allocation method, Monte Carlo algorithm, and particle swarm algorithm.

7. The method for remote sensing planning of UAV networking according to claim 6, characterized in that: The steps of allocating multi-machine networking tasks using the station-based UAV networking task allocation algorithm include: Based on the multi-machine networking task factors, formulate the multi-machine networking task allocation strategy; Based on the multi-machine networking task allocation strategy, the task allocation for collaborative operations between UAVs is carried out by dynamically adjusting the operation area and task sequence of UAVs; The task allocation is optimized using the station-based UAV networking task allocation algorithm.

8. The method for remote sensing planning of UAV networking according to claim 7, characterized in that: Also includes: Process the remote sensing data collected by drones to generate digital results.

9. The method for remote sensing planning of UAV networking according to claim 8, characterized in that: The multi-machine networking mission factors include the UAV's endurance, operating efficiency and mission requirements.

10. A UAV network remote sensing planning system, characterized in that: include: The single-machine optimization module is used to optimize the trajectory of each UAV to obtain the optimal flight path, optimal flight direction and optimal mission starting point of the single aircraft; The networking allocation module is used to allocate multi-machine networking tasks based on the optimal flight path, optimal flight direction and optimal mission starting point of all single machines, and complete the remote sensing planning of UAV networking tasks.

Images