Distributed online adaptive task planning system for unmanned aerial vehicle group

Abstract

The invention discloses a distributed online adaptive task planning system for an unmanned aerial vehicle group, and relates to the technical field of unmanned aerial vehicle task planning. The system comprises a data acquisition and processing module, a task planning and distribution module, a path planning module, a load configuration module, a real-time monitoring and adjusting module, a cooperative control module, a real-time communication module and an optimization module, and generating a task planning scheme and performing task allocation by applying an online optimization algorithm and a self-adaptive technology. According to the invention, the task planning and distribution module integrates advanced algorithms and technologies to perform task planning and task distribution, so that each unmanned aerial vehicle can bear appropriate task load, an unmanned aerial vehicle / vehicle cluster can autonomously and efficiently complete diversified tasks in a complex environment, intelligent scheduling, path optimization and cooperative operation of the unmanned aerial vehicles / vehicles are realized, and the unmanned aerial vehicle / vehicle cluster is enabled to be more intelligent. And the self-organization capability, the dynamic adaptability and the collaborative operation efficiency of the unmanned aerial vehicle group are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle (UAV) mission planning, and in particular to a distributed online adaptive mission planning system for a swarm of unmanned aerial vehicles (UAVs). Background Art

[0002] Drones originated in the military field. Compared with manned aircraft, drones have the advantages of being reusable, recoverable, free of casualties, strong continuous working ability, and low life cycle cost. Due to the increasing complexity of the combat environment and the limited mission execution capabilities of a single drone, multi-drone cluster collaborative operations will become an important development trend in future drone operations, in order to achieve complementary capabilities between drones and thus improve the effectiveness of the entire system. A distributed online adaptive mission planning system for drone swarms is an important research direction in the field of drone technology. It integrates advanced algorithms, big data analysis technology, and real-time communication capabilities to achieve efficient, flexible, and intelligent mission planning for drone swarms.

[0003] The existing technology has the following problems:

[0004] Most of the existing UAV swarm mission planning systems focus on path planning, while the coordination at the task allocation level, especially the dynamic distributed task allocation, has not been deeply studied, which limits the cooperative combat capability of UAV swarms in complex tasks. At the same time, the system lacks sufficient real-time and autonomy. When faced with complex and changeable battlefield environments and mission requirements, the system cannot make decisions and adjust plans quickly, resulting in low efficiency or even failure of mission execution. When each UAV transmits perception information to the mission control station for global planning, when the quality and speed of the data link are low, the information obtained by the mission control station is often outdated, incomplete, or even wrong, which will lead to decision-making errors and mission failures. With the increase in the number of UAVs and the complexity of tasks, the excessive amount of calculation of the system increases the complexity of the algorithm. In addition, during the execution of the mission, once an abnormal situation occurs in a UAV and the system's ability to cope with emergencies is poor, the effectiveness of the entire combat mission will be greatly affected. Summary of the invention

[0005] The present invention provides a distributed online adaptive task planning system for a drone swarm to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0007] A distributed online adaptive task planning system for a drone swarm, the system comprising: a data acquisition and processing module, a task planning and allocation module, a path planning module, a load configuration module, a real-time monitoring and adjustment module, a collaborative control module, a real-time communication module and an optimization module. The task planning and allocation module is used to generate a task planning scheme and perform task allocation according to task requirements and the status of the drone swarm using an online optimization algorithm and adaptive technology. The load configuration module is used to configure a load for each drone according to task requirements, including but not limited to a camera, a sensor, and a weapon.

[0008] Preferably, the data acquisition and processing module is used to collect data on drone status, environmental information, and mission requirements, pre-process the data, fuse multi-source perception data, and analyze the data.

[0009] Preferably, the path planning module is used to plan the optimal or safe flight path for each drone using path planning technology based on the drone's current position, target position and environmental information, including but not limited to terrain, obstacles, and threats.

[0010] Preferably, the real-time monitoring and adjustment module is used to receive flight status data from the drones in real time, including but not limited to position, speed, and battery level, and to monitor the drone swarm in real time. Once the drone swarm has abnormal conditions, including but not limited to deviation from the route and insufficient battery level, the system uses intelligent decision support technology based on machine learning and task adaptive adjustment technology to make adjustments or issue warnings.

[0011] Preferably, the collaborative control module is responsible for the collaborative control between the drone groups through collaborative technology, including but not limited to adaptive collaborative control technology and drone / unmanned aerial vehicle collaborative technology.

[0012] Preferably, the real-time communication module provides real-time communication between drone groups by using real-time communication technology, including communication and network protection mechanisms.

[0013] Preferably, the optimization module is used to simulate real-world scenario testing and continuously iterate and optimize system performance.

[0014] Preferably, the system uses distributed computing technology to distribute the computational burden of task planning to each drone or computing node, so that each drone can perform local path planning and task allocation based on the environmental information and task requirements it obtains.

