Advertisement

Rapid Humanoid Motion Learning through Coordinated, Parallel Evolution

  • Marijn Stollenga
  • Jürgen Schmidhuber
  • Faustino Gomez
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8575)

Abstract

Planning movements for humanoid robots is still a major challenge due to the very high degrees-of-freedom involved. Most humanoid control frameworks incorporate dynamical constraints related to a task that require detailed knowledge of the robot’s dynamics, making them impractical as efficient planning. In previous work, we introduced a novel planning method that uses an inverse kinematics solver called Natural Gradient Inverse Kinematics (NGIK) to build task-relevant roadmaps (graphs in task space representing robot configurations that satisfy task constraints) by searching the configuration space via the Natural Evolution Strategies (NES) algorithm. The approach places minimal requirements on the constraints, allowing for complex planning in the task space. However, building a roadmap via NGIK is too slow for dynamic environments. In this paper, the approach is scaled-up to a fully-parallelized implementation where additional constraints coordinate the interaction between independent NES searches running on separate threads. Parallelization yields a 12× speedup that moves this promising planning method a major step closer to working in dynamic environments.

Keywords

Robotics planning parallel search NES 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    libann: A library for approximate nearest neighbor searching, http://www.cs.umd.edu/~mount/ANN/
  2. 2.
    Solid: Collision detection library, http://www.dtecta.com/
  3. 3.
    Badger, J.M., Hart, S.W., Yamokoski, J.D.: Towards autonomous operation of robonaut 2 (2011)Google Scholar
  4. 4.
    Berenson, D., Srinivasa, S.S., Ferguson, D., Kuffner, J.J.: Manipulation planning on constraint manifolds. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pp. 625–632. IEEE (2009)Google Scholar
  5. 5.
    Berenson, D., Srinivasa, S., Kuffner, J.: Task space regions a framework for pose-constrained manipulation planning. The International Journal of Robotics Research 30(12), 1435–1460 (2011)CrossRefGoogle Scholar
  6. 6.
    Frank, M., Leitner, J., Stollenga, M., Harding, S., Förster, A., Schmidhuber, J.: The modular behavioral environment for humanoids and other robots (MoBeE). In: ICINCO, pp. 304–313. SciTePress (2012) ISBN 978-989-8565-22-8Google Scholar
  7. 7.
    Glasmachers, T., Schaul, T., Yi, S., Wierstra, D., Schmidhuber, J.: Exponential natural evolution strategies. In: Proceedings of the 12th Annual Conference on Genetic and Evolutionary Computation, pp. 393–400. ACM (2010)Google Scholar
  8. 8.
    Hauser, K., Ng-Thow-Hing, V., Gonzalez-Baños, H.: Multi-modal motion planning for a humanoid robot manipulation task. Robotics Research, 307–317 (2011)Google Scholar
  9. 9.
    Hsu, D., Latombe, J.-C., Motwani, R.: Path planning in expansive configuration spaces. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), vol. 3, pp. 2719–2726 (1997)Google Scholar
  10. 10.
    Kalakrishnan, M., Chitta, S., Theodorou, E., Pastor, P., Schaal, S.: Stomp: Stochastic trajectory optimization for motion planning. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pp. 4569–4574. IEEE (2011)Google Scholar
  11. 11.
    Kallmann, M., Huang, Y., Backman, R.: A skill-based motion planning framework for humanoids. In: Proceedings of the International Conference on Robotics and Automation (ICRA), pp. 2507–2514. IEEE (2010)Google Scholar
  12. 12.
    Kavraki, L.E., Svestka, P., Latombe, J.C., Overmars, M.H.: Probabilistic roadmaps for path planning in high-dimensional configuration spaces. IEEE Transactions on Robotics and Automation 12(4), 566–580 (1996)CrossRefGoogle Scholar
  13. 13.
    Desktop-HPC Lab. First results for swift on a 64-core amd opteron 6376, https://community.dur.ac.uk/pedro.gonnet/?p=269
  14. 14.
    LaValle, S.M.: Planning algorithms. Cambridge University Press (2006)Google Scholar
  15. 15.
    Reinders, J.: Intel threading building blocks: outfitting C++ for multi-core processor parallelism. O’Reilly Media, Inc. (2010)Google Scholar
  16. 16.
    Sentis, L., Khatib, O.: A whole-body control framework for humanoids operating in human environments. In: Proceedings of IEEE International Conference on Robotics and Automation (ICRA), pp. 2641–2648. IEEE (2006)Google Scholar
  17. 17.
    Stollenga, M., Pape, L., Frank, M., Leitner, J., Förster, A., Schmidhuber, J.: Task-relevant roadmaps: A framework for humanoid motion planning. In: IEEE International Conference on Intelligent Robots and Systems (IROS), pp. 5772–5778 (2013)Google Scholar
  18. 18.
    Tsagarakis, N.G., Metta, G., Sandini, G., Vernon, D., Beira, R., Becchi, F., Righetti, L., Santos-Victor, J., Ijspeert, A.J., Carrozza, M.C., et al.: iCub: the design and realization of an open humanoid platform for cognitive and neuroscience research. Advanced Robotics 21(10), 1151–1175 (2007)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Marijn Stollenga
    • 1
  • Jürgen Schmidhuber
    • 1
  • Faustino Gomez
    • 1
  1. 1.USI-SUPSIIDSIAManno-LuganoSwitzerland

Personalised recommendations