Unmanned aerial vehicle cluster meeting method based on deep reinforcement learning

Abstract

The invention provides an unmanned aerial vehicle cluster meeting method based on deep reinforcement learning. In the training stage, a fixed area is set in the meeting task scene to serve as a meeting area of the unmanned aerial vehicle cluster, area center point position information is obtained, a deep neural network for judging movement of the unmanned aerial vehicle cluster is established, thedeep neural network is trained, and after training is completed, a final deep neural network is obtained; and in the execution stage: the input data is inputted into the trained deep neural network for judgment. According to the method, the state space and the behavior space of the unmanned aerial vehicle cluster task are expanded, the practicability is high for incomplete scene information, thetask-oriented unmanned aerial vehicle cluster unified decision network is constructed, and unified command and control of the decision network for the uncertain number of unmanned aerial vehicles arerealized.

Description

technical field [0001] The invention relates to the fields of machine learning and path planning, in particular to a method for rendezvous of drone swarms. Background technique [0002] In order to achieve precise strikes by UAV clusters on a certain target area or to complete the reconnaissance and search tasks in a certain area, and improve the success rate of completing tasks, it is often necessary for multiple UAVs to fly to a certain target area from different directions to complete the rendezvous task . Traditionally, basic consensus algorithms and consensus algorithms based on past state differences are used to solve UAV cluster rendezvous tasks. These algorithm systems have slow convergence speed, long task completion time, and low effectiveness and feasibility. [0003] The current research on the behavior control direction of UAVs using artificial intelligence methods mainly stays in the research and application of individual UAVs, and there are few researches on ...

AI Technical Summary

Problems solved by technology

Judging from the results of collaborative missions of UAV clusters realized in China, my country's UAV clusters have more research on how to effectively prevent collisions when UAV clusters cooperate to perform tasks, and the payload of UAVs and its execution are more important. High-level tasks, such as: coordinated detection, coordinated attack, coordinated defense and other task-level related research are still relatively few

Images