A full-body control method for unmanned aerial vehicles in a strong wind disturbance environment

By combining Gaussian processes and deep neural networks, the robustness and agility of UAVs in strong wind environments are improved, solving the problems of control accuracy and computational efficiency of UAVs under strong wind disturbances, and enhancing the stability and flexibility of the system.

CN120178932BActive Publication Date: 2026-06-05SUN YAT SEN UNIV
View PDF 3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Patents(China)
Current Assignee / Owner
SUN YAT SEN UNIV
Filing Date
2025-03-18
Publication Date
2026-06-05

AI Technical Summary

Technical Problem

Drones struggle to maintain robustness and agility in environments with strong wind disturbances. Existing control methods struggle to balance computational efficiency and accuracy, and the coupled control of the robotic arm and rotor is complex, affecting system stability and flexibility.

Method used

A whole-body control method based on Gaussian processes and deep neural networks is adopted. By updating the wind disturbance estimate and linearized dynamic model online, the control input is dynamically planned and combined with the motion assistance of the robotic arm to complete the UAV mission.

Benefits of technology

It improves the robustness and agility of UAVs in strong wind environments, enables rapid response and high-precision aerial operations, reduces computational burden, and enhances system stability and flexibility.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120178932B_ABST
    Figure CN120178932B_ABST
Patent Text Reader

Abstract

The application discloses a full-body control method for unmanned aerial vehicles in a strong wind disturbance environment, and relates to the technical field of unmanned aerial vehicle control.The method comprises the following steps: selecting a corresponding target decision variable according to different wind disturbances; converting a nonlinear dynamics model of an unmanned aerial vehicle air operation system into a linear dynamics model; the unmanned aerial vehicle air operation system comprises an unmanned aerial vehicle and a mechanical arm connected with the unmanned aerial vehicle; updating a wind disturbance estimation value on line according to on-line state data of the unmanned aerial vehicle air operation system; solving a model predictive control optimization problem corresponding to the linear dynamics model according to a decision variable and the wind disturbance estimation value to obtain a control input; and controlling the unmanned aerial vehicle air operation system according to the control input.The application selects a target decision variable corresponding to wind disturbance and updates a wind disturbance estimation value on line, and then solves a suitable control input to control the system, so that the unmanned aerial vehicle air operation system can adapt to various scenes under strong wind disturbance, and the robustness and agility are improved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Learning-based rotor unmanned aerial vehicle path tracking prediction control method

    CN112416021A

  • Unmanned aerial vehicle wind disturbance control method and device, equipment and storage medium

    CN116974182A

  • Flight mechanical arm tail end control method capable of resisting multi-source interference and coordinating motion planning

    CN118322200A