[0015] Preferably, the online optimization algorithm is specifically a particle swarm optimization algorithm, and the formula of the algorithm includes:

[0016] Speed ​​update formula: )+ ),in It is a particle In the The speed in the dimension The value at the iteration, is the inertia weight, and is the learning factor, and is a random number between [0,1], It is a particle In the The optimal position of an individual in the dimension is The value at the iteration, The particle swarm is The global optimal position in dimension is The value at the iteration, It is a particle In the The position on the dimension is The value at the iteration;

[0017] Position update formula: ,in It is a particle In the The position on the dimension is The value at iteration.

[0018] Due to the adoption of the above technical solution, the present invention has the following technical advances compared with the prior art:

[0019] 1. The present invention provides a distributed online adaptive task planning system for drone swarms. The task planning and allocation module integrates advanced algorithms and technologies for task planning and task allocation, ensuring that each drone can undertake an appropriate amount of tasks, so that the drone / vehicle cluster can autonomously and efficiently complete diversified tasks in complex environments, realize intelligent scheduling, path optimization and collaborative operation of drones / vehicles, enhance the self-organizing ability, dynamic adaptability and collaborative operation efficiency of drone swarms, and significantly improve the performance and safety of drone swarms when performing complex tasks. The system adopts distributed computing technology to realize the dispersion and sharing of computing resources, reduce the computing burden of central nodes, improve the flexibility and robustness of the system, and reduce the risk of single point failures.

[0020] 2. The present invention provides a distributed online adaptive task planning system for drone swarms. The system receives flight status data from drones in real time through a real-time monitoring and adjustment module, and monitors the drone swarm in real time. Once the drone swarm deviates from the route, runs out of power or encounters abnormal conditions, the system uses task adaptive adjustment technology based on machine learning to adjust the task or issue a warning. This not only optimizes the global operating efficiency of the drone swarm, but also enhances the system's ability to respond to emergencies, thereby improving the system's decision-making speed and quality. The optimization module simulates real-world scenario tests, continuously iterates and optimizes system performance, and ensures its optimal performance in specific tasks.

[0021] 3. The present invention provides a distributed online adaptive task planning system for drone swarms, which deeply integrates the application potential of manned and unmanned aerial vehicles through collaborative modules, improves the system's information perception, decision-making speed and task execution efficiency, and achieves close cooperation between manned and unmanned aerial vehicles. At the same time, by building a highly adaptive collaborative mechanism, it strengthens the target allocation and path planning capabilities in a dynamic environment, ensures that the drone swarm can maintain a high degree of coordination and consistency when performing complex tasks, and effectively performs diversified tasks such as low-altitude transportation and low-altitude logistics, thereby comprehensively improving the efficiency and survivability of manned and unmanned aerial vehicle collaborative operations.

[0022] 4. The present invention provides a distributed online adaptive task planning system for drone swarms. The real-time communication module provides real-time communication between drone swarms by using real-time communication technology to ensure the security of information sharing and command links. The system supports the collaborative operation of multiple drones and improves the overall operation efficiency and effect by reasonably allocating tasks and resources, providing the system with sufficient real-time and autonomy. When faced with complex and changeable battlefield environments and mission requirements, the system can quickly make more scientific and reasonable decisions and plan adjustments. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a schematic diagram of the framework of the distributed online adaptive task planning system for drone swarms of the present invention. DETAILED DESCRIPTION

[0024] In order to make the technical means, creative features, objectives and effects achieved by the present invention easy to understand, the present invention is further explained below in conjunction with specific implementation methods.

[0025] like Figure 1As shown, a distributed online adaptive task planning system for a drone swarm is provided, the system comprising: a data acquisition and processing module, a task planning and allocation module, a path planning module, a load configuration module, a real-time monitoring and adjustment module, a collaborative control module, a real-time communication module and an optimization module. The task planning and allocation module is used to generate a task planning scheme and perform task allocation according to the task requirements and the status of the drone swarm by using an online optimization algorithm and adaptive technology. The load configuration module is used to configure a load for each drone according to the task requirements, including but not limited to cameras, sensors, and weapons, to ensure that the time and method of using the load are reasonable and to improve the efficiency of task execution.

[0026] An efficient, flexible and intelligent task planning system is formed through modules such as data acquisition and processing module, task planning and allocation module, path planning module, payload configuration module, real-time monitoring and adjustment module, collaborative control module, real-time communication module and optimization module. It can provide accurate adaptive task planning and efficient collaborative control solutions for drone swarms in complex environments. It integrates advanced algorithms and technologies for task planning and task allocation to ensure that each drone can undertake the appropriate amount of tasks and ensure the smooth execution of tasks. It realizes intelligent scheduling, path optimization and collaborative operation of drones / vehicles, improves the self-organizing ability, dynamic adaptability and collaborative operation efficiency of drone swarms, and significantly improves the performance and safety of drone swarms when performing complex tasks. It is widely used in military, rescue, logistics, agriculture and other fields.

