Trajectory prediction: learning to map situations to robot trajectories

ABSTRACT

Trajectory planning and optimization is a fundamental problem in articulated robotics. Algorithms used typically for this problem compute optimal trajectories from scratch in a new situation. In effect, extensive data is accumulated containing situations together with the respective optimized trajectories - but this data is in practice hardly exploited. The aim of this paper is to learn from this data. Given a new situation we want to predict a suitable trajectory which only needs minor refinement by a conventional optimizer. Our approach has two essential ingredients. First, to generalize from previous situations to new ones we need an appropriate situation descriptor - we propose a sparse feature selection approach to find such well-generalizing features of situations. Second, the transfer of previously optimized trajectories to a new situation should not be made in joint angle space - we propose a more efficient task space transfer of old trajectories to new situations. Experiments on a simulated humanoid reaching problem show that we can predict reasonable motion prototypes in new situations for which the refinement is much faster than an optimization from scratch.

REFERENCES

• 1: Paolo Baerlocher , Ronan Boulic, An inverse kinematics architecture enforcing an arbitrary number of strict priority levels, The Visual Computer: International Journal of Computer Graphics, v.20 n.6, p.402-417, August 2004 [doi>10.1007/s00371-004-0244-4]
• 2: Berniker, M., & Kording, K. (2008). Estimating the sources of motor errors for adaptation and generalization. Nature Neuroscience, 11, 1454--1461.
• 3: Bertram, D., Kuffner, J., Dillmann, R., & Asfour, T. (2006). An integrated approach to inverse kinematics and path planning for redundant manipulators. IEEE Int. Conf. on Robotics and Automation (ICRA) (pp. 1874--1879).
• 4: Branicky, M., Knepper, R., & Kuffner, J. (2008). Path and trajectory diversity: Theory and algorithms. IEEE Int. Conf. on Robotics and Automation (ICRA) (pp. 1359--1364).
• 5: Sylvain Calinon , Aude Billard, Recognition and reproduction of gestures using a probabilistic framework combining PCA, ICA and HMM, Proceedings of the 22nd international conference on Machine learning, p.105-112, August 07-11, 2005, Bonn, Germany [doi>10.1145/1102351.1102365]
• 6: Kazuo Hiraki , Akio Sashima , Steven Phillips, From egocentric to allocentric spatial behavior: a computational model of spatial development, Adaptive Behavior, v.6 n.3-4, p.371-391, Winter/Spring 1998 [doi>10.1177/105971239800600302]
• 7: Lydia E. Kavraki , Jean-Claude Latombe , Rajeev Motwani , Prabhakar Raghavan, Randomized query processing in robot path planning, Proceedings of the twenty-seventh annual ACM symposium on Theory of computing, p.353-362, May 29-June 01, 1995, Las Vegas, Nevada, United States [doi>10.1145/225058.225159]
• 8: George Konidaris , Andrew Barto, Autonomous shaping: knowledge transfer in reinforcement learning, Proceedings of the 23rd international conference on Machine learning, p.489-496, June 25-29, 2006, Pittsburgh, Pennsylvania [doi>10.1145/1143844.1143906]
• 9: David G. Lowe, Similarity metric learning for a variable-kernel classifier, Neural Computation, v.7 n.1, p.72-85, Jan. 1995 [doi>10.1162/neco.1995.7.1.72]
• 10: Martin, S., Wright, S., & Sheppard, J. (2007). Offline and online evolutionary bi-directional RRT algorithms for efficient re-planning in dynamic environments. IEEE Int. Conf. on Automation Science and Engineering (CASE). (pp. 1131--1136).
• 11: Y. Nakamura , H. Hanafusa, Optimal redundancy control of robot manipulators, International Journal of Robotics Research, v.6 n.1, p.32-42, Spring 1987 [doi>10.1177/027836498700600103]
• 12: Peshkin, L., & de Jong, E. D. (2002). Context-based policy search: Transfer of experience across problems. ICML-2002 Workshop on Development of Representations.
• 13: Mark Schmidt , Glenn Fung , Rómer Rosales, Fast Optimization Methods for L1 Regularization: A Comparative Study and Two New Approaches, Proceedings of the 18th European conference on Machine Learning, September 17-21, 2007, Warsaw, Poland [doi>10.1007/978-3-540-74958-5_28]
• 14: Bernhard Scholkopf , Alexander J. Smola, Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond, MIT Press, Cambridge, MA, 2001
• 15: Shon, A., Storz, J., & Rao, R. (2007). Towards a real-time bayesian imitation system for a humanoid robot. IEEE Int. Conf. on Robotics and Automation (ICRA) (pp. 2847--2852).
• 16: Stolle, M., & Atkeson, C. (2007). Knowledge transfer using local features. IEEE Int. Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL). (pp. 26--31).
• 17: Todorov, E., & Li, W. (2005). A generalized iterative LQG method for locally-optimal feedback control of constrained nonlinear stochastic systems. Proc. of the American Control Conference (pp. 300--306).
• 18: Wagner, T., Visser, U., & Herzog, O. (2004). Egocentric qualitative spatial knowledge representation for physical robots. Robotics and Autonomous Systems, 49, 25--42.
• 19: Zacharias, F., Borst, C., & Hirzinger, G. (2007). Capturing robot workspace structure: representing robot capabilities. IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS) (pp. 3229--3236).
• 20: Zhang, J., & Knoll, A. (1995). An enhanced optimization approach for generating smooth robot trajectories in the presence of obstacles. Proc. of the European Chinese Automation Conf. (pp. 263--268).

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.6 Learning

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.8 Problem Solving, Control Methods, and Search
          Subjects: Plan execution, formation, and generation
      I.2.9 Robotics
          Subjects: Workcell organization and planning
  I.6 SIMULATION AND MODELING
      I.6.5 Model Development
          Subjects: Modeling methodologies
      I.6.6 Simulation Output Analysis

General Terms:
Algorithms, Design, Performance, Theory