Programming Everyday Task by Demonstration using Primitive Skills for a Manipulator

This manuscript presents a method to program everyday manipulation tasks for a robot by human demonstration using primitive skills. The hand movement in the demonstrated task is recorded then segmented into sub-actions. Each sub-action is mapped to primitives skills of the robot. We proposed a list of necessary skills for a manipulator which are common to use in many everyday tasks. In order to adapt with the change of object's location, we applied Dynamic Movement Primitives model for regenerating movement which follows the demonstrated trajectory. In experiment, we considered the task “dispensing water” from a water thermos pot performed by a robot arm to verify the proposed method.

[1]  Rüdiger Dillmann,et al.  Teaching and learning of robot tasks via observation of human performance , 2004, Robotics Auton. Syst..

[2]  Aude Billard,et al.  Learning Non-linear Multivariate Dynamics of Motion in Robotic Manipulators , 2011, Int. J. Robotics Res..

[3]  Aude Billard,et al.  Robot learning by demonstration , 2013, Scholarpedia.

[4]  Takashi Yoshimi,et al.  An approach to learn hand movements for robot actions from human demonstrations , 2016, 2016 IEEE/SICE International Symposium on System Integration (SII).

[5]  John S. Baras,et al.  Learning hand movements from markerless demonstrations for humanoid tasks , 2014, 2014 IEEE-RAS International Conference on Humanoid Robots.

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

[7]  Darwin G. Caldwell,et al.  Learning and Reproduction of Gestures by Imitation , 2010, IEEE Robotics & Automation Magazine.

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

[9]  Stefan Schaal,et al.  Movement segmentation using a primitive library , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[10]  Jun Morimoto,et al.  On-line motion synthesis and adaptation using a trajectory database , 2012, Robotics Auton. Syst..

[11]  Jun Nakanishi,et al.  Dynamical Movement Primitives: Learning Attractor Models for Motor Behaviors , 2013, Neural Computation.

[12]  Alexander SkoglundBoyko.  Programming by Demonstration of Pick-and-Place Tasks for Industrial Manipulators using Task Primitives , 2007 .

[13]  Stefan Schaal,et al.  Movement Segmentation and Recognition for Imitation Learning , 2012, AISTATS.

[14]  Jun Nakanishi,et al.  Movement imitation with nonlinear dynamical systems in humanoid robots , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[15]  Danica Kragic,et al.  Learning Actions from Observations , 2010, IEEE Robotics & Automation Magazine.

[16]  Eric L. Sauser,et al.  An Approach Based on Hidden Markov Model and Gaussian Mixture Regression , 2010 .

[17]  Gordon Cheng,et al.  Learning tasks from observation and practice , 2004, Robotics Auton. Syst..