REFLEXIVE COLLISION RESPONSE WITH VIRTUAL SKIN - Roadmap Planning Meets Reinforcement Learning

Mikhail Frank, Alexander Förster, Jürgen Schmidhuber

2012

Abstract

Prevalent approaches to motion synthesis for complex robots offer either the ability to build up knowledge of feasible actions through exploration, or the ability to react to a changing environment, but not both. This work proposes a simple integration of roadmap planning with reflexive collision response, which allows the roadmap representation to be transformed into a Markov Decision Process. Consequently, roadmap planning is extended to changing environments, and the adaptation of the map can be phrased as a reinforcement learning problem. An implementation of the reflexive collision response is provided, such that the reinforcement learning problem can be studied in an applied setting. The feasibility of the software is analyzed in terms of runtime performance, and its functionality is demonstrated on the iCub humanoid robot.

References

  1. Brock, O. and Khatib, O. (2000). Real-time re-planning in high-dimensional configuration spaces using sets of homotopic paths. In Robotics and Automation, 2000. Proceedings. ICRA'00. IEEE International Conference on, volume 1, pages 550-555. IEEE.
  2. De Santis, A., Albu-Schaffer, A., Ott, C., Siciliano, B., and Hirzinger, G. (2007). The skeleton algorithm for selfcollision avoidance of a humanoid manipulator. In Advanced intelligent mechatronics, 2007 IEEE/ASME international conference on, pages 1-6. IEEE.
  3. Dietrich, A., Wimbock, T., Taubig, H., Albu-Schaffer, A., and Hirzinger, G. (2011). Extensions to reactive selfcollision avoidance for torque and position controlled humanoids. In Robotics and Automation (ICRA), 2011 IEEE International Conference on, pages 3455-3462. IEEE.
  4. Diftler, M., Mehling, J., Abdallah, M., Radford, N., Bridgwater, L., Sanders, A., Askew, S., Linn, D., Yamokoski, J., Permenter, F., Hargrave, B., Platt, R., Savely, R., and Ambrose, R. (2011). Robonaut 2: The first humanoid robot in space. In Proceedings of IEEE International Conference on Robotics and Automation (ICRA).
  5. Gupta, K. (1986). Kinematic analysis of manipulators using the zero reference position description. The International Journal of Robotics Research, 5(2):5.
  6. Iossifidis, I. and Schoner, G. (2004). Autonomous reaching and obstacle avoidance with the anthropomorphic arm of a robotic assistant using the attractor dynamics approach. In Robotics and Automation, 2004. Proceedings. ICRA'04. 2004 IEEE International Conference on, volume 5, pages 4295-4300. IEEE.
  7. Iossifidis, I. and Schoner, G. (2006). Reaching with a redundant anthropomorphic robot arm using attractor dynamics. VDI BERICHTE, 1956:45.
  8. Khatib, O. (1986). Real-time obstacle avoidance for manipulators and mobile robots. The international journal of robotics research, 5(1):90.
  9. Kim, J. and Khosla, P. (1992). Real-time obstacle avoidance using harmonic potential functions. Robotics and Automation, IEEE Transactions on, 8(3):338-349.
  10. Kusuda, Y. (2008). Toyota's violin-playing robot. Industrial Robot: An International Journal, 35(6):504-506.
  11. Latombe, J., Kavraki, L., Svestka, P., and Overmars, M. (1996). Probabilistic roadmaps for path planning in high-dimensional configuration spaces. IEEE Transactions on Robotics and Automation, 12(4):566-580.
  12. LaValle, S. (1998). Rapidly-exploring random trees: A new tool for path planning. Technical report, Computer Science Dept., Iowa State University.
  13. LaValle, S. (2006). Planning algorithms. Cambridge Univ Pr.
  14. Li, T. and Shie, Y. (2007). An incremental learning approach to motion planning with roadmap management. Journal of Information Science and Engineering, 23(2):525-538.
  15. Metta, G., Sandini, G., Vernon, D., Natale, L., and Nori, F. (2008). The icub humanoid robot: an open platform for research in embodied cognition. In Proceedings of the 8th Workshop on Performance Metrics for Intelligent Systems, pages 50-56. ACM.
  16. Perez, A., Karaman, S., Shkolnik, A., Frazzoli, E., Teller, S., and Walter, M. (2011). Asymptotically-optimal path planning for manipulation using incremental sampling-based algorithms. In Intelligent Robots and Systems (IROS), 2011 IEEE/RSJ International Conference on, pages 4307-4313. IEEE.
  17. Schoner, G. and Dose, M. (1992). A dynamical systems approach to task-level system integration used to plan and control autonomous vehicle motion. Robotics and Autonomous Systems, 10(4):253-267.
  18. Stasse, O., Escande, A., Mansard, N., Miossec, S., Evrard, P., and Kheddar, A. (2008). Real-time (self)-collision avoidance task on a hrp-2 humanoid robot. In Robotics and Automation, 2008. ICRA 2008. IEEE International Conference on, pages 3200-3205. IEEE.
  19. Sugiura, H., Gienger, M., Janssen, H., and Goerick, C. (2007). Real-time collision avoidance with whole body motion control for humanoid robots. In Intelligent Robots and Systems, 2007. IROS 2007. IEEE/RSJ International Conference on, pages 2053- 2058. IEEE.
  20. Takagi, S. (2006). Toyota partner robots. Journal of the Robotics Society of Japan, 24(2):62.
  21. van den Bergen, G. (2004). Collision Detection in Interactive 3D Environments. Morgan Kaufmann.
Download


Paper Citation


in Harvard Style

Frank M., Förster A. and Schmidhuber J. (2012). REFLEXIVE COLLISION RESPONSE WITH VIRTUAL SKIN - Roadmap Planning Meets Reinforcement Learning . In Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: SSIR, (ICAART 2012) ISBN 978-989-8425-95-9, pages 642-651. DOI: 10.5220/0003883206420651


in Bibtex Style

@conference{ssir12,
author={Mikhail Frank and Alexander Förster and Jürgen Schmidhuber},
title={REFLEXIVE COLLISION RESPONSE WITH VIRTUAL SKIN - Roadmap Planning Meets Reinforcement Learning},
booktitle={Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: SSIR, (ICAART 2012)},
year={2012},
pages={642-651},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003883206420651},
isbn={978-989-8425-95-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: SSIR, (ICAART 2012)
TI - REFLEXIVE COLLISION RESPONSE WITH VIRTUAL SKIN - Roadmap Planning Meets Reinforcement Learning
SN - 978-989-8425-95-9
AU - Frank M.
AU - Förster A.
AU - Schmidhuber J.
PY - 2012
SP - 642
EP - 651
DO - 10.5220/0003883206420651