Deep Reinforcement Learning Based Active Disturbance Rejection Control for ROV Position and Attitude Control

Remotely operated vehicles (ROVs) face challenges in achieving optimal trajectory tracking performance during underwater movement due to external disturbances and parameter uncertainties. To address this issue, this paper proposes a position and attitude control strategy for underwater robots based...

Full description

Saved in:
Bibliographic Details
Main Authors: Gaosheng Luo, Dong Zhang, Wei Feng, Zhe Jiang, Xingchen Liu
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/8/4443
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849712398114488320
author Gaosheng Luo
Dong Zhang
Wei Feng
Zhe Jiang
Xingchen Liu
author_facet Gaosheng Luo
Dong Zhang
Wei Feng
Zhe Jiang
Xingchen Liu
author_sort Gaosheng Luo
collection DOAJ
description Remotely operated vehicles (ROVs) face challenges in achieving optimal trajectory tracking performance during underwater movement due to external disturbances and parameter uncertainties. To address this issue, this paper proposes a position and attitude control strategy for underwater robots based on a reinforcement learning active disturbance rejection controller. The linear active disturbance rejection controller has achieved satisfactory results in the field of underwater robot control. However, fixed-parameter controllers cannot achieve optimal control performance for the controlled object. Therefore, further exploration of the adaptive capability of control parameters based on the linear active disturbance rejection controller was conducted. The deep deterministic policy gradient (DDPG) algorithm was used to optimize the linear extended state observer (LESO). This strategy employs deep neural networks to adjust the LESO parameters online based on measured states, allowing for more accurate estimation of model uncertainties and environmental disturbances, and compensating the total disturbance into the control input online, resulting in better disturbance estimation and control performance. Simulation results show that the proposed control scheme, compared to PID and fixed parameter LADRC, as well as the double closed-loop sliding mode control method based on nonlinear observers (NESO-DSMC), significantly improves the disturbance estimation accuracy of the linear active disturbance rejection controller, leading to higher control precision and stronger robustness, thus demonstrating the effectiveness of the proposed control strategy.
format Article
id doaj-art-d11b2bc7daa04d12a153a54d20fb23f9
institution DOAJ
issn 2076-3417
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-d11b2bc7daa04d12a153a54d20fb23f92025-08-20T03:14:16ZengMDPI AGApplied Sciences2076-34172025-04-01158444310.3390/app15084443Deep Reinforcement Learning Based Active Disturbance Rejection Control for ROV Position and Attitude ControlGaosheng Luo0Dong Zhang1Wei Feng2Zhe Jiang3Xingchen Liu4Shanghai Engineering Research Center of Hadal Science and Technology, College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, ChinaShanghai Engineering Research Center of Hadal Science and Technology, College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, ChinaShenzhen Institute for Advanced Study, University of Electronic Science and Technology of China, Shenzhen 518110, ChinaShanghai Engineering Research Center of Hadal Science and Technology, College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, ChinaShanghai Engineering Research Center of Hadal Science and Technology, College of Engineering Science and Technology, Shanghai Ocean University, Shanghai 201306, ChinaRemotely operated vehicles (ROVs) face challenges in achieving optimal trajectory tracking performance during underwater movement due to external disturbances and parameter uncertainties. To address this issue, this paper proposes a position and attitude control strategy for underwater robots based on a reinforcement learning active disturbance rejection controller. The linear active disturbance rejection controller has achieved satisfactory results in the field of underwater robot control. However, fixed-parameter controllers cannot achieve optimal control performance for the controlled object. Therefore, further exploration of the adaptive capability of control parameters based on the linear active disturbance rejection controller was conducted. The deep deterministic policy gradient (DDPG) algorithm was used to optimize the linear extended state observer (LESO). This strategy employs deep neural networks to adjust the LESO parameters online based on measured states, allowing for more accurate estimation of model uncertainties and environmental disturbances, and compensating the total disturbance into the control input online, resulting in better disturbance estimation and control performance. Simulation results show that the proposed control scheme, compared to PID and fixed parameter LADRC, as well as the double closed-loop sliding mode control method based on nonlinear observers (NESO-DSMC), significantly improves the disturbance estimation accuracy of the linear active disturbance rejection controller, leading to higher control precision and stronger robustness, thus demonstrating the effectiveness of the proposed control strategy.https://www.mdpi.com/2076-3417/15/8/4443ROVlinear active disturbance rejection controldeep reinforcement learningdeep deterministic policy gradient (DDPG) algorithmresilience to disturbance
spellingShingle Gaosheng Luo
Dong Zhang
Wei Feng
Zhe Jiang
Xingchen Liu
Deep Reinforcement Learning Based Active Disturbance Rejection Control for ROV Position and Attitude Control
Applied Sciences
ROV
linear active disturbance rejection control
deep reinforcement learning
deep deterministic policy gradient (DDPG) algorithm
resilience to disturbance
title Deep Reinforcement Learning Based Active Disturbance Rejection Control for ROV Position and Attitude Control
title_full Deep Reinforcement Learning Based Active Disturbance Rejection Control for ROV Position and Attitude Control
title_fullStr Deep Reinforcement Learning Based Active Disturbance Rejection Control for ROV Position and Attitude Control
title_full_unstemmed Deep Reinforcement Learning Based Active Disturbance Rejection Control for ROV Position and Attitude Control
title_short Deep Reinforcement Learning Based Active Disturbance Rejection Control for ROV Position and Attitude Control
title_sort deep reinforcement learning based active disturbance rejection control for rov position and attitude control
topic ROV
linear active disturbance rejection control
deep reinforcement learning
deep deterministic policy gradient (DDPG) algorithm
resilience to disturbance
url https://www.mdpi.com/2076-3417/15/8/4443
work_keys_str_mv AT gaoshengluo deepreinforcementlearningbasedactivedisturbancerejectioncontrolforrovpositionandattitudecontrol
AT dongzhang deepreinforcementlearningbasedactivedisturbancerejectioncontrolforrovpositionandattitudecontrol
AT weifeng deepreinforcementlearningbasedactivedisturbancerejectioncontrolforrovpositionandattitudecontrol
AT zhejiang deepreinforcementlearningbasedactivedisturbancerejectioncontrolforrovpositionandattitudecontrol
AT xingchenliu deepreinforcementlearningbasedactivedisturbancerejectioncontrolforrovpositionandattitudecontrol