Advertisement

Demonstration-Guided Motion Planning

  • Gu Ye
  • Ron Alterovitz
Chapter
Part of the Springer Tracts in Advanced Robotics book series (STAR, volume 100)

Abstract

We present demonstration-guided motion planning (DGMP), a new frame-work for planning motions for personal robots to perform household tasks. DGMP combines the strengths of sampling-based motion planning and robot learning from demonstrations to generate plans that (1) avoid novel obstacles in cluttered environments, and (2) learn and maintain critical aspects of the motion required to successfully accomplish a task. Sampling-based motion planning methods are highly effective at computing paths from start to goal configurations that avoid obstacles, but task constraints (e.g. a glass of water must be held upright to avoid a spill) must be explicitly enumerated and programmed. Instead, we use a set of expert demonstrations and automatically extract time-dependent task constraints by learning low variance aspects of the demonstrations, which are correlated with the task constraints. We then introduce multi-component rapidly-exploring roadmaps (MC-RRM), a sampling-based method that incrementally computes a motion plan that avoids obstacles and optimizes a learned cost metric. We demonstrate the effectiveness of DGMP using the Aldebaran Nao robot performing household tasks in a cluttered environment, including moving a spoon full of sugar from a bowl to a cup and cleaning the surface of a table.

Keywords

Motion Planning Motion Feature Dynamic Time Warping Task Constraint Cluttered Environment 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Notes

Acknowledgment

This research was supported in part by the National Science Foundation (NSF) under awards #IIS-0905344 and #IIS-1117127 and by the National Institutes of Health (NIH) under grant #R21EB011628. The authors thank Jenny Womack from the Dept. of Allied Health Sciences for her input and John Thomas and Herman Towles from the Dept. of Computer Science for their help with the experiment setup.

