Common Dimensional Autoencoder for Identifying Agonist-Antagonist Muscle Pairs in Musculoskeletal Robots

  • Hiroaki Masuda
  • Shuhei IkemotoEmail author
  • Koh Hosoda
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 867)


One of the distinctive features of musculoskeletal systems is the redundancy provided by agonist-antagonist muscle pairs. To identify agonist-antagonist muscle pairs in a musculoskeletal robot, however, is difficult as it requires complex structures to mimic human physiology. Thus, we propose a method to identify agonist-antagonist muscle pairs in a complex musculoskeletal robot using motor commands. Moreover, the common dimensional autoencoder, where the encoded feature has identical dimensions to the original input vector, is used to separate the image and the kernel spaces for each time period. Finally, we successfully confirmed the efficacy of our method by applying a 2-link planar manipulator to a 3-pairs-6-muscles configuration.


Musculoskeletal robot Redundancy Autoencoder 


  1. [Hosoda2012]
    Hosoda, K., Sekimoto, S., Nishigori, Y., Takamuku, S., Ikemoto, S.: Anthropomorphic muscular-skeletal robotic upper limb for understanding embodied intelligence. Adv. Robot. 26(7), 729–744 (2012)CrossRefGoogle Scholar
  2. [Marques2010]
    Marques, H., Jantsch, M., Wittmeier, S., Holland, S., Alessandro, C., Diamond, A., Lungarella, M., Knight, R.: ECCE1: the first of a series of anthropomimetic musculoskeletal upper torsos. In: Proceedings of 10th IEEE-RAS International Conference on Humanoid Robots, pp. 391–396 (2010)Google Scholar
  3. [Shirafuji2014]
    Shirafuji, S., Ikemoto, S., Hosoda, K.: Development of a tendon-driven robotic finger for an anthropomorphic robotic hand. Int. J. Robot. Res. 33, 677–693 (2014)CrossRefGoogle Scholar
  4. [Ozawa2009]
    Ozawa, R., Hashirii, K., Kobayashi, H.: Design and control of underactuated tendon-driven mechanisms. In: Proceedings of IEEE International Conference on Robotics and Automation, pp. 1522–1527 (2009)Google Scholar
  5. [Sawada2012]
    Sawada, D., Ozawa, R.: Joint control of tendon-driven mechanisms with branching tendons. In: Proceedings of IEEE International Conference on Robotics and Automation, pp. 1501–1507 (2012)Google Scholar
  6. [Hartmann2012]
    Hartmann, C., Boedecker, J., Obst, O., Ikemoto, S., Asada, M.: Real-time inverse dynamics learning for musculoskeletal robots based on echo state Gaussian process regression. In: Proceedings of Robotics: Science and Systems (2012)Google Scholar
  7. [Diamond2014]
    Diamond, A., Holland, O.E.: Reaching control of a full-torso, modelled musculoskeletal robot using muscle synergies emergent under reinforcement learning. Bioinspiration Biomimetics 9, 016015 (2014)CrossRefGoogle Scholar
  8. [Ikemoto2018]
    Ikemoto, S., Duan, Y., Takahara, K., Kumi, T., Hosoda, K.: Robot control based on analytical models extracted from a neural network. In: The 1st International Symposium on Systems Intelligence Division (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Osaka UniversityToyonaka, OsakaJapan

Personalised recommendations