[0027] The data acquisition and processing module is used to collect data on drone status, environmental information, and mission requirements, pre-process the data, fuse multi-source perception data, and analyze the data.

[0028] By fusing multi-source perception data, the mission control station can obtain real-time and complete data, improve the quality of decision-making, and reduce mission failures.

[0029] The path planning module is used to plan the optimal or safe flight path for each drone using path planning technology based on the drone's current position, target position and environmental information, including but not limited to terrain, obstacles, and threats.

[0030] Path planning technology supports online adjustments to adapt to environmental changes and changes in task requirements to ensure efficient completion of tasks.

[0031] The real-time monitoring and adjustment module is used to receive real-time flight status data from drones, including but not limited to location, speed, and battery level, and to monitor the drone swarm in real time. Once the drone swarm has abnormal conditions, including but not limited to deviation from the route and insufficient battery level, the system uses intelligent decision support technology based on machine learning and task adaptive adjustment technology to make adjustments or issue warnings.

[0032] The system's intelligent decision support technology based on machine learning not only optimizes the global operating efficiency of the drone swarm, but also enhances the system's ability to respond to emergencies, thereby improving the system's decision-making speed and quality.

[0033] The collaborative control module is responsible for the collaborative control between drone groups through collaborative technologies, including but not limited to adaptive collaborative control technology and drone / unmanned aerial collaborative technology.

[0034] Through the collaborative module, the application potential of manned and unmanned aerial vehicles is deeply integrated, the system's information perception, decision-making speed and task execution efficiency are improved, and close cooperation between manned and unmanned aerial vehicles is achieved. At the same time, by building a highly adaptive collaborative mechanism, the target allocation and path planning capabilities in a dynamic environment are enhanced, ensuring that the drone swarm can maintain a high degree of coordination and consistency when performing complex tasks, and effectively perform diversified tasks such as low-altitude traffic and low-altitude logistics, thereby comprehensively improving the efficiency and survivability of manned and unmanned aerial vehicle collaborative operations.

[0035] The real-time communication module provides real-time communication between drone groups by using real-time communication technology, including communication and network protection mechanisms, to ensure the security of information sharing and command links. The system supports the collaborative operation of multiple drones and improves overall operation efficiency and effectiveness by reasonably allocating tasks and resources, providing the system with sufficient real-time and autonomy. When faced with complex and changing battlefield environments and mission requirements, the system can quickly make more scientific and reasonable decisions and plan adjustments.

[0036] The optimization module is used to simulate real-world scenario testing and continuously iterate and optimize system performance to ensure its optimal performance in specific tasks.

[0037] The system uses distributed computing technology to distribute the computational burden of task planning to each drone or computing node. Each drone can perform local path planning and task allocation based on the environmental information and task requirements it obtains.

[0038] The system uses distributed computing technology to achieve the dispersion and sharing of computing resources, which reduces the computing burden of the central node, improves the flexibility and robustness of the system, and reduces the risk of single point failure.

[0039] The online optimization algorithm is specifically a particle swarm optimization algorithm, and the formula of the algorithm includes:

[0040] Speed ​​update formula: )+ ),in It is a particle In the The speed in the dimension The value at the iteration, is the inertia weight, and is the learning factor, and is a random number between [0,1], It is a particle In the The optimal position of an individual in the dimension is The value at the iteration, The particle swarm is The global optimal position in dimension is The value at the iteration, It is a particle In the The position on the dimension is The value at the iteration;

[0041] Position update formula: ,in It is a particle In the The position on the dimension is The value at iteration.

