Fixed-wing unmanned aerial vehicle distributed formation and obstacle avoidance method based on diffusion reinforcement learning

CN121596887APending Publication Date: 2026-03-03NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202511608251.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-11-05
Publication Date
2026-03-03

AI Technical Summary

Technical Problem

Existing technologies struggle to effectively achieve distributed formation and obstacle avoidance of fixed-wing UAV swarms in complex and unknown environments, especially in situations with dense obstacles. Traditional methods lack adaptability and are prone to oscillating behavior or collisions.

Method used

A deep reinforcement learning approach based on a generative-diffusion model is adopted for multiple UAVs. Through a diffusion policy network and a graph value network, control commands are generated using local observations to achieve distributed formation and obstacle avoidance of UAVs. This method comprises a diffusion model policy network (actuator) and a graph value network (evaluator), operating under a centralized training and distributed execution paradigm. A graph attention network is used to process dynamic neighbor information to generate diverse actions.

Benefits of technology

In unknown and chaotic environments, fixed-wing UAV swarms can maintain tight formation and navigate safely, significantly improving flight stability and reducing collision rates, which is superior to existing methods.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121596887A_ABST
    Figure CN121596887A_ABST
Patent Text Reader

Abstract

The invention discloses a fixed-wing unmanned aerial vehicle distributed formation and obstacle avoidance method based on diffusion reinforcement learning, and the method comprises the steps: processing single observation data through a graph attention network, and enabling the single observation data to serve as a condition for generating an optimal action in a reverse denoising process; the method is suitable for distributed cluster control of a fixed-wing unmanned aerial vehicle cluster in an unknown and disordered environment, treats huge challenges brought by complex dynamics and non-integral constraints in the cluster, and effectively solves a series of problems that an existing method is difficult to capture multi-modal action distribution necessary for robust obstacle avoidance under an uncertain condition. A large number of numerical simulation results show that the method is obviously superior to an existing baseline method in the aspects of flight stability and collision rate, the potential of a diffusion model in the aspect of extensible and robust unmanned aerial vehicle flight control is highlighted, and the method has good theoretical popularization value and engineering application prospects.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Cited By

  • Flight cabin remote real machine control method based on multi-source perception fusion

    CN122363341A

  • Flight cabin remote real machine control method based on multi-source perception fusion

    CN122363341B