Hierarchical End-to-end Control Policy for Multi-degree-of-freedom Manipulators

Cheol Hui Min, Jae Bok Song

    Research output: Contribution to journalArticlepeer-review

    5 Citations (Scopus)

    Abstract

    In recent years, several control policies for a multi-degree-of-freedom (DOF) manipulator using deep reinforcement learning have been proposed. To avoid complexity, previous studies have applied a number of constraints on the high-dimensional state-action space, thus hindering generalized policy function learning. In this study, the control problem is addressed by in-troducing a hierarchical reinforcement learning method that can learn the end-to-end control policy of a multi-DOF manipula-tor without any constraints on the state-action space. The proposed method learns hierarchical policy using two off-policy methods. Using human demonstration data and a newly proposed data-correction method, controlling the multi-DOF manipu-lator in an end-to-end manner is shown to outperform the non-hierarchical deep reinforcement learning methods.

    Original languageEnglish
    Pages (from-to)3296-3311
    Number of pages16
    JournalInternational Journal of Control, Automation and Systems
    Volume20
    Issue number10
    DOIs
    Publication statusPublished - 2022 Oct

    Bibliographical note

    Publisher Copyright:
    © 2022, ICROS, KIEE and Springer.

    Keywords

    • Deep reinforcement learning
    • demonstration-based learning
    • end-to-end robot control
    • hierarchical reinforcement learning

    ASJC Scopus subject areas

    • Control and Systems Engineering
    • Computer Science Applications

    Fingerprint

    Dive into the research topics of 'Hierarchical End-to-end Control Policy for Multi-degree-of-freedom Manipulators'. Together they form a unique fingerprint.

    Cite this