Anti-aerodynamic disturbance multi-uav fixed time neural adaptive formation control method

By employing a hierarchical control architecture and an improved non-singular fixed-time sliding mode control, the deterministic convergence problem of multi-UAV formations under complex aerodynamic disturbances was solved, achieving fast and safe formation control and improving the robustness of the system and the effectiveness of the neural network.

CN122086102BActive Publication Date: 2026-06-23HARBIN INST OF TECH
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
HARBIN INST OF TECH
Filing Date
2026-04-22
Publication Date
2026-06-23

AI Technical Summary

Technical Problem

Existing multi-UAV formation control technologies struggle to achieve deterministic convergence when faced with complex coupled aerodynamic uncertainties and strict time window constraints. Furthermore, neural networks are prone to failure under large disturbances, leading to system instability.

Method used

A hierarchical control architecture is adopted, combining distributed reference generation, robust tracking controller and improved non-singular fixed-time sliding mode control. An outer-loop formation controller and an inner-loop attitude/velocity controller are designed. Radial basis function neural network is used to compensate for aerodynamic disturbances. Adaptive update law and obstacle safety term are used to ensure that the formation error converges within a predefined safety area.

Benefits of technology

It achieves deterministic fixed-time convergence of UAV formations under complex aerodynamic disturbances, improving convergence speed and robustness, ensuring flight safety and the effectiveness of the neural network, and avoiding system instability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122086102B_ABST
    Figure CN122086102B_ABST
Patent Text Reader

Abstract

The application relates to the technical field of multi-unmanned aerial vehicle cooperative control, and discloses a multi-unmanned aerial vehicle fixed-time neural adaptive formation control method resisting aerodynamic disturbance, which constructs a hierarchical controller architecture, the outer ring is a distributed reference generation and safety tracking controller, and the inner ring is a fixed-time terminal sliding mode controller with a cubic nonsingular smooth switching mechanism; a fixed-time sliding mode surface with the cubic nonsingular smooth switching mechanism is configured to realize deterministic convergence, an adaptive RBF neural network is adopted to actively compensate aerodynamic disturbance, a safety mechanism based on an obstacle function is combined to constrain the unmanned aerial vehicle state in a safety set, Lyapunov analysis verifies the fixed-time stability of the system, and simulation results of six unmanned aerial vehicle formations show that the convergence speed of the method is improved by 29.6%, the robustness is better, and the safe, accurate and rapid formation control of the multi-unmanned aerial vehicle under complex aerodynamic disturbance can be realized.
Need to check novelty before this filing date? Find Prior Art