[0042] In summary, the central control system receives task instructions from users or superior systems, parses and preliminarily plans the tasks, collects data such as drone status, environmental information, and task requirements through the data acquisition and processing module, pre-processes the data, integrates multi-source perception data, and analyzes the data. The task planning and allocation module uses online optimization algorithms and adaptive technologies to generate task planning plans and allocate tasks based on task requirements and the status of the drone group, ensuring that each drone can undertake the appropriate amount of tasks, so that the drone / car cluster can autonomously and efficiently complete diversified tasks in complex environments. The path planning module uses path planning technology to plan the best or safest path for each drone. The flight path and payload configuration module configure payloads for each drone according to mission requirements, including but not limited to cameras, sensors, and weapons, to ensure that the timing and method of payload use are reasonable and to improve mission execution efficiency. The drone takes off and performs missions according to the planned path and mission planning plan. The real-time monitoring and adjustment module receives flight status data from the drone in real time and monitors the drone swarm in real time. Once an abnormal situation occurs in the drone swarm, the system uses machine learning-based intelligent decision support technology and mission adaptive adjustment technology to make adjustments or issue warnings, which not only optimizes the global operating efficiency of the drone swarm, but also enhances the system's ability to respond to emergencies. The collaborative control module uses collaborative technology to Responsible for the coordinated control between drone groups, strengthening the target allocation and path planning capabilities in dynamic environments, ensuring that drone groups can maintain a high degree of coordination and consistency when performing complex tasks, realizing intelligent scheduling, path optimization and collaborative operations of drones / cars, and deeply integrating the application potential of manned and unmanned aerial vehicles, improving the system's information perception, decision-making speed and task execution efficiency, and achieving close cooperation between manned and unmanned aerial vehicles. Drones perform tasks according to planned paths and provide real-time feedback on task execution to the central control system. The central control system performs subsequent processing or adjustments based on the task execution status. In the face of complex and changeable battlefield environments and task requirements, it can quickly Quickly make more scientific and reasonable decisions and plan adjustments, effectively perform diversified tasks such as low-altitude transportation and low-altitude logistics, improve overall operational efficiency and effectiveness, and significantly improve the performance and safety of drone swarms when performing complex tasks. The system uses distributed computing technology to achieve the dispersion and sharing of computing resources, which reduces the computing burden of the central node, improves the flexibility and robustness of the system, and reduces the risk of single point failures. In addition, through the optimization module to simulate real-scene tests, the system performance is continuously iterated and optimized to ensure its optimal performance in specific tasks. The real-time communication module provides real-time communication for communications between drone swarms by using real-time communication technology to ensure the security of information sharing and command links.

[0043] The above generally describes the present invention in detail, but it is obvious to a person skilled in the art that some modifications or improvements can be made to the present invention. Therefore, modifications or improvements that do not depart from the spirit of the present invention are within the scope of protection of the present invention.

Claims

1. A distributed online adaptive mission planning system for drone swarms, characterized by: The system includes: a data acquisition and processing module, a task planning and allocation module, a path planning module, a load configuration module, a real-time monitoring and adjustment module, a collaborative control module, a real-time communication module and an optimization module. The task planning and allocation module is used to generate a task planning plan and perform task allocation according to the task requirements and the status of the drone group using an online optimization algorithm and adaptive technology. The load configuration module is used to configure a load for each drone according to the task requirements, including but not limited to cameras, sensors, and weapons.

2. The distributed online adaptive mission planning system for drone swarms according to claim 1, characterized in that: The data acquisition and processing module is used to collect data on drone status, environmental information, and mission requirements, pre-process the data, fuse multi-source perception data, and analyze the data.

3. The distributed online adaptive mission planning system for drone swarms according to claim 1 is characterized by: The path planning module is used to plan the optimal or safe flight path for each drone using path planning technology based on the drone's current position, target position and environmental information, including but not limited to terrain, obstacles, and threats.

4. The distributed online adaptive mission planning system for drone swarms according to claim 1, characterized in that: The real-time monitoring and adjustment module is used to receive flight status data from drones in real time, including but not limited to position, speed, and power, and to monitor the drone swarm in real time. Once the drone swarm has abnormal conditions including but not limited to deviation from the route and insufficient power, the system uses task adaptive adjustment technology based on machine learning intelligent decision support technology to make adjustments or issue warnings.

5. The distributed online adaptive mission planning system for drone swarms according to claim 1, characterized in that: The collaborative control module is responsible for the collaborative control between the drone groups through collaborative technology, including but not limited to adaptive collaborative control technology and drone / unmanned aerial vehicle collaborative technology.

6. The distributed online adaptive mission planning system for drone swarms according to claim 1, characterized in that: The real-time communication module provides real-time communication between drone groups by using real-time communication technology, including communication and network protection mechanisms.

7. The distributed online adaptive mission planning system for drone swarms according to claim 1, characterized in that: The optimization module is used to simulate real-world testing and continuously iterate and optimize system performance.

8. The distributed online adaptive mission planning system for drone swarms according to claim 1, characterized in that: The system uses distributed computing technology to distribute the computational burden of task planning to each drone or computing node. Each drone can perform local path planning and task allocation based on the environmental information and task requirements it obtains.

9. The distributed online adaptive mission planning system for drone swarms according to claim 1, characterized in that: The online optimization algorithm is specifically a particle swarm optimization algorithm, and the formula of the algorithm includes: Speed ​​update formula: )+ ),in It is a particle In the The speed in the dimension The value at the iteration, is the inertia weight, and is the learning factor, and is a random number between [0,1], It is a particle In the The optimal position of an individual in the dimension is The value at the iteration, The particle swarm is The global optimal position in dimension is The value at the iteration, It is a particle In the The position on the dimension is The value at the iteration; Position update formula: ,in It is a particle In the The position on the dimension is The value at iteration.

Images