Dimensionality reduction for trajectory learning from demonstration

Programming by demonstration is an attractive model for allowing both experts and non-experts to command robots' actions. In this work, we contribute an approach for learning precise reaching trajectories for robotic manipulators. We use dimensionality reduction to smooth the example trajectories and transform their representation to a space more amenable to planning. Key to this approach is the careful selection of neighboring points within and between trajectories. This algorithm is capable of creating efficient, collision-free plans even under typical real-world training conditions such as incomplete sensor coverage and lack of an environment model, without imposing additional requirements upon the user such as constraining the types of example trajectories provided. Experimental results are presented to validate this approach.

[1]  Brett Browning,et al.  Learning by demonstration with critique from a human teacher , 2007, 2007 2nd ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[2]  K. Dautenhahn,et al.  Imitation in Animals and Artifacts , 2002 .

[3]  Jun Nakanishi,et al.  Trajectory formation for imitation with nonlinear dynamical systems , 2001, Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next Millennium (Cat. No.01CH37180).

[4]  J. Tenenbaum,et al.  A global geometric framework for nonlinear dimensionality reduction. , 2000, Science.

[5]  Christopher G. Atkeson,et al.  Policies based on trajectory libraries , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[6]  W. Smart,et al.  Speeding up Reinforcement Learning using Manifold Representations: Preliminary Results , 2005 .

[7]  Maja J. Mataric,et al.  A spatio-temporal extension to Isomap nonlinear dimension reduction , 2004, ICML.

[8]  Manuela M. Veloso,et al.  Confidence-based policy learning from demonstration using Gaussian mixture models , 2007, AAMAS '07.

[9]  Bernhard Schölkopf,et al.  Learning with Local and Global Consistency , 2003, NIPS.

[10]  Lydia E. Kavraki,et al.  Randomized preprocessing of configuration for fast path planning , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[11]  David M. Bradley,et al.  Boosting Structured Prediction for Imitation Learning , 2006, NIPS.

[12]  Matthias Hein,et al.  Manifold Denoising as Preprocessing for Finding Natural Representations of Data , 2007, AAAI.

[13]  Ales Ude,et al.  Planning of joint trajectories for humanoid robots using B-spline wavelets , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[14]  C.H. Lee.  A phase space spline smoother for fitting trajectories , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[15]  Stefano Caselli,et al.  Trajectory reconstruction with NURBS curves for robot programming by demonstration , 2005, 2005 International Symposium on Computational Intelligence in Robotics and Automation.

[16]  Christopher G. Atkeson,et al.  Learning from observation using primitives , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[17]  Anthony Stentz,et al.  Optimal and efficient path planning for partially-known environments , 1994, Proceedings of the 1994 IEEE International Conference on Robotics and Automation.

[18]  S. LaValle,et al.  Randomized Kinodynamic Planning , 2001 .

[19]  Reid G. Simmons,et al.  Learning Sequential Composition Plans Using Reduced-Dimensionality Examples , 2009, AAAI Spring Symposium: Agents that Learn from Human Teachers.

[20]  David Eppstein,et al.  MESH GENERATION AND OPTIMAL TRIANGULATION , 1992 .

[21]  Rüdiger Dillmann,et al.  Interactive generation of flexible robot programs , 1998, Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146).

[22]  Aude Billard,et al.  Dynamical System Modulation for Robot Learning via Kinesthetic Demonstrations , 2008, IEEE Transactions on Robotics.

[23]  O. C. Jenkins,et al.  2 D Subspaces for User-Driven Robot Grasping , 2007 .

[24]  William T. Freeman,et al.  Understanding belief propagation and its generalizations , 2003 .

[25]  Nathan Delson,et al.  Robot programming by human demonstration: adaptation and inconsistency in constrained motion , 1996, Proceedings of IEEE International Conference on Robotics and Automation.