Generalizing pouring actions between objects using warped parameters

One of the key challenges for learning manipulation skills is generalizing between different objects. The robot should adapt both its actions and the task constraints to the geometry of the object being manipulated. In this paper, we propose computing geometric parameters of novel objects by warping known objects to match their shape. We refer to the parameters computed in this manner as warped parameters, as they are defined as functions of the warped object's point cloud. The warped parameters form the basis of the features for the motor skill learning process, and they are used to generalize between different objects. The proposed method was successfully evaluated on a pouring task both in simulation and on a real robot.

[1]  Jochen J. Steil,et al.  Task-level imitation learning using variance-based movement optimization , 2009, 2009 IEEE International Conference on Robotics and Automation.

[2]  Pieter Abbeel,et al.  Learning from Demonstrations Through the Use of Non-rigid Registration , 2013, ISRR.

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

[4]  Rüdiger Dillmann,et al.  Learning of Planning Models for Dexterous Manipulation Based on Human Demonstrations , 2012, International Journal of Social Robotics.

[5]  Ulrich Hillenbrand.  Non-parametric 3D Shape Warping , 2010, 2010 20th International Conference on Pattern Recognition.

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

[7]  Marc Toussaint,et al.  Gaussian process implicit surfaces for shape estimation and grasping , 2011, 2011 IEEE International Conference on Robotics and Automation.

[8]  Hong Liu,et al.  Experimental study on impedance control for the five-finger dexterous robot hand DLR-HIT II , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[9]  Carme Torras,et al.  Force-based robot learning of pouring skills using parametric hidden Markov models , 2013, 9th International Workshop on Robot Motion and Control.

[10]  Oliver Kroemer,et al.  Generalization of human grasping for multi-fingered robot hands , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[11]  Máximo A. Roa,et al.  Transferring functional grasps through contact warping and local replanning , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[12]  Rainer Jäkel,et al.  Learning of Generalized Manipulation Strategies in Service Robotics , 2013 .

[13]  Michael Beetz,et al.  Constraint-based movement representation grounded in geometric features , 2013, 2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids).

[14]  Oliver Kroemer,et al.  Learning to predict phases of manipulation tasks as hidden states , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[15]  Oliver Kroemer,et al.  A kernel-based approach to direct action perception , 2012, 2012 IEEE International Conference on Robotics and Automation.

[16]  Bernhard Schölkopf,et al.  Learning Dense 3D Correspondence , 2006, NIPS.

[17]  Moritz Tenorth,et al.  Decomposing CAD models of objects of daily use and reasoning about their functional parts , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[18]  David P. Dobkin,et al.  Multiresolution mesh morphing , 1999, SIGGRAPH.

[19]  Ales Ude,et al.  Learning to pour with a robot arm combining goal and shape learning for dynamic movement primitives , 2011, Robotics Auton. Syst..