Skill learning and action recognition by arc-length dynamic movement primitives

Abstract Effective robot programming by demonstration requires the availability of multiple demonstrations to learn about all relevant aspects of the demonstrated skill or task. Typically, a human teacher must demonstrate several variants of the desired task to generate a sufficient amount of data to reliably learn it. Here a problem often arises that there is a large variability in the speed of execution across human demonstrations. This can cause problems when multiple demonstrations are compared to extract the relevant information for learning. In this paper we propose an extension of dynamic movement primitives called arc-length dynamic movement primitives, where spatial and temporal components of motion are well separated. We show theoretically and experimentally that the proposed representation can be effectively applied for robot skill learning and action recognition even when there are large variations in the speed of demonstrated movements.

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

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

[3]  J. E. Glynn,et al.  Numerical Recipes: The Art of Scientific Computing , 1989 .

[4]  Nam Jun Cho,et al.  Measuring motion significance and motion complexity , 2017, Inf. Sci..

[5]  Jun Morimoto,et al.  Learning parametric dynamic movement primitives from multiple demonstrations , 2011, Neural Networks.

[6]  Andrej Gams,et al.  Velocity adaptation for self-improvement of skills learned from user demonstrations , 2013, 2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids).

[7]  Andrej Gams,et al.  Coupling Movement Primitives: Interaction With the Environment and Bimanual Tasks , 2014, IEEE Transactions on Robotics.

[8]  Jun Morimoto,et al.  CB: A Humanoid Research Platform for Exploring NeuroScience , 2006, 2006 6th IEEE-RAS International Conference on Humanoid Robots.

[9]  Jun Morimoto,et al.  Orientation in Cartesian space dynamic movement primitives , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

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

[11]  Minija Tamosiunaite,et al.  Interaction learning for dynamic movement primitives used in cooperative robotic tasks , 2013, Robotics Auton. Syst..

[12]  Satoshi Endo,et al.  Dynamic Movement Primitives for Human-Robot interaction: Comparison with human behavioral observation , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[13]  Jan Peters,et al.  Nonamemanuscript No. (will be inserted by the editor) Reinforcement Learning to Adjust Parametrized Motor Primitives to , 2011 .

[14]  Alfred Gray,et al.  Modern differential geometry of curves and surfaces with Mathematica (2. ed.) , 1998 .

[15]  Ales Ude,et al.  Speed adaptation for self-improvement of skills learned from user demonstrations , 2015, Robotica.

[16]  Carme Torras,et al.  Learning Physical Collaborative Robot Behaviors From Human Demonstrations , 2016, IEEE Transactions on Robotics.

[17]  Jake K. Aggarwal,et al.  Human activity recognition from 3D data: A review , 2014, Pattern Recognit. Lett..

[18]  Oliver Kroemer,et al.  Interaction primitives for human-robot cooperation tasks , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[19]  Jan Peters,et al.  Learning motor skills from partially observed movements executed at different speeds , 2015, 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[20]  Andrej Gams,et al.  Generalization of orientation trajectories and force-torque profiles for robotic assembly , 2017, Robotics Auton. Syst..

[21]  Stefan Schaal,et al.  Reinforcement Learning With Sequences of Motion Primitives for Robust Manipulation , 2012, IEEE Transactions on Robotics.

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

[23]  Rajnikant V. Patel,et al.  Formulation of Joint Trajectories for Industrial Robots Using B-Splines , 1987, IEEE Transactions on Industrial Electronics.

[24]  Aude Billard,et al.  Learning control Lyapunov function to ensure stability of dynamical system-based robot reaching motions , 2014, Robotics Auton. Syst..

[25]  Andrew W. Moore,et al.  Locally Weighted Learning , 1997, Artificial Intelligence Review.

[26]  Darwin G. Caldwell,et al.  Compliant skills acquisition and multi-optima policy search with EM-based reinforcement learning , 2013, Robotics Auton. Syst..

[27]  S. Chiba,et al.  Dynamic programming algorithm optimization for spoken word recognition , 1978 .

[28]  Stefan Schaal,et al.  Online movement adaptation based on previous sensor experiences , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

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

[30]  Stefan Schaal,et al.  Incremental Local Gaussian Regression , 2014, NIPS.

[31]  Jun Nakanishi,et al.  Nonlinear dynamical systems for imitation with humanoid robots , 2001 .

[32]  Oliver Kroemer,et al.  Probabilistic movement primitives for coordination of multiple human–robot collaborative tasks , 2017, Auton. Robots.