Dimitri: an Open-Source Humanoid Robot with Compliant Joint

  • Christopher Tatsch
  • Ahmadreza Ahmadi
  • Fabrício Bottega
  • Jun Tani
  • Rodrigo da Silva Guerra
Article
  • 47 Downloads

Abstract

We introduce Dimitri, an open-software & open-hardware humanoid robot with 31 DOFs, fitted with cost-effective modular compliant joints and parallel link legs, designed for advanced human-robot interaction research, force-informed object handling and intelligent environment discovery. Our main innovation is in the design of a robust full-body biped humanoid robot equipped with very low-cost polyurethane torsional spring fixed to traditional servo motors and a circuit to measure angular displacement, transforming the system into a series elastic actuator (SEA). In order to illustrate the robot’s qualities in the field of machine learning applied to robotics and manipulation, a multiple timescale recurrent neural network (MTRNN) is implemented, allowing the robot to replicate combined movement sequences earlier taught via interactive demonstration.

Keywords

Humanoid robot Compliant joints MTRNN Neural network 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ahmadi, A., Tatsch, C., Montenegro, F.J.C., Tani, J., Guerra R.D.S.: Dimitri: a low-cost compliant humanoid torso designed for cognitive robotics research. In: Proceedings of the 2016 IEEE Latin American Robotics Symposium (LARS) (2016)Google Scholar
  2. 2.
    Allgeuer, P., Farazi, H., Ficht, G., Schreiber, M., Behnke, S.: The igus humanoid open platform. KI-Künstliche Intelligenz 30(3–4), 315–319 (2016)CrossRefGoogle Scholar
  3. 3.
    Ashby, M., Johnson, K.: Materials and desing: the art and science of material selection in product design. Elsevier Editora Ltda, Rio de Janeiro (2011)Google Scholar
  4. 4.
    Bishop, C.M.: Pattern recognition. Machine Learning (2006)Google Scholar
  5. 5.
    Jeannerod, M.: The representing brain: neural correlates of motor intention and imagery. Behav. Brain Sci. 17(02), 187–202 (1994)CrossRefGoogle Scholar
  6. 6.
    Martins, L.T., Guerra, R.D.S., Tatsch, C., Maciel, E.H., Gerndt, R.: Polyurethane-based modular series elastic upgrade to a robotics actuator. In: Proceedings of the Robot Soccer World Cup XVIII (2015)Google Scholar
  7. 7.
    Martins, L.T., Tatsch, C.A.A., Maciel, E.H., Gerndt, R., Guerra, R.D.S.: A polyurethane-based compliant element for upgrading conventional servos into series elastic actuators. IFAC-PapersOnLine 48(19), 112–117 (2015)CrossRefGoogle Scholar
  8. 8.
    Park, G., Tani, J.: Development of compositional and contextual communicable congruence in robots by using dynamic neural network models. Neural Netw. 72, 109–122 (2015)CrossRefGoogle Scholar
  9. 9.
    Pratt, G., Williamson, M.: Human robot interaction and cooperative robots. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, vol. 1, pp 399–406 (1995)Google Scholar
  10. 10.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. Tech. rep., DTIC Document (1985)Google Scholar
  11. 11.
    Tani, J.: Model-based learning for mobile robot navigation from the dynamical systems perspective. IEEE Trans. Syst. Man Cybern. B Cybern. 26(3), 421–436 (1996)CrossRefGoogle Scholar
  12. 12.
    Yamashita, Y., Tani, J.: Emergence of functional hierarchy in a multiple timescale neural network model: a humanoid robot experiment. PLoS Comput. Biol. 4(11), e1000220 (2008)CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media B.V. 2017

Authors and Affiliations

  • Christopher Tatsch
    • 1
  • Ahmadreza Ahmadi
    • 2
  • Fabrício Bottega
    • 1
  • Jun Tani
    • 3
  • Rodrigo da Silva Guerra
    • 1
  1. 1.Centro de TecnologiaUniversidade Federal de Santa MariaSanta MariaBrazil
  2. 2.Department of Electrical EngineeringKAISTDaejeonKorea
  3. 3.Cognitive Neurorobotics Research UnitOkinawa Institute of Science and Technology (OIST)OkinawaJapan

Personalised recommendations