References

  1. 1.
    P. Abbeel, D. Dolgov, A. Ng, S. Thrun, Apprenticeship learning for motion planning with application to parking lot navigation, in Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (Sept. 2008), pp. 1083–1090Google Scholar
  2. 2.
    P. Abbeel, A.Y. Ng, Apprenticeship learning via inverse reinforcement learning, in Proceedings of International Conference on Machine Learning (ICML) (2004)Google Scholar
  3. 3.
    Aldebran Robotics, Aldebran Robotics NAO for education (2010), http://www.aldebaran-robotics.com/en/naoeducation
  4. 4.
    B.D. Argall, S. Chernova, M. Veloso, B. Browning, A survey of robot learning from demonstration. Robot. Auton. Syst. 57, 469–483 (2009)CrossRefGoogle Scholar
  5. 5.
    D. Berenson, T. Simeon, S.S. Srinivasa, Addressing cost-space chasms in manipulation planning, in Proceedings of IEEE International Conference on Robotics and Automation (ICRA) (May 2011), pp. 4561–4568Google Scholar
  6. 6.
    S. Billard, R. Calinon, S. Dillmann, Schaal, Robot programming by demonstration, in Handbook of Robotics, ed. by B. Siciliano, O. Khatib (Springer, 2008), ch. 59, pp. 1371–1394Google Scholar
  7. 7.
    S. Calinon, Robot Programming by Demonstration, 1st edn. (CRC Press Inc, Boca Raton, 2009)Google Scholar
  8. 8.
    S. Calinon, F.D’halluin, D.G. Caldwell, A.G. Billard, Handling of multiple constraints and motion alternatives in a robot programming by demonstration framework, in 9th IEEE—RAS International Conference on Humanoid Robots (Dec. 2009), pp. 582–588Google Scholar
  9. 9.
    S. Calinon, F. Guenter, A. Billard, On learning, representing, and generalizing a task in a humanoid robot. IEEE Trans. Syst. Man Cybern. Part B 37(2), 286–298 (2007)CrossRefGoogle Scholar
  10. 10.
    H. Choset, K.M. Lynch, S. Hutchinson, G. Kantor, W. Burgard, L.E. Kavraki, S. Thrun, Principles of Robot Motion: Theory, Algorithms, and Implementations (MIT Press, 2005)Google Scholar
  11. 11.
    J. Claassens, An RRT-based path planner for use in trajectory imitation, in Proceedings of IEEE International Conference on Robotics and Automation (ICRA) (May 2010), pp. 3090–3095Google Scholar
  12. 12.
    A. Coates, P. Abbeel, A. Ng, Learning for control from multiple demonstrations, in Proceedings of 25th International Conference on Machine Learning (2008), pp. 144–151Google Scholar
  13. 13.
    L. Jaillet, J. Cortes, T. Simeon, Sampling-based path planning on configuration-space costmaps. IEEE Trans. Robot. 26(4), 635–646 (2010)CrossRefGoogle Scholar
  14. 14.
    R. Jakel, S.R. Schmidt-Rohr, M. Losch, R. Dillmann, Representation and constrained planning of manipulation strategies in the context of programming by demonstration, in Proceedings of IEEE International Conference on Robotics and Automation (ICRA) (May 2010), pp. 162–169Google Scholar
  15. 15.
    S. Karaman, E. Frazzoli, Incremental sampling-based algorithms for optimal motion planning, in Proceedings of Robotics: Science and Systems (2010)Google Scholar
  16. 16.
    S.M. LaValle, Planning Algorithms (Cambridge University Press, Cambridge, U.K., 2006)CrossRefzbMATHGoogle Scholar
  17. 17.
    S.J. Lee, Z. Popović, Learning behavior styles with inverse reinforcement learning. ACM Trans. Graph. (SIGGRAPH 2010) 29(4), 122:1–122:7 (2010)Google Scholar
  18. 18.
    J. Mainprice, E. Sisbot, L. Jaillet, J. Cortés, R. Alami, T. Siméon, Planning human-aware motions using a sampling-based costmap planner, in Proceedings of IEEE International Conference on Robotics and Automation (ICRA) (May 2011), pp. 5012–5017Google Scholar
  19. 19.
    H. Mayer, I. Nagy, A. Knoll, E.U. Braun, R. Lange, R. Bauernschmitt, Adaptive control for human-robot skilltransfer: trajectory planning based on fluid dynamics, in Proceedings of IEEE International Conference on Robotics and Automation (ICRA) (April 2007), pp. 1800–1807Google Scholar
  20. 20.
    P. Pastor, H. Hoffmann, T. Asfour, S. Schaal, Learning and generalization of motor skills by learning from demonstration, in Proceedings of IEEE International Conference on Robotics and Automation (ICRA) (May 2009), pp. 763–768Google Scholar
  21. 21.
    R.B. Rusu, I.A. Sucan, B.P. Gerkey, S. Chitta, M. Beetz, L.E. Kavraki, Real-time perception-guided motion planning for a personal robot, in Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (Oct. 2009), pp. 4245–4252Google Scholar
  22. 22.
    H. Sakoe, S. Chiba, Dynamic programming algorithm optimization for spoken word recognition. IEEE Trans. Acoust. Speech Sig. Process. 26(1), 43–49 (1978)CrossRefzbMATHGoogle Scholar
  23. 23.
    D. Silver, J.A. Bagnell, A. Stentz, Learning from demonstration for autonomous navigation in complex unstructured terrain. Int. J. Robot. Res. 29(12), 1565–1592 (2010)CrossRefGoogle Scholar
  24. 24.
    J. van den Berg, S. Miller, D. Duckworth, H. Hu, A. Wan, X.-Y. Fu, K. Goldberg, P. Abbeel, Superhuman performance of surgical tasks by robots using iterative learning from human-guided demonstrations, in Proceedings of IEEE International Conference on Robotics and Automation (ICRA) (May 2010), pp. 2074–2081Google Scholar

Copyright information

© Springer International Publishing Switzerland 2017

Authors and Affiliations

  1. 1.Department of Computer ScienceThe University of North CarolinaChapel HillUSA

Personalised recommendations