Learning arm motion strategies for balance recovery of humanoid robots

Masaki Nakada, Brian Allen, Shigeo Morishima, Demetri Terzopoulos

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    5 Citations (Scopus)

    Abstract

    Humans are able to robustly maintain balance in the presence of disturbances by combining a variety of control strategies using posture adjustments and limb motions. Such responses can be applied to balance control in two-armed bipedal robots. We present an upper-body control strategy for improving balance in a humanoid robot. Our method improves on lowerbody balance techniques by introducing an arm rotation strategy (ARS). The ARS uses Q-learning to map sensed state to the appropriate arm control torques. We demonstrate successful balance in a physically-simulated humanoid robot, in response to perturbations that overwhelm lower-body balance strategies alone.

    Original languageEnglish
    Title of host publicationProceedings - EST 2010 - 2010 International Conference on Emerging Security Technologies, ROBOSEC 2010 - Robots and Security, LAB-RS 2010 - Learning and Adaptive Behavior in Robotic Systems
    Pages165-170
    Number of pages6
    DOIs
    Publication statusPublished - 2010
    Event2010 International Conference on Emerging Security Technologies, EST 2010, Robots and Security, ROBOSEC 2010, Learning and Adaptive Behavior in Robotic Systems, LAB-RS 2010 - Canterbury
    Duration: 2010 Sep 62010 Sep 8

    Other

    Other2010 International Conference on Emerging Security Technologies, EST 2010, Robots and Security, ROBOSEC 2010, Learning and Adaptive Behavior in Robotic Systems, LAB-RS 2010
    CityCanterbury
    Period10/9/610/9/8

    Fingerprint

    Robots
    Recovery
    Torque control

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Human-Computer Interaction
    • Control and Systems Engineering

    Cite this

    Nakada, M., Allen, B., Morishima, S., & Terzopoulos, D. (2010). Learning arm motion strategies for balance recovery of humanoid robots. In Proceedings - EST 2010 - 2010 International Conference on Emerging Security Technologies, ROBOSEC 2010 - Robots and Security, LAB-RS 2010 - Learning and Adaptive Behavior in Robotic Systems (pp. 165-170). [5600269] https://doi.org/10.1109/EST.2010.18

    Learning arm motion strategies for balance recovery of humanoid robots. / Nakada, Masaki; Allen, Brian; Morishima, Shigeo; Terzopoulos, Demetri.

    Proceedings - EST 2010 - 2010 International Conference on Emerging Security Technologies, ROBOSEC 2010 - Robots and Security, LAB-RS 2010 - Learning and Adaptive Behavior in Robotic Systems. 2010. p. 165-170 5600269.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Nakada, M, Allen, B, Morishima, S & Terzopoulos, D 2010, Learning arm motion strategies for balance recovery of humanoid robots. in Proceedings - EST 2010 - 2010 International Conference on Emerging Security Technologies, ROBOSEC 2010 - Robots and Security, LAB-RS 2010 - Learning and Adaptive Behavior in Robotic Systems., 5600269, pp. 165-170, 2010 International Conference on Emerging Security Technologies, EST 2010, Robots and Security, ROBOSEC 2010, Learning and Adaptive Behavior in Robotic Systems, LAB-RS 2010, Canterbury, 10/9/6. https://doi.org/10.1109/EST.2010.18
    Nakada M, Allen B, Morishima S, Terzopoulos D. Learning arm motion strategies for balance recovery of humanoid robots. In Proceedings - EST 2010 - 2010 International Conference on Emerging Security Technologies, ROBOSEC 2010 - Robots and Security, LAB-RS 2010 - Learning and Adaptive Behavior in Robotic Systems. 2010. p. 165-170. 5600269 https://doi.org/10.1109/EST.2010.18
    Nakada, Masaki ; Allen, Brian ; Morishima, Shigeo ; Terzopoulos, Demetri. / Learning arm motion strategies for balance recovery of humanoid robots. Proceedings - EST 2010 - 2010 International Conference on Emerging Security Technologies, ROBOSEC 2010 - Robots and Security, LAB-RS 2010 - Learning and Adaptive Behavior in Robotic Systems. 2010. pp. 165-170
    @inproceedings{a2626b6e19c149adb28b71fa5106c277,
    title = "Learning arm motion strategies for balance recovery of humanoid robots",
    abstract = "Humans are able to robustly maintain balance in the presence of disturbances by combining a variety of control strategies using posture adjustments and limb motions. Such responses can be applied to balance control in two-armed bipedal robots. We present an upper-body control strategy for improving balance in a humanoid robot. Our method improves on lowerbody balance techniques by introducing an arm rotation strategy (ARS). The ARS uses Q-learning to map sensed state to the appropriate arm control torques. We demonstrate successful balance in a physically-simulated humanoid robot, in response to perturbations that overwhelm lower-body balance strategies alone.",
    author = "Masaki Nakada and Brian Allen and Shigeo Morishima and Demetri Terzopoulos",
    year = "2010",
    doi = "10.1109/EST.2010.18",
    language = "English",
    isbn = "9780769541754",
    pages = "165--170",
    booktitle = "Proceedings - EST 2010 - 2010 International Conference on Emerging Security Technologies, ROBOSEC 2010 - Robots and Security, LAB-RS 2010 - Learning and Adaptive Behavior in Robotic Systems",

    }

    TY - GEN

    T1 - Learning arm motion strategies for balance recovery of humanoid robots

    AU - Nakada, Masaki

    AU - Allen, Brian

    AU - Morishima, Shigeo

    AU - Terzopoulos, Demetri

    PY - 2010

    Y1 - 2010

    N2 - Humans are able to robustly maintain balance in the presence of disturbances by combining a variety of control strategies using posture adjustments and limb motions. Such responses can be applied to balance control in two-armed bipedal robots. We present an upper-body control strategy for improving balance in a humanoid robot. Our method improves on lowerbody balance techniques by introducing an arm rotation strategy (ARS). The ARS uses Q-learning to map sensed state to the appropriate arm control torques. We demonstrate successful balance in a physically-simulated humanoid robot, in response to perturbations that overwhelm lower-body balance strategies alone.

    AB - Humans are able to robustly maintain balance in the presence of disturbances by combining a variety of control strategies using posture adjustments and limb motions. Such responses can be applied to balance control in two-armed bipedal robots. We present an upper-body control strategy for improving balance in a humanoid robot. Our method improves on lowerbody balance techniques by introducing an arm rotation strategy (ARS). The ARS uses Q-learning to map sensed state to the appropriate arm control torques. We demonstrate successful balance in a physically-simulated humanoid robot, in response to perturbations that overwhelm lower-body balance strategies alone.

    UR - http://www.scopus.com/inward/record.url?scp=78649430034&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=78649430034&partnerID=8YFLogxK

    U2 - 10.1109/EST.2010.18

    DO - 10.1109/EST.2010.18

    M3 - Conference contribution

    SN - 9780769541754

    SP - 165

    EP - 170

    BT - Proceedings - EST 2010 - 2010 International Conference on Emerging Security Technologies, ROBOSEC 2010 - Robots and Security, LAB-RS 2010 - Learning and Adaptive Behavior in Robotic Systems

    ER -