Deep Reinforcement Learning-Based Control of Stewart Platform With Parametric Simulation in ROS and Gazebo

Basit Öğe Kaydı
dc.authoridTavakol Aghaei, Vahid/0000-0002-4876-1015
dc.authoridİkizoğlu, Serhat/0000-0003-2394-7988
dc.authorwosidTavakol Aghaei, Vahid/AES-9479-2022
dc.authorwosidİkizoğlu, Serhat/ABB-1783-2020
dc.contributor.authorYadavari, Hadi
dc.contributor.authorAghaei, Vahid Tavakol
dc.contributor.authorIkizoglu, Serhat
dc.date.accessioned2024-05-19T14:46:29Z
dc.date.available2024-05-19T14:46:29Z
dc.date.issued2023
dc.departmentİstinye Üniversitesien_US
dc.description.abstractThe Stewart platform is an entirely parallel robot with mechanical differences from typical serial robotic manipulators, which has a wide application area ranging from flight and driving simulators to structural test platforms. This work concentrates on learning to control a complex model of the Stewart platform using state-of-the-art deep reinforcement learning (DRL) algorithms. In this regard, to enhance the reliability of the learning performance and to have a test bed capable of mimicking the behavior of the system completely, a precisely designed simulation environment is presented. Therefore, we first design a parametric representation for the kinematics of the Stewart platform in Gazebo and robot operating system (ROS) and integrate it with a Python class to conveniently generate the structures in simulation description format (SDF). Then, to control the system, we benefit from three DRL algorithms: the asynchronous advantage actor-critic (A3C), the deep deterministic policy gradient (DDPG), and the proximal policy optimization (PPO) to learn the control gains of a proportional integral derivative (PID) controller for a given reaching task. We chose to apply these algorithms due to the Stewart platform's continuous action and state spaces, making them well-suited for our problem, where exact controller tuning is a crucial task. The simulation results show that the DRL algorithms can successfully learn the controller gains, resulting in satisfactory control performance.en_US
dc.identifier.doi10.1115/1.4056971
dc.identifier.issn1942-4302
dc.identifier.issn1942-4310
dc.identifier.issue3en_US
dc.identifier.scopus2-s2.0-85151427194en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.urihttps://doi.org10.1115/1.4056971
dc.identifier.urihttps://hdl.handle.net/20.500.12713/5531
dc.identifier.volume15en_US
dc.identifier.wosWOS:000988824300014en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherAsmeen_US
dc.relation.ispartofJournal of Mechanisms and Robotics-Transactions of the Asmeen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.snmz20240519_kaen_US
dc.subjectReinforcement Learningen_US
dc.subjectDeep Learningen_US
dc.subjectControlen_US
dc.subjectRosen_US
dc.subjectGazeboen_US
dc.subjectStewart Platformen_US
dc.subjectParallel Platformsen_US
dc.titleDeep Reinforcement Learning-Based Control of Stewart Platform With Parametric Simulation in ROS and Gazeboen_US
dc.typeArticleen_US

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu