Effect of base rotation on the controllability of a redundant soft robotic arm

Hiroki Shigemune, Vito Cacucciolo, Matteo Cianchetti, Hideyuki Sawada, Shuji Hashimoto, Cecilia Laschi

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

    Abstract

    Soft robotic arms have gained popularity in the recent years because of their dexterity, robustness and safe interaction with humans. However, since these arms are subject to non-linear mechanics and are intrinsically under-actuated, their control still present many challenges. Octopus arms are one of the most popular biological models for soft robotics. It is known that the octopus reaching movement consists in two steps: (1) the rotation of the arm's base towards the target, and (2) the extension of the arm to reach the target. From a robotics point of view, the rotation of the base adds one additional degree of freedom to an already hyper-redundant system. Therefore, its role in the effectiveness of the control is ambiguous. In this work, we investigate the role of the base rotation for learning an effective reaching strategy. We conduct numerical experiments based on a mathematical model of the mechanics of the octopus arm in water and a simple neural network enabling to encode the control strategy through optimization learning. The network node corresponding to the base rotation is switched on or off for comparison. We test the reaching success rate with and without base rotation with targets in various positions. The results show that the addition of the base rotation can be highly beneficial or even detrimental, based on the position of the target. Nonetheless, globally the addition of base rotation affects the control strategy and expand the reachable regions.

    Original languageEnglish
    Title of host publication2018 IEEE International Conference on Soft Robotics, RoboSoft 2018
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages350-355
    Number of pages6
    ISBN (Electronic)9781538645161
    DOIs
    Publication statusPublished - 2018 Jul 5
    Event1st IEEE International Conference on Soft Robotics, RoboSoft 2018 - Livorno, Italy
    Duration: 2018 Apr 242018 Apr 28

    Other

    Other1st IEEE International Conference on Soft Robotics, RoboSoft 2018
    CountryItaly
    CityLivorno
    Period18/4/2418/4/28

    Fingerprint

    Robotic arms
    Controllability
    Robotics
    Target
    Mechanics
    Control Strategy
    Redundant System
    Biological Models
    Degrees of freedom (mechanics)
    Ambiguous
    Expand
    Degree of freedom
    Numerical Experiment
    Neural Networks
    Mathematical Model
    Mathematical models
    Robustness
    Neural networks
    Water
    Optimization

    Keywords

    • Artificial Neural Networks
    • Bio-inspired robotics
    • Genetic Algorithms
    • Indirect Encoding
    • Mathematical modeling
    • Optimization
    • Soft robotics

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Control and Optimization
    • Modelling and Simulation
    • Mechanical Engineering

    Cite this

    Shigemune, H., Cacucciolo, V., Cianchetti, M., Sawada, H., Hashimoto, S., & Laschi, C. (2018). Effect of base rotation on the controllability of a redundant soft robotic arm. In 2018 IEEE International Conference on Soft Robotics, RoboSoft 2018 (pp. 350-355). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ROBOSOFT.2018.8404944

    Effect of base rotation on the controllability of a redundant soft robotic arm. / Shigemune, Hiroki; Cacucciolo, Vito; Cianchetti, Matteo; Sawada, Hideyuki; Hashimoto, Shuji; Laschi, Cecilia.

    2018 IEEE International Conference on Soft Robotics, RoboSoft 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 350-355.

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

    Shigemune, H, Cacucciolo, V, Cianchetti, M, Sawada, H, Hashimoto, S & Laschi, C 2018, Effect of base rotation on the controllability of a redundant soft robotic arm. in 2018 IEEE International Conference on Soft Robotics, RoboSoft 2018. Institute of Electrical and Electronics Engineers Inc., pp. 350-355, 1st IEEE International Conference on Soft Robotics, RoboSoft 2018, Livorno, Italy, 18/4/24. https://doi.org/10.1109/ROBOSOFT.2018.8404944
    Shigemune H, Cacucciolo V, Cianchetti M, Sawada H, Hashimoto S, Laschi C. Effect of base rotation on the controllability of a redundant soft robotic arm. In 2018 IEEE International Conference on Soft Robotics, RoboSoft 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 350-355 https://doi.org/10.1109/ROBOSOFT.2018.8404944
    Shigemune, Hiroki ; Cacucciolo, Vito ; Cianchetti, Matteo ; Sawada, Hideyuki ; Hashimoto, Shuji ; Laschi, Cecilia. / Effect of base rotation on the controllability of a redundant soft robotic arm. 2018 IEEE International Conference on Soft Robotics, RoboSoft 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 350-355
    @inproceedings{3dbeb9b21ef54de2905e8583579ba8cf,
    title = "Effect of base rotation on the controllability of a redundant soft robotic arm",
    abstract = "Soft robotic arms have gained popularity in the recent years because of their dexterity, robustness and safe interaction with humans. However, since these arms are subject to non-linear mechanics and are intrinsically under-actuated, their control still present many challenges. Octopus arms are one of the most popular biological models for soft robotics. It is known that the octopus reaching movement consists in two steps: (1) the rotation of the arm's base towards the target, and (2) the extension of the arm to reach the target. From a robotics point of view, the rotation of the base adds one additional degree of freedom to an already hyper-redundant system. Therefore, its role in the effectiveness of the control is ambiguous. In this work, we investigate the role of the base rotation for learning an effective reaching strategy. We conduct numerical experiments based on a mathematical model of the mechanics of the octopus arm in water and a simple neural network enabling to encode the control strategy through optimization learning. The network node corresponding to the base rotation is switched on or off for comparison. We test the reaching success rate with and without base rotation with targets in various positions. The results show that the addition of the base rotation can be highly beneficial or even detrimental, based on the position of the target. Nonetheless, globally the addition of base rotation affects the control strategy and expand the reachable regions.",
    keywords = "Artificial Neural Networks, Bio-inspired robotics, Genetic Algorithms, Indirect Encoding, Mathematical modeling, Optimization, Soft robotics",
    author = "Hiroki Shigemune and Vito Cacucciolo and Matteo Cianchetti and Hideyuki Sawada and Shuji Hashimoto and Cecilia Laschi",
    year = "2018",
    month = "7",
    day = "5",
    doi = "10.1109/ROBOSOFT.2018.8404944",
    language = "English",
    pages = "350--355",
    booktitle = "2018 IEEE International Conference on Soft Robotics, RoboSoft 2018",
    publisher = "Institute of Electrical and Electronics Engineers Inc.",

