Learning-Based Discontinuous Path Following Control for a Biomimetic Underwater Vehicle
This paper addresses a learning-based discontinuous path following control scheme for a biomimetic underwater vehicle (BUV) driven by undulatory fins. Despite the flexibility of the BUV motion, it faces the challenge of dealing with discontinuous paths affected by irregular seafloor topography and u...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
American Association for the Advancement of Science
2024-01-01
|
Series: | Research |
Online Access: | https://spj.science.org/doi/10.34133/research.0299 |
_version_ | 1797338604427542528 |
---|---|
author | Yu Wang Hongfei Chu Ruichen Ma Xuejian Bai Long Cheng Shuo Wang Min Tan |
author_facet | Yu Wang Hongfei Chu Ruichen Ma Xuejian Bai Long Cheng Shuo Wang Min Tan |
author_sort | Yu Wang |
collection | DOAJ |
description | This paper addresses a learning-based discontinuous path following control scheme for a biomimetic underwater vehicle (BUV) driven by undulatory fins. Despite the flexibility of the BUV motion, it faces the challenge of dealing with discontinuous paths affected by irregular seafloor topography and underwater vegetation. Therefore, BUV must employ path switching strategy to navigate to the next safe area. We introduce a discontinuous path following control method based on deep reinforcement learning (DRL). This method uses the line of sight (LOS) navigation algorithm to provide the Markov decision process (MDP) state inputs and the soft actor-critic (SAC) algorithm to train the control strategy of the BUV. Unlike the traditional fixed waveform control method, this method encourages the BUV to learn different waveforms and fluctuation frequencies through DRL. At the same time, the BUV has the ability to switch to a new path at necessary moments, such as when encountering underwater rocks. The results of simulations and experiments demonstrate the successful integration of the undulatory fins with the SAC controller, showcasing its efficacy and diversity in discontinuous underwater path following tasks. |
first_indexed | 2024-03-08T09:33:42Z |
format | Article |
id | doaj.art-3b3a8aea3c7b4af58ff62b7ccc996de1 |
institution | Directory Open Access Journal |
issn | 2639-5274 |
language | English |
last_indexed | 2024-03-08T09:33:42Z |
publishDate | 2024-01-01 |
publisher | American Association for the Advancement of Science |
record_format | Article |
series | Research |
spelling | doaj.art-3b3a8aea3c7b4af58ff62b7ccc996de12024-01-30T16:27:01ZengAmerican Association for the Advancement of ScienceResearch2639-52742024-01-01710.34133/research.0299Learning-Based Discontinuous Path Following Control for a Biomimetic Underwater VehicleYu Wang0Hongfei Chu1Ruichen Ma2Xuejian Bai3Long Cheng4Shuo Wang5Min Tan6State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China.State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China.State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China.School of Electrical Engineering, Liaoning University of Technology, Jinzhou, China.State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China.State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China.State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China.This paper addresses a learning-based discontinuous path following control scheme for a biomimetic underwater vehicle (BUV) driven by undulatory fins. Despite the flexibility of the BUV motion, it faces the challenge of dealing with discontinuous paths affected by irregular seafloor topography and underwater vegetation. Therefore, BUV must employ path switching strategy to navigate to the next safe area. We introduce a discontinuous path following control method based on deep reinforcement learning (DRL). This method uses the line of sight (LOS) navigation algorithm to provide the Markov decision process (MDP) state inputs and the soft actor-critic (SAC) algorithm to train the control strategy of the BUV. Unlike the traditional fixed waveform control method, this method encourages the BUV to learn different waveforms and fluctuation frequencies through DRL. At the same time, the BUV has the ability to switch to a new path at necessary moments, such as when encountering underwater rocks. The results of simulations and experiments demonstrate the successful integration of the undulatory fins with the SAC controller, showcasing its efficacy and diversity in discontinuous underwater path following tasks.https://spj.science.org/doi/10.34133/research.0299 |
spellingShingle | Yu Wang Hongfei Chu Ruichen Ma Xuejian Bai Long Cheng Shuo Wang Min Tan Learning-Based Discontinuous Path Following Control for a Biomimetic Underwater Vehicle Research |
title | Learning-Based Discontinuous Path Following Control for a Biomimetic Underwater Vehicle |
title_full | Learning-Based Discontinuous Path Following Control for a Biomimetic Underwater Vehicle |
title_fullStr | Learning-Based Discontinuous Path Following Control for a Biomimetic Underwater Vehicle |
title_full_unstemmed | Learning-Based Discontinuous Path Following Control for a Biomimetic Underwater Vehicle |
title_short | Learning-Based Discontinuous Path Following Control for a Biomimetic Underwater Vehicle |
title_sort | learning based discontinuous path following control for a biomimetic underwater vehicle |
url | https://spj.science.org/doi/10.34133/research.0299 |
work_keys_str_mv | AT yuwang learningbaseddiscontinuouspathfollowingcontrolforabiomimeticunderwatervehicle AT hongfeichu learningbaseddiscontinuouspathfollowingcontrolforabiomimeticunderwatervehicle AT ruichenma learningbaseddiscontinuouspathfollowingcontrolforabiomimeticunderwatervehicle AT xuejianbai learningbaseddiscontinuouspathfollowingcontrolforabiomimeticunderwatervehicle AT longcheng learningbaseddiscontinuouspathfollowingcontrolforabiomimeticunderwatervehicle AT shuowang learningbaseddiscontinuouspathfollowingcontrolforabiomimeticunderwatervehicle AT mintan learningbaseddiscontinuouspathfollowingcontrolforabiomimeticunderwatervehicle |