Robust Reinforcement Learning Control Framework for a Quadrotor Unmanned Aerial Vehicle Using Critic Neural Network

This article introduces a novel robust reinforcement learning (RL) control scheme for a quadrotor unmanned aerial vehicle (QUAV) under external disturbances and model uncertainties. First, the translational and rotational motions of the QUAV are decoupled and trained separately to mitigate the compu...

Full description

Saved in:
Bibliographic Details
Main Authors: Yu Cai, Yefeng Yang, Tao Huang, Boyang Li
Format: Article
Language:English
Published: Wiley 2025-03-01
Series:Advanced Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1002/aisy.202400427
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849774923341365248
author Yu Cai
Yefeng Yang
Tao Huang
Boyang Li
author_facet Yu Cai
Yefeng Yang
Tao Huang
Boyang Li
author_sort Yu Cai
collection DOAJ
description This article introduces a novel robust reinforcement learning (RL) control scheme for a quadrotor unmanned aerial vehicle (QUAV) under external disturbances and model uncertainties. First, the translational and rotational motions of the QUAV are decoupled and trained separately to mitigate the computational complexity of the controller design and training process. Then, the proximal policy optimization algorithm with a dual‐critic structure is proposed to address the overestimation issue and accelerate the convergence speed of RL controllers. Furthermore, a novel reward function and a robust compensator employing a switch value function are proposed to address model uncertainties and external disturbances. At last, simulation results and comparisons demonstrate the effectiveness and robustness of the proposed RL control framework.
format Article
id doaj-art-3a8672f7a53b43e2a913c7967e2300e7
institution DOAJ
issn 2640-4567
language English
publishDate 2025-03-01
publisher Wiley
record_format Article
series Advanced Intelligent Systems
spelling doaj-art-3a8672f7a53b43e2a913c7967e2300e72025-08-20T03:01:35ZengWileyAdvanced Intelligent Systems2640-45672025-03-0173n/an/a10.1002/aisy.202400427Robust Reinforcement Learning Control Framework for a Quadrotor Unmanned Aerial Vehicle Using Critic Neural NetworkYu Cai0Yefeng Yang1Tao Huang2Boyang Li3Center for Control Theory and Guidance Technology Harbin Institute of Technology Harbin 150001 ChinaCenter for Control Theory and Guidance Technology Harbin Institute of Technology Harbin 150001 ChinaCenter for Control Theory and Guidance Technology Harbin Institute of Technology Harbin 150001 ChinaSchool of Engineering The University of Newcastle Callaghan NSW 2308 AustraliaThis article introduces a novel robust reinforcement learning (RL) control scheme for a quadrotor unmanned aerial vehicle (QUAV) under external disturbances and model uncertainties. First, the translational and rotational motions of the QUAV are decoupled and trained separately to mitigate the computational complexity of the controller design and training process. Then, the proximal policy optimization algorithm with a dual‐critic structure is proposed to address the overestimation issue and accelerate the convergence speed of RL controllers. Furthermore, a novel reward function and a robust compensator employing a switch value function are proposed to address model uncertainties and external disturbances. At last, simulation results and comparisons demonstrate the effectiveness and robustness of the proposed RL control framework.https://doi.org/10.1002/aisy.202400427proximal policy optimizationquadrotor unmanned aerial vehiclesreinforcement learning controlrobust compensations
spellingShingle Yu Cai
Yefeng Yang
Tao Huang
Boyang Li
Robust Reinforcement Learning Control Framework for a Quadrotor Unmanned Aerial Vehicle Using Critic Neural Network
Advanced Intelligent Systems
proximal policy optimization
quadrotor unmanned aerial vehicles
reinforcement learning control
robust compensations
title Robust Reinforcement Learning Control Framework for a Quadrotor Unmanned Aerial Vehicle Using Critic Neural Network
title_full Robust Reinforcement Learning Control Framework for a Quadrotor Unmanned Aerial Vehicle Using Critic Neural Network
title_fullStr Robust Reinforcement Learning Control Framework for a Quadrotor Unmanned Aerial Vehicle Using Critic Neural Network
title_full_unstemmed Robust Reinforcement Learning Control Framework for a Quadrotor Unmanned Aerial Vehicle Using Critic Neural Network
title_short Robust Reinforcement Learning Control Framework for a Quadrotor Unmanned Aerial Vehicle Using Critic Neural Network
title_sort robust reinforcement learning control framework for a quadrotor unmanned aerial vehicle using critic neural network
topic proximal policy optimization
quadrotor unmanned aerial vehicles
reinforcement learning control
robust compensations
url https://doi.org/10.1002/aisy.202400427
work_keys_str_mv AT yucai robustreinforcementlearningcontrolframeworkforaquadrotorunmannedaerialvehicleusingcriticneuralnetwork
AT yefengyang robustreinforcementlearningcontrolframeworkforaquadrotorunmannedaerialvehicleusingcriticneuralnetwork
AT taohuang robustreinforcementlearningcontrolframeworkforaquadrotorunmannedaerialvehicleusingcriticneuralnetwork
AT boyangli robustreinforcementlearningcontrolframeworkforaquadrotorunmannedaerialvehicleusingcriticneuralnetwork