Autonomous Learning of Internal Dynamic Models for Reaching Tasks

  • Tadej PetričEmail author
  • Aleš Ude
  • Auke J. Ijspeert
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 371)


The paper addresses the problem of learning internal task-specific dynamic models for a reaching task. Using task-specific dynamic models is crucial for achieving both high tracking accuracy and compliant behaviour, which improves safety concerns while working in unstructured environment or with humans. The proposed approach uses programming by demonstration to learn new task-related movements encoded as Compliant Movement Primitives (CMPs). CMPs are a combination of position trajectories encoded in a form of Dynamic Movement Primitives (DMPs) and corresponding task-specific Torque Primitives (TPs) encoded as a linear combination of kernel functions. Unlike the DMPs, TPs cannot be directly acquired from user demonstrations. Inspired by the human sensorimotor learning ability we propose a novel method which autonomously learns task-specific TPs, based on a given kinematic trajectory in DMPs.


Compliant movement primitives Task-specific dynamics Learning Dynamic movement primitives 



The research activities leading to the results presented in this paper were supported by the Sciex-NMSCH project no. 14.069.


  1. 1.
    Nakanishi, J., Morimoto, J., Endo, G., Cheng, G., Schaal, S., Kawato, M.: Learning from demonstration and adaptation of biped locomotion. Robot. Auton. Syst. 47(2–3), 79–91 (2004)CrossRefGoogle Scholar
  2. 2.
    Ude, A., Atkeson, C.G., Riley, M.: Programming full-body movements for humanoid robots by observation. Robot. Auton. Syst. 47, 93–108 (2004)CrossRefGoogle Scholar
  3. 3.
    Hersch, M., Guenter, F., Calinon, S., Billard, A.: Dynamical system modulation for robot learning via kinaesthetic demonstrations. IEEE Trans. Rob. 24(6), 1463–1467 (2008)CrossRefGoogle Scholar
  4. 4.
    Schaal, S., Mohajerian, P., Ijspeert, A.: Dynamics systems vs. optimal control—a unifying view. Prog. Brain Res. 165(1), 425–445 (2007)CrossRefGoogle Scholar
  5. 5.
    Ulmen, J., Cutkosky, M.: A robust, low-cost and low-noise artificial skin for human-friendly robots. In: Proceedings of IEEE International Conference on Robotics and Automation, pp. 4836–4841 (2010)Google Scholar
  6. 6.
    Shin, D., Sardellitti, I., Park, Y.L., Khatib, O., Cutkosky, M.: Design and control of a bio-inspired human-friendly robot. Int. J. Robot. Res. 29(5), 571–584 (2009)CrossRefGoogle Scholar
  7. 7.
    Buchli, J., Stulp, F., Theodorou, E., Schaal, S.: Learning variable impedance control. Int. J. Robot. Res. 30(7), 820–833 (2011)CrossRefGoogle Scholar
  8. 8.
    Haddadin, S., Albu-Schaffer, A., Hirzinger, G.: Requirements for safe robots: measurements, analysis and new insights. Int. J. Robot. Res. 28(11–12), 1507–1527 (2009)CrossRefGoogle Scholar
  9. 9.
    Basa, D., Schneider, A.: Movement primitives learning point-to-point movements on an elastic limb using dynamic movement primitives. Robot. Auton. Syst. 66, 55 (2015)CrossRefGoogle Scholar
  10. 10.
    Gams, A., Petrič, T.: Adapting periodic motion primitives to external feedback: modulating and changing the motion. In: 23rd International Conference on Robotics in Alpe-Adria-Danube Region (RAAD), pp. 1–6 (2014)Google Scholar
  11. 11.
    Gopalan, N., Deisenroth, M.P., Peters, J.: Feedback error learning for rhythmic motor primitives. In: Proceedings of the IEEE International Conference on Robotics and Automation, pp. 1317–1322 (May 2013)Google Scholar
  12. 12.
    Ijspeert, A.J., Nakanishi, J., Hoffmann, H., Pastor, P., Schaal, S.: Dynamical movement primitives: learning attractor models for motor behaviors. Neural Comput. 25, 328–373 (2013)MathSciNetCrossRefzbMATHGoogle Scholar
  13. 13.
    Gomi, H., Kawato, M.: Neural network control for a closed-loop system using feedback-error-learning. Neural Networks 6, 933 (1993)CrossRefGoogle Scholar
  14. 14.
    Krakauer, J.W., Ghilardi, M.F., Ghez, C.: Independent learning of internal models for kinematic and dynamic control of reaching. Nat. Neurosci. 2(11), 1026–1031 (1999)CrossRefGoogle Scholar
  15. 15.
    Oztop, E., Kawato, M., Arbib, M.: Mirror neurons and imitation: a computationally guided review. Neural Networks 19, 254–271 (2006)CrossRefzbMATHGoogle Scholar
  16. 16.
    Wolpert, D.M., Kawato, M.: Multiple paired forward and inverse models for motor control. Neural Networks J. Int. Neural Network Soc. 11(7–8), 1317–1329 (1998)CrossRefGoogle Scholar
  17. 17.
    Ude, A., Gams, A., Asfour, T., Morimoto, J.: Task-specific generalization of discrete and periodic dynamic movement primitives. IEEE Trans. Rob. 26(5), 800–815 (2010)CrossRefGoogle Scholar
  18. 18.
    Žlajpah, L.: Simulation in robotics. Math. Comput. Simul. 79, 879–897 (2008)CrossRefzbMATHGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Biorobotics LaboratoryEPFL, École Polytechnique Fédérale de LausanneLausanneSwitzerland
  2. 2.JSI, Jozef Stefan InstituteLjubljanaSlovenia

Personalised recommendations