Autonomous Robots

, Volume 40, Issue 1, pp 109–124 | Cite as

Learning to plan for constrained manipulation from demonstrations

  • Mike Phillips
  • Victor Hwang
  • Sachin Chitta
  • Maxim Likhachev


Motion planning in high dimensional state spaces, such as for mobile manipulation, is a challenging problem. Constrained manipulation, e.g., opening articulated objects like doors or drawers, is also hard since sampling states on the constrained manifold is expensive. Further, planning for such tasks requires a combination of planning in free space for reaching a desired grasp or contact location followed by planning for the constrained manipulation motion, often necessitating a slow two step process in traditional approaches. In this work, we show that combined planning for such tasks can be dramatically accelerated by providing user demonstrations of the constrained manipulation motions. In particular, we show how such demonstrations can be incorporated into a recently developed framework of planning with experience graphs which encode and reuse previous experiences. We focus on tasks involving articulation constraints, e.g., door opening or drawer opening, where the motion of the object itself involves only a single degree of freedom. We provide experimental results with the PR2 robot opening a variety of such articulated objects using our approach, using full-body manipulation (after receiving kinesthetic demonstrations). We also provide simulated results highlighting the benefits of our approach for constrained manipulation tasks.


Motion planning Manipulation planning Experience graphs 



We thank Willow Garage for their support of this work. This research was also sponsored by ARL, under the Robotics CTA program Grant W911NF-10-2-0016.


  1. Aine, S., Swaminathan, S., Narayanan, V., Hwang, V., & Likhachev, M. (2014). Multi-heuristic A*. In: Proceedings of Robotics: Science and Systems. Berkeley, USA.Google Scholar
  2. Argall, B., Chernova, S., Veloso, M. M., & Browning, B. (2009). A survey of robot learning from demonstration. Robotics and Autonomous Systems, 57(5), 469–483.CrossRefGoogle Scholar
  3. Berenson, D., Abbeel, P., & Goldberg, K. (2012). A robot path planning framework that learns from experience. In: ICRA.Google Scholar
  4. Berenson, D., Srinivasa, S., Ferguson, D., & Kuffner, J. (2009). Manipulation planning on constraint manifolds. In: IEEE International Conference on Robotics and Automation (ICRA ’09).Google Scholar
  5. Bruce, J., & Veloso, M. (2002). Real-time randomized path planning for robot navigation. In: IEEE/RSJ International Conference on Intelligent Robots and Systems.Google Scholar
  6. Burns, E., Lemons, S., Ruml, W., & Zhou, R. (2010). Best-first heuristic search for multicore machines. Journal of Artificial Intelligence Research, 39, 689–743.zbMATHMathSciNetGoogle Scholar
  7. Cohen, B. J., Chitta, S., & Likhachev, M. (2014). Single- and dual-arm motion planning with heuristic search. IJRR, 33(2), 305–320.Google Scholar
  8. Helmert, M. (2006). The fast downward planning system. Journal of Artificial Intelligence Research (JAIR), 26, 191–246.zbMATHCrossRefGoogle Scholar
  9. Jetchev, N., & Toussaint, M. (2010). Trajectory prediction: Learning to map situations to robot trajectories. In: IEEE International Conference on Robotics and Automation.Google Scholar
  10. Jiang, X., & Kallmann, M. (2007). Learning humanoid reaching tasks in dynamic environments. In: IEEE International Conference on Intelligent Robots and Systems.Google Scholar
  11. Jr., Kuffner, J.J.K., & LaValle, S.M. (2000). Rrt-connect: An efficient approach to single-query path planning. In: ICRA.Google Scholar
  12. Kavraki, L. E., Svestka, P., Latombe, J. C., & Overmars, M. H. (1996). Probabilistic roadmaps for path planning in high-dimensional configuration spaces. IEEE Transactions on Robotics and Automation, 12(4), 566–580.CrossRefGoogle Scholar
  13. Kober, J., & Peters, J. (2009). Policy search for motor primitives in robotics. In: Advances in neural information processing systems 22 (nips 2008), Cambridge: MIT press.Google Scholar
  14. Koenig, S., & Likhachev, M. (2002). D* lite. AAAI, pp. 476–483.Google Scholar
  15. Kormushev, P., Calinon, S., & Caldwell, D.G. (2010). Robot motor skill coordination with EM-based reinforcement learning. In: Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), (pp. 3232–3237). Taipei.Google Scholar
  16. Likhachev, M., Gordon, G., & Thrun, S. (2003). ARA*: Anytime A* with provable bounds on sub-optimality. In: Advances in Neural Information Processing Systems (NIPS) 16. Cambridge: MIT Press.Google Scholar
  17. Oriolo, G., & Mongillo, C. (2005). Motion planning for mobile manipulators along given end-effector paths. In: Proceedings of the 2005 IEEE International Conference on Robotics and Automation, ICRA 2005, (pp. 2154–2160). Barcelona.Google Scholar
  18. Pastor, P., Hoffmann, H., Asfour, T., & Schaal, S. (2009). Learning and generalization of motor skills by learning from demonstration. In: International Conference on Robotics and Automation (icra2009).Google Scholar
  19. Phillips, M., Cohen, B.J., Chitta, S., & Likhachev, M. (2012). E-graphs: Bootstrapping planning with experience graphs. In: Robotics: Science and Systems.Google Scholar
  20. Phillips, M., Dornbush, A., Chitta, S., & Likhachev, M. (2013). Anytime incremental planning with e-graphs. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA).Google Scholar
  21. Phillips, M., Likhachev, M., & Koenig, S. (2014). Pa*se: Parallel A* for slow expansions. In: Proceedings of the International Conference on Automated Planning and Scheduling (ICAPS).Google Scholar
  22. Pohl, I. (1970). First results on the effect of error in heuristic search. Machine Intelligence, 5, 219–236.MathSciNetGoogle Scholar
  23. Porta Pleite, J. M., Jalliet, L., & Bohigas Nadal, O. (2012). Randomized path planning on manifolds based on higher-dimensional continuation. International Journal of Robotics Research, 31(2), 201–215.CrossRefGoogle Scholar
  24. Sakoe, H., & Chiba, S. (1978). Dynamic programming algorithm optimization for spoken word recognition. In: IEEE Transactions on Acoustics, Speech, and Signal Processing, 26.Google Scholar
  25. Sciavicco, L., Siciliano, B., & Sciavicco, B. (2000). Modelling and Control of Robot Manipulators (2nd ed.). Secaucus: Springer.zbMATHCrossRefGoogle Scholar
  26. Stentz, A.T. (1995). The focussed d* algorithm for real-time replanning. In: Proceedings of the International Joint Conference on Artificial Intelligence.Google Scholar
  27. Stolle, M., & Atkeson, C. (2006). Policies based on trajectory libraries. In: IEEE International Conference on Robotics and Automation.Google Scholar
  28. Sucan, I. A., & Chitta, S. (2012). Motion planning with constraints using configuration space approximations. IEEE. Algarve: Vilamoura.Google Scholar
  29. Valenzano, R., Sturtevant, N., Schaeffer, J., & Buro, K. (2010). Simultaneously searching with multiple settings: An alternative to parameter tuning for suboptimal single-agent search algorithms. In: International Conference on Automated Planning and Scheduling.Google Scholar
  30. Yang, Y., & Brock, O. (2010). Elastic roadmaps—motion generation for autonomous mobile manipulation. Autonomous Robots, 28(1), 113–130.CrossRefGoogle Scholar
  31. Zucker, M., Kuffner, J., & Branicky, M. (2007). Multipartite rrts for rapid replanning in dynamic environments. In: IEEE International Conference on Robotics and Automation.Google Scholar

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  • Mike Phillips
    • 1
  • Victor Hwang
    • 1
  • Sachin Chitta
    • 2
  • Maxim Likhachev
    • 1
  1. 1.Carnegie Mellon University PittsburghUSA
  2. 2.Willow GarageMenlo ParkUSA

Personalised recommendations