Litcius/Paper detail

Deep Reinforcement Learning-Based Wind Disturbance Rejection Control Strategy for UAV

Qun Ma, Yibo Wu, Muhammad Usman Shoukat, Yukai Yan, Jun Wang, Long Yang, Fuwu Yan, Lirong Yan

2024Drones22 citationsDOIOpen Access PDF

Abstract

Unmanned aerial vehicles (UAVs) face significant challenges in maintaining stability when subjected to external wind disturbances and internal noise. This paper addresses these issues by introducing a real-time wind speed fitting algorithm and a wind field model that accounts for varying wind conditions, such as wind shear and turbulence. To improve control in such conditions, a deep reinforcement learning (DRL) strategy is developed and tested through both simulations and real-world experiments. The results indicate a 65% reduction in trajectory tracking error with the DRL controller. Additionally, a UAV built for testing exhibited enhanced stability and reduced angular deviations in wind conditions up to level 5. These findings demonstrate the effectiveness of the proposed DRL-based control strategy in increasing UAV resilience to wind disturbances.

Topics & Concepts

Disturbance (geology)Reinforcement learningControl (management)Control theory (sociology)Active disturbance rejection controlReinforcementComputer scienceArtificial intelligenceEngineeringGeologyQuantum mechanicsPaleontologyState observerNonlinear systemStructural engineeringPhysicsUAV Applications and OptimizationAdaptive Dynamic Programming ControlAerospace and Aviation Technology