Learning to Achieve Different Levels of Adaptability for Human–Robot Collaboration Utilizing a Neuro-dynamical System

Shingo Murata, Yuxi Li, Hiroaki Arie, Tetsuya Ogata, Shigeki Sugano

    Research output: Contribution to journalArticle

    3 Citations (Scopus)

    Abstract

    Intelligent robots are expected to collaboratively work with humans in dynamically changing daily-life environments. To realize successful human–robot collaboration, robots need to deal with latent spatiotemporal complexity in the workspace and the task. To overcome this crucial issue, three levels of adaptability—motion modification, action selection, and role switching—should be considered. This study demonstrates that a single hierarchically organized neuro-dynamical system called a multiple timescale recurrent neural network (MTRNN) can achieve these levels of adaptability by utilizing hierarchical and bidirectional information processing. The system is implemented in a humanoid robot and the robot is required to learn to perform collaborative tasks in which some parts must be performed by a human partner and others by the robot. Experimental results show that the robot can perform collaborative tasks under dynamically changing environments, including both learned and unlearned situations, thanks to different levels of adaptability acquired in the system.

    Original languageEnglish
    JournalIEEE Transactions on Cognitive and Developmental Systems
    DOIs
    Publication statusAccepted/In press - 2018 Jan 23

    Fingerprint

    Dynamical systems
    Robots
    Intelligent robots
    Recurrent neural networks

    Keywords

    • adaptation
    • Collaboration
    • Complexity theory
    • generalization
    • Human–robot collaboration
    • neuro-robotics
    • Probabilistic logic
    • recurrent neural network (RNN).
    • Robots
    • Switches
    • Task analysis
    • Trajectory

    ASJC Scopus subject areas

    • Software
    • Artificial Intelligence

    Cite this

    @article{e7fa3d47b91d407aaf8374795839938b,
    title = "Learning to Achieve Different Levels of Adaptability for Human–Robot Collaboration Utilizing a Neuro-dynamical System",
    abstract = "Intelligent robots are expected to collaboratively work with humans in dynamically changing daily-life environments. To realize successful human–robot collaboration, robots need to deal with latent spatiotemporal complexity in the workspace and the task. To overcome this crucial issue, three levels of adaptability—motion modification, action selection, and role switching—should be considered. This study demonstrates that a single hierarchically organized neuro-dynamical system called a multiple timescale recurrent neural network (MTRNN) can achieve these levels of adaptability by utilizing hierarchical and bidirectional information processing. The system is implemented in a humanoid robot and the robot is required to learn to perform collaborative tasks in which some parts must be performed by a human partner and others by the robot. Experimental results show that the robot can perform collaborative tasks under dynamically changing environments, including both learned and unlearned situations, thanks to different levels of adaptability acquired in the system.",
    keywords = "adaptation, Collaboration, Complexity theory, generalization, Human–robot collaboration, neuro-robotics, Probabilistic logic, recurrent neural network (RNN)., Robots, Switches, Task analysis, Trajectory",
    author = "Shingo Murata and Yuxi Li and Hiroaki Arie and Tetsuya Ogata and Shigeki Sugano",
    year = "2018",
    month = "1",
    day = "23",
    doi = "10.1109/TCDS.2018.2797260",
    language = "English",
    journal = "IEEE Transactions on Cognitive and Developmental Systems",
    issn = "2379-8920",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",

    }

    TY - JOUR

    T1 - Learning to Achieve Different Levels of Adaptability for Human–Robot Collaboration Utilizing a Neuro-dynamical System

    AU - Murata, Shingo

    AU - Li, Yuxi

    AU - Arie, Hiroaki

    AU - Ogata, Tetsuya

    AU - Sugano, Shigeki

    PY - 2018/1/23

    Y1 - 2018/1/23

    N2 - Intelligent robots are expected to collaboratively work with humans in dynamically changing daily-life environments. To realize successful human–robot collaboration, robots need to deal with latent spatiotemporal complexity in the workspace and the task. To overcome this crucial issue, three levels of adaptability—motion modification, action selection, and role switching—should be considered. This study demonstrates that a single hierarchically organized neuro-dynamical system called a multiple timescale recurrent neural network (MTRNN) can achieve these levels of adaptability by utilizing hierarchical and bidirectional information processing. The system is implemented in a humanoid robot and the robot is required to learn to perform collaborative tasks in which some parts must be performed by a human partner and others by the robot. Experimental results show that the robot can perform collaborative tasks under dynamically changing environments, including both learned and unlearned situations, thanks to different levels of adaptability acquired in the system.

    AB - Intelligent robots are expected to collaboratively work with humans in dynamically changing daily-life environments. To realize successful human–robot collaboration, robots need to deal with latent spatiotemporal complexity in the workspace and the task. To overcome this crucial issue, three levels of adaptability—motion modification, action selection, and role switching—should be considered. This study demonstrates that a single hierarchically organized neuro-dynamical system called a multiple timescale recurrent neural network (MTRNN) can achieve these levels of adaptability by utilizing hierarchical and bidirectional information processing. The system is implemented in a humanoid robot and the robot is required to learn to perform collaborative tasks in which some parts must be performed by a human partner and others by the robot. Experimental results show that the robot can perform collaborative tasks under dynamically changing environments, including both learned and unlearned situations, thanks to different levels of adaptability acquired in the system.

    KW - adaptation

    KW - Collaboration

    KW - Complexity theory

    KW - generalization

    KW - Human–robot collaboration

    KW - neuro-robotics

    KW - Probabilistic logic

    KW - recurrent neural network (RNN).

    KW - Robots

    KW - Switches

    KW - Task analysis

    KW - Trajectory

    UR - http://www.scopus.com/inward/record.url?scp=85040970496&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85040970496&partnerID=8YFLogxK

    U2 - 10.1109/TCDS.2018.2797260

    DO - 10.1109/TCDS.2018.2797260

    M3 - Article

    AN - SCOPUS:85040970496

    JO - IEEE Transactions on Cognitive and Developmental Systems

    JF - IEEE Transactions on Cognitive and Developmental Systems

    SN - 2379-8920

    ER -