Advertisement

Automated Robot Skill Learning from Demonstration for Various Robot Systems

  • Lisa GutzeitEmail author
  • Alexander Fabisch
  • Christoph Petzoldt
  • Hendrik Wiese
  • Frank Kirchner
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11793)

Abstract

Transferring human movements to robotic systems is of high interest to equip the systems with new behaviors without expert knowledge. Typically, skills are often only learned for a very specific setup and a certain robot. We propose a modular framework to learn skills that is applicable on different robotic systems without adaptations. Our work builds on the recently introduced BesMan Learning Platform, which comprises the full workflow to transfer human demonstrations to a system, including automatized behavior segmentation, imitation learning, reinforcement learning for motion refinement, and methods to generalize to related tasks. For this paper, we extend this approach in order that different skills can be imitated by various systems in an automated fashion with a minimal amount of configuration, e.g., definition of the target system and environment. For this, we focus on the imitation of the demonstrated movements and show their transferability without movement refinement. We demonstrate the generality of the approach on a large dataset, consisting of about 700 throwing demonstrations. Nearly all of these human demonstrations are successfully transferred to four different robot target systems, namely Universal Robot’s UR5 and UR10, KUKA LBR iiwa, and DFKI’s robot COMPI. An analysis of the quality of the imitated movement on the real UR5 robot shows that useful throws can be executed on the system which can be used as starting points for further movement refinement.

Keywords

Behavior learning Learning from demonstration Behavior segmentation Imitation learning Transfer learning Manipulation Robotics 

Notes

Acknowledgements

This work was supported through grants from the German Federal Ministry for Economic Affairs and Energy (BMWi, No 50RA1703, No 50RA1701), one grant from the European Union’s Horizon 2020 research and innovation program (No H2020-FOF 2016 723853), and part of the work was done in a collaboration with Intel Labs China. We would like to thank Intel Corp. for financial support.

References

  1. 1.
    Argall, B.D., Chernova, S., Veloso, M., Browning, B.: A survey of robot learning from demonstration. Robot. Auton. Syst. 57(5), 469–483 (2009)CrossRefGoogle Scholar
  2. 2.
    Bargsten, V., de Gea Fernández, J.: Compi: Development of a 6-DOF compliant robot arm for human-robot cooperation. In: Proceedings of the 8th International Workshop on Human-Friendly Robotics. Technische Universitaet Muenchen (TUM) (2015)Google Scholar
  3. 3.
    Fabisch, A.: A Comparison of Policy Search in Joint Space and Cartesian Space for Refinement of Skills. In: Berns, K., Görges, D. (eds.) RAAD 2019. AISC, vol. 980, pp. 301–309. Springer, Cham (2020).  https://doi.org/10.1007/978-3-030-19648-6_35CrossRefGoogle Scholar
  4. 4.
    Fabisch, A.: pytransform3d: 3D transformations for python. J. Open Source Softw. 4, 1159 (2019).  https://doi.org/10.21105/joss.01159CrossRefGoogle Scholar
  5. 5.
    Gleicher, M.: Retargetting motion to new characters. In: Proceedings of the 25th Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH 1998, pp. 33–42. ACM, New York (1998).  https://doi.org/10.1145/280814.280820
  6. 6.
    Gutzeit, L., Otto, M., Kirchner, E.A.: Simple and robust automatic detection and recognition of human movement patterns in tasks of different complexity. In: Physiological Computing Systems. Springer (2019, submitted)Google Scholar
  7. 7.
    Gutzeit, L., et al.: The BesMan learning platform for automated robot skill learning. Front. Robot. AI 5, 43 (2018).  https://doi.org/10.3389/frobt.2018.00043CrossRefGoogle Scholar
  8. 8.
    Gutzeit, L., Kirchner, E.A.: Automatic detection and recognition of human movement patterns in manipulation tasks. In: Proceedings of the 3rd International Conference on Physiological Computing Systems (2016)Google Scholar
  9. 9.
    Hansen, N., Ostermeier, A.: Completely derandomized self-adaptation in evolution strategies. Evol. Comput. 9, 159–195 (2001)CrossRefGoogle Scholar
  10. 10.
    Ijspeert, A.J., Nakanishi, J., Hoffmann, H., Pastor, P., Schaal, S.: Dynamical movement primitives: learning attractor models for motor behaviors. Neural Comput. 25(2), 328–373 (2013)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Maeda, G.J., Ewerton, M., Koert, D., Peters, J.: Acquiring and generalizing the embodiment mapping from human observations to robot skills. IEEE Robot. Autom. Lett. (RA-L) 1(2), 784–791 (2016).  https://doi.org/10.1109/LRA.2016.2525038CrossRefGoogle Scholar
  12. 12.
    Michieletto, S., Chessa, N., Menegatti, E.: Learning how to approach industrial robot tasks from natural demonstrations. In: 2013 IEEE Workshop on Advanced Robotics and its Social Impacts, pp. 255–260, November 2013.  https://doi.org/10.1109/ARSO.2013.6705538
  13. 13.
    Morasso, P.: Spatial control of arm movements. Exp. Brain Res. 42, 223–227 (1981)CrossRefGoogle Scholar
  14. 14.
    Nehaniv, C.L., Dautenhahn, K., Dautenhahn, K.: Imitation in Animals and Artifacts. MIT Press, Cambridge (2002)zbMATHGoogle Scholar
  15. 15.
    Pastor, P., Hoffmann, H., Asfour, T., Schaal, S.: Learning and generalization of motor skills by learning from demonstration. In: IEEE International Conference on Robotics and Automation, pp. 763–768 (2009)Google Scholar
  16. 16.
    Pollard, N.S., Hodgins, J.K., Riley, M.J., Atkeson, C.G.: Adapting human motion for the control of a humanoid robot. In: Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No. 02CH37292). vol. 2, pp. 1390–1397, May 2002.  https://doi.org/10.1109/ROBOT.2002.1014737
  17. 17.
    Sakoe, H., Chiba, S.: Dynamic programming algorithm optimization for spoken word recognition. IEEE Trans. Acoust. Speech Sig. Process. 26(1), 43–49 (1978).  https://doi.org/10.1109/TASSP.1978.1163055CrossRefzbMATHGoogle Scholar
  18. 18.
    Senger, L., Schröer, M., Metzen, J.H., Kirchner, E.A.: Velocity-based multiple change-point inference for unsupervised segmentation of human movement behavior. In: Proceedings of the 22th International Conference on Pattern Recognition (ICPR2014), pp. 4564–4569 (2014).  https://doi.org/10.1109/ICPR.2014.781

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Lisa Gutzeit
    • 1
    Email author
  • Alexander Fabisch
    • 2
  • Christoph Petzoldt
    • 1
    • 3
  • Hendrik Wiese
    • 2
  • Frank Kirchner
    • 1
    • 2
  1. 1.Robotics Research GroupUniversity of BremenBremenGermany
  2. 2.German Research Center for Artificial Intelligence (DFKI GmbH), Robotics Innovation CenterBremenGermany
  3. 3.BIBA - Bremer Institut für Produktion und Logistik GmbH at the University of BremenBremenGermany

Personalised recommendations