Online Reinforcement-Learning-Based Adaptive Terminal Sliding Mode Control for Disturbed Bicycle Robots on a Curved Pavement
The reaction wheel is able to help improve the balancing ability of a bicycle robot on curved pavement. However, preserving good control performances for such a robot that is driving on unstructured surfaces under matched and mismatched disturbances is challenging due to the underactuated characteri...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-10-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/11/21/3495 |
_version_ | 1797468523780374528 |
---|---|
author | Xianjin Zhu Yang Deng Xudong Zheng Qingyuan Zheng Bin Liang Yu Liu |
author_facet | Xianjin Zhu Yang Deng Xudong Zheng Qingyuan Zheng Bin Liang Yu Liu |
author_sort | Xianjin Zhu |
collection | DOAJ |
description | The reaction wheel is able to help improve the balancing ability of a bicycle robot on curved pavement. However, preserving good control performances for such a robot that is driving on unstructured surfaces under matched and mismatched disturbances is challenging due to the underactuated characteristic and the nonlinearity of the robot. In this paper, a controller combining proximal policy optimization algorithms with terminal sliding mode controls is developed for controlling the balance of the robot. Online reinforcement-learning-based adaptive terminal sliding mode control is proposed to attenuate the influence of the matched and mismatched disturbance by adjusting parameters of the controller online. Different from several existing adaptive sliding mode approaches that only tune parameters of the reaching controller, the proposed method also considers the online adjustment of the sliding surface to provide adequate robustness against mismatched disturbances. The co-simulation experimental results in MSC Adams illustrate that the proposed controller can achieve better control performances than four existing methods for a reaction wheel bicycle robot moving on curved pavement, which verifies the robustness and applicability of the method. |
first_indexed | 2024-03-09T19:08:37Z |
format | Article |
id | doaj.art-a88d191c064c4d2b922ecebf918729b0 |
institution | Directory Open Access Journal |
issn | 2079-9292 |
language | English |
last_indexed | 2024-03-09T19:08:37Z |
publishDate | 2022-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Electronics |
spelling | doaj.art-a88d191c064c4d2b922ecebf918729b02023-11-24T04:24:51ZengMDPI AGElectronics2079-92922022-10-011121349510.3390/electronics11213495Online Reinforcement-Learning-Based Adaptive Terminal Sliding Mode Control for Disturbed Bicycle Robots on a Curved PavementXianjin Zhu0Yang Deng1Xudong Zheng2Qingyuan Zheng3Bin Liang4Yu Liu5School of Mechatronics Engineering, Harbin Institute of Technology, Harbin 150006, ChinaDepartment of Automation, Tsinghua University, Beijing 100084, ChinaSchool of Modern Post (School of Automation), Beijing University of Posts and Communications, Beijing 100876, ChinaDepartment of Automation, Tsinghua University, Beijing 100084, ChinaDepartment of Automation, Tsinghua University, Beijing 100084, ChinaSchool of Mechatronics Engineering, Harbin Institute of Technology, Harbin 150006, ChinaThe reaction wheel is able to help improve the balancing ability of a bicycle robot on curved pavement. However, preserving good control performances for such a robot that is driving on unstructured surfaces under matched and mismatched disturbances is challenging due to the underactuated characteristic and the nonlinearity of the robot. In this paper, a controller combining proximal policy optimization algorithms with terminal sliding mode controls is developed for controlling the balance of the robot. Online reinforcement-learning-based adaptive terminal sliding mode control is proposed to attenuate the influence of the matched and mismatched disturbance by adjusting parameters of the controller online. Different from several existing adaptive sliding mode approaches that only tune parameters of the reaching controller, the proposed method also considers the online adjustment of the sliding surface to provide adequate robustness against mismatched disturbances. The co-simulation experimental results in MSC Adams illustrate that the proposed controller can achieve better control performances than four existing methods for a reaction wheel bicycle robot moving on curved pavement, which verifies the robustness and applicability of the method.https://www.mdpi.com/2079-9292/11/21/3495reaction wheel bicycle robotreinforcement learningsliding model controlrobustness |
spellingShingle | Xianjin Zhu Yang Deng Xudong Zheng Qingyuan Zheng Bin Liang Yu Liu Online Reinforcement-Learning-Based Adaptive Terminal Sliding Mode Control for Disturbed Bicycle Robots on a Curved Pavement Electronics reaction wheel bicycle robot reinforcement learning sliding model control robustness |
title | Online Reinforcement-Learning-Based Adaptive Terminal Sliding Mode Control for Disturbed Bicycle Robots on a Curved Pavement |
title_full | Online Reinforcement-Learning-Based Adaptive Terminal Sliding Mode Control for Disturbed Bicycle Robots on a Curved Pavement |
title_fullStr | Online Reinforcement-Learning-Based Adaptive Terminal Sliding Mode Control for Disturbed Bicycle Robots on a Curved Pavement |
title_full_unstemmed | Online Reinforcement-Learning-Based Adaptive Terminal Sliding Mode Control for Disturbed Bicycle Robots on a Curved Pavement |
title_short | Online Reinforcement-Learning-Based Adaptive Terminal Sliding Mode Control for Disturbed Bicycle Robots on a Curved Pavement |
title_sort | online reinforcement learning based adaptive terminal sliding mode control for disturbed bicycle robots on a curved pavement |
topic | reaction wheel bicycle robot reinforcement learning sliding model control robustness |
url | https://www.mdpi.com/2079-9292/11/21/3495 |
work_keys_str_mv | AT xianjinzhu onlinereinforcementlearningbasedadaptiveterminalslidingmodecontrolfordisturbedbicyclerobotsonacurvedpavement AT yangdeng onlinereinforcementlearningbasedadaptiveterminalslidingmodecontrolfordisturbedbicyclerobotsonacurvedpavement AT xudongzheng onlinereinforcementlearningbasedadaptiveterminalslidingmodecontrolfordisturbedbicyclerobotsonacurvedpavement AT qingyuanzheng onlinereinforcementlearningbasedadaptiveterminalslidingmodecontrolfordisturbedbicyclerobotsonacurvedpavement AT binliang onlinereinforcementlearningbasedadaptiveterminalslidingmodecontrolfordisturbedbicyclerobotsonacurvedpavement AT yuliu onlinereinforcementlearningbasedadaptiveterminalslidingmodecontrolfordisturbedbicyclerobotsonacurvedpavement |