    }

    TY - GEN

    T1 - Effect of base rotation on the controllability of a redundant soft robotic arm

    AU - Shigemune, Hiroki

    AU - Cacucciolo, Vito

    AU - Cianchetti, Matteo

    AU - Sawada, Hideyuki

    AU - Hashimoto, Shuji

    AU - Laschi, Cecilia

    PY - 2018/7/5

    Y1 - 2018/7/5

    N2 - Soft robotic arms have gained popularity in the recent years because of their dexterity, robustness and safe interaction with humans. However, since these arms are subject to non-linear mechanics and are intrinsically under-actuated, their control still present many challenges. Octopus arms are one of the most popular biological models for soft robotics. It is known that the octopus reaching movement consists in two steps: (1) the rotation of the arm's base towards the target, and (2) the extension of the arm to reach the target. From a robotics point of view, the rotation of the base adds one additional degree of freedom to an already hyper-redundant system. Therefore, its role in the effectiveness of the control is ambiguous. In this work, we investigate the role of the base rotation for learning an effective reaching strategy. We conduct numerical experiments based on a mathematical model of the mechanics of the octopus arm in water and a simple neural network enabling to encode the control strategy through optimization learning. The network node corresponding to the base rotation is switched on or off for comparison. We test the reaching success rate with and without base rotation with targets in various positions. The results show that the addition of the base rotation can be highly beneficial or even detrimental, based on the position of the target. Nonetheless, globally the addition of base rotation affects the control strategy and expand the reachable regions.

    AB - Soft robotic arms have gained popularity in the recent years because of their dexterity, robustness and safe interaction with humans. However, since these arms are subject to non-linear mechanics and are intrinsically under-actuated, their control still present many challenges. Octopus arms are one of the most popular biological models for soft robotics. It is known that the octopus reaching movement consists in two steps: (1) the rotation of the arm's base towards the target, and (2) the extension of the arm to reach the target. From a robotics point of view, the rotation of the base adds one additional degree of freedom to an already hyper-redundant system. Therefore, its role in the effectiveness of the control is ambiguous. In this work, we investigate the role of the base rotation for learning an effective reaching strategy. We conduct numerical experiments based on a mathematical model of the mechanics of the octopus arm in water and a simple neural network enabling to encode the control strategy through optimization learning. The network node corresponding to the base rotation is switched on or off for comparison. We test the reaching success rate with and without base rotation with targets in various positions. The results show that the addition of the base rotation can be highly beneficial or even detrimental, based on the position of the target. Nonetheless, globally the addition of base rotation affects the control strategy and expand the reachable regions.

    KW - Artificial Neural Networks

    KW - Bio-inspired robotics

    KW - Genetic Algorithms

    KW - Indirect Encoding

    KW - Mathematical modeling

    KW - Optimization

    KW - Soft robotics

    UR - http://www.scopus.com/inward/record.url?scp=85050682765&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85050682765&partnerID=8YFLogxK

    U2 - 10.1109/ROBOSOFT.2018.8404944

    DO - 10.1109/ROBOSOFT.2018.8404944

    M3 - Conference contribution

    AN - SCOPUS:85050682765

    SP - 350

    EP - 355

    BT - 2018 IEEE International Conference on Soft Robotics, RoboSoft 2018

    PB - Institute of Electrical and Electronics Engineers Inc.

    ER -