Learning-Based Propulsion Control for Amphibious Quadruped Robots With Dynamic Adaptation to Changing Environment

Simple item page
dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.authorYao, Qingfengen_US
dc.contributor.authorMeng, Linghanen_US
dc.contributor.authorZhang, Qifengen_US
dc.contributor.authorZhao, Jingen_US
dc.contributor.authorPajarinen, Jonien_US
dc.contributor.authorWang, Xiaohuien_US
dc.contributor.authorLi, Zhibinen_US
dc.contributor.authorWang, Congen_US
dc.contributor.departmentDepartment of Electrical Engineering and Automationen
dc.contributor.groupauthorRobot Learningen
dc.contributor.organizationCAS - Shenyang Institute of Automationen_US
dc.contributor.organizationHeriot-Watt Universityen_US
dc.contributor.organizationUniversity College Londonen_US
dc.date.accessioned2024-01-17T08:12:02Z
dc.date.available2024-01-17T08:12:02Z
dc.date.issued2023-12-01en_US
dc.descriptionFunding Information: This work was supported in part by the Applied Basic Research Program of Liaoning Province under Grant 2022020403-JH2/1013, in part by the National Key Research and Development Program of China under Grant 2022YFB4701900, in part by the National Natural Science Foundation of China under Grant 61821005, in part by the Open Research Project of the State Key Laboratory of Industrial Control Technology, Zhejiang University, China under Grant ICT2023B50, in part by the Program of China Scholarship Council, and in part by the JIANG Xinsong Innovation Fund under Grant E2510202. Publisher Copyright: © 2016 IEEE.
dc.description.abstractThis letter proposes a learning-based adaptive propulsion control (APC) method for a quadruped robot integrated with thrusters in amphibious environments, allowing it to move efficiently in water while maintaining its ground locomotion capabilities. We designed the specific reinforcement learning method to train the neural network to perform the vector propulsion control. Our approach coordinates the legs and propeller, enabling the robot to achieve speed and trajectory tracking tasks in the presence of actuator failures and unknown disturbances. Our simulated validations of the robot in water demonstrate the effectiveness of the trained neural network to predict the disturbances and actuator failures based on historical information, showing that the framework is adaptable to changing environments and is suitable for use in dynamically changing situations. Our proposed approach is suited to the hardware augmentation of quadruped robots to create avenues in the field of amphibious robotics and expand the use of quadruped robots in various applications.en
dc.description.versionPeer revieweden
dc.format.extent8
dc.format.extent7889-7896
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationYao, Q, Meng, L, Zhang, Q, Zhao, J, Pajarinen, J, Wang, X, Li, Z & Wang, C 2023, ' Learning-Based Propulsion Control for Amphibious Quadruped Robots With Dynamic Adaptation to Changing Environment ', IEEE Robotics and Automation Letters, vol. 8, no. 12, pp. 7889-7896 . https://doi.org/10.1109/LRA.2023.3323893en
dc.identifier.doi10.1109/LRA.2023.3323893en_US
dc.identifier.issn2377-3766
dc.identifier.issn2377-3774
dc.identifier.otherPURE UUID: 1dad93ca-09db-4892-9229-bbfd7572a9deen_US
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/1dad93ca-09db-4892-9229-bbfd7572a9deen_US
dc.identifier.otherPURE LINK: http://www.scopus.com/inward/record.url?scp=85174822124&partnerID=8YFLogxKen_US
dc.identifier.otherPURE FILEURL: https://research.aalto.fi/files/133842031/Learning-Based_Propulsion_Control_for_Amphibious_Quadruped_Robots.pdfen_US
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/125771
dc.identifier.urnURN:NBN:fi:aalto-202401171446
dc.language.isoenen
dc.publisherIEEE
dc.relation.ispartofseriesIEEE Robotics and Automation Lettersen
dc.relation.ispartofseriesVolume 8, issue 12en
dc.rightsopenAccessen
dc.subject.keywordamphibious robotsen_US
dc.subject.keywordQuadruped robotsen_US
dc.subject.keywordreinforcement learningen_US
dc.subject.keywordrobot learningen_US
dc.titleLearning-Based Propulsion Control for Amphibious Quadruped Robots With Dynamic Adaptation to Changing Environmenten
dc.typeA1 Alkuperäisartikkeli tieteellisessä aikakauslehdessäfi
dc.type.versionacceptedVersion
Files
Collections
[article-cris] Sähkötekniikan korkeakoulu / ELEC