Towards Robust Skill Generalization: Unifying Learning from Demonstration and Motion Planning

In this paper, we present Combined Learning from demonstration And Motion Planning (CLAMP) as an efficient approach to skill learning and generalizable skill reproduction. CLAMP combines the strengths of Learning from Demonstration (LfD) and motion planning into a unifying framework. We carry out probabilistic inference to find trajectories which are optimal with respect to a given skill and also feasible in different scenarios. We use factor graph optimization to speed up inference. To encode optimality, we provide a new probabilistic skill model based on a stochastic dynamical system. This skill model requires minimal parameter tuning to learn, is suitable to encode skill constraints, and allows efficient inference. Preliminary experimental results showing skill generalization over initial robot state and unforeseen obstacles are presented.

[1]  A. E. Hoerl,et al.  Ridge regression: biased estimation for nonorthogonal problems , 2000 .

[2]  Jun Nakanishi,et al.  Learning Attractor Landscapes for Learning Motor Primitives , 2002, NIPS.

[3]  X. Jin.  Factor graphs and the Sum-Product Algorithm , 2002 .

[4]  W. Wong,et al.  On ψ-Learning , 2003 .

[5]  Rajesh P. N. Rao,et al.  Dynamic Imitation in a Humanoid Robot through Nonparametric Probabilistic Inference , 2006, Robotics: Science and Systems.

[6]  Steven M. LaValle,et al.  Planning algorithms , 2006 .

[7]  Philip Chan,et al.  Toward accurate dynamic time warping in linear time and space , 2007, Intell. Data Anal..

[8]  Aude Billard,et al.  On Learning, Representing, and Generalizing a Task in a Humanoid Robot , 2007, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[9]  Stefan Schaal,et al.  Learning and generalization of motor skills by learning from demonstration , 2009, 2009 IEEE International Conference on Robotics and Automation.

[10]  Brett Browning,et al.  A survey of robot learning from demonstration , 2009, Robotics Auton. Syst..

[11]  Michalis K. Titsias,et al.  Variational Learning of Inducing Variables in Sparse Gaussian Processes , 2009, AISTATS.

[12]  Darwin G. Caldwell,et al.  Learning-based control strategy for safe human-robot interaction exploiting task and robot redundancies , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[13]  Markus Schneider,et al.  Robot Learning by Demonstration with local Gaussian process regression , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[14]  Jun Morimoto,et al.  Task-Specific Generalization of Discrete and Periodic Dynamic Movement Primitives , 2010, IEEE Transactions on Robotics.

[15]  Aude Billard,et al.  Learning Stable Nonlinear Dynamical Systems With Gaussian Mixture Models , 2011, IEEE Transactions on Robotics.

[16]  Ron Alterovitz,et al.  Demonstration-Guided Motion Planning , 2011, ISRR.

[17]  Jan Peters,et al.  Probabilistic Movement Primitives , 2013, NIPS.

[18]  Siddhartha S. Srinivasa,et al.  CHOMP: Covariant Hamiltonian optimization for motion planning , 2013, Int. J. Robotics Res..

[19]  Markus Schneider,et al.  LAT: A simple Learning from Demonstration method , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[20]  Incremental Sparse GP Regression for Continuous-Time Trajectory Estimation and Mapping , 2015, ISRR.

[21]  Simo Särkkä,et al.  Batch nonlinear continuous-time trajectory estimation as exactly sparse Gaussian process regression , 2014, Autonomous Robots.

[22]  Siddhartha S. Srinivasa,et al.  Movement primitives via optimization , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[23]  Byron Boots,et al.  Motion Planning as Probabilistic Inference using Gaussian Processes and Factor Graphs , 2016, Robotics: Science and Systems.

[24]  Byron Boots,et al.  Gaussian Process Motion planning , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[25]  Jan Peters,et al.  Demonstration based trajectory optimization for generalizable robot motions , 2016, 2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids).

[26]  Sylvain Calinon,et al.  A tutorial on task-parameterized movement learning and retrieval , 2015, Intelligent Service Robotics.

[27]  Byron Boots,et al.  Motion planning with graph-based trajectories and Gaussian process inference , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[28]  Byron Boots,et al.  Approximately optimal continuous-time motion planning and control via Probabilistic Inference , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[29]  Jan Peters,et al.  Guiding Trajectory Optimization by Demonstrated Distributions , 2017, IEEE Robotics and Automation Letters.

[30]  Byron Boots,et al.  Simultaneous Trajectory Estimation and Planning via Probabilistic Inference , 2017, Robotics: Science and Systems.

[31]  Byron Boots,et al.  Continuous-time Gaussian process motion planning via probabilistic inference , 2017, Int. J. Robotics Res..