Reinforcement learning method and system for intelligent decision making of unmanned aerial vehicle, and storage medium

By adopting a boundary grid reward mechanism based on differential game in intelligent decision-making of drone, the problem that multi-agent reinforcement learning is difficult to accurately design the reward function in DCA problems is solved, and the effective defense strategy learning and defense effect of drone formations in complex environments is achieved.

CN119647631AActive Publication Date: 2025-03-18HEFEI UNIV OF TECH
10 Cites 3 Cited by

Patent Information

Application Number
CN202510176233.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-02-18
Publication Date
2025-03-18
Estimated Expiration
2045-02-18

AI Technical Summary

Technical Problem

Multi-agent reinforcement learning is difficult to accurately design the reward function in defensive anti-aircraft operations (DCA) problems, resulting in poor results in intelligent decision-making of drones.

Method used

By obtaining the drone formation information of the defensive party and the drone formation defense strategy, the detection results are used to generate a decision plan update model, including state space, decision plan, reward return and profit function, and the boundary grid reward obtained based on differential game is used to ensure that the reward mechanism can accurately reflect the goal achievement of both parties.

Benefits of technology

It realizes effective defense strategy learning for drone formations in complex environments, improves defense effect, and dispatches the scale of drone formations in real time when performing tasks.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a reinforcement learning method and system for unmanned aerial vehicle intelligent decision, and a storage medium, and relates to the technical field of unmanned aerial vehicles. According to the invention, on one hand, the decision-making scheme of the unmanned aerial vehicle can be updated through the detection result of the unmanned aerial vehicle, thereby scheduling the task execution scale of the unmanned aerial vehicle formation in real time, and improving the defense effect. And on the other hand, a boundary grid reward obtained based on the differential game is designed, it is ensured that a reward mechanism can accurately reflect the target achievement situation of both game parties, and through continuous iterative optimization of reinforcement learning, the unmanned aerial vehicle can gradually learn an effective unmanned aerial vehicle formation defense strategy in a complex environment.
Need to check novelty before this filing date? Find Prior Art