A comparison of distance measures for learning nonparametric motor skill libraries

Autonomous robots that interact with the environment to learn new motor skills need to continuously memorize and compare fresh knowledge with past experience. Traditional approaches assume that experts label skills. In this paper, we introduce a new framework for autonomously learning a nonparametric skill library. Crucial design choices are the space in which the motor skills are represented, a distance measure to evaluate the similarity between known skills and new observations and a clustering policy. These aspects determine the structure and amount of skills learned by the library. In this paper, we use a probabilistic skill representation to support a large variety of measures as well as useful library features. Clustering is done via a decision tree. We evaluated the learning process with respect to 19 distance measures used to separate four manipulation skills on a KUKA LWR arm. The results suggest comparisons of trajectories in the end effector space, and that the use of measures for distributions depends on the amount of available data.

[1]  Jan Peters,et al.  Probabilistic Movement Models Show that Postural Control Precedes and Predicts Volitional Motor Control , 2016, Scientific Reports.

[2]  Pierre-Yves Oudeyer,et al.  Intrinsic Motivation Systems for Autonomous Mental Development , 2007, IEEE Transactions on Evolutionary Computation.

[3]  Sebastian Thrun,et al.  Explanation-based neural network learning a lifelong learning approach , 1995 .

[4]  Oliver Kroemer,et al.  Learning to select and generalize striking movements in robot table tennis , 2012, AAAI Fall Symposium: Robots Learning Interactively from Human Teachers.

[5]  Eric Eaton,et al.  Using Task Features for Zero-Shot Knowledge Transfer in Lifelong Learning , 2016, IJCAI.

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

[7]  Frank Kirchner,et al.  Incremental learning of skill collections based on intrinsic motivation , 2013, Front. Neurorobot..

[8]  Jan Peters,et al.  Extracting low-dimensional control variables for movement primitives , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[9]  Jochen J. Steil,et al.  Self-supervised bootstrapping of a movement primitive library from complex trajectories , 2014, 2014 IEEE-RAS International Conference on Humanoid Robots.

[10]  Stefan Schaal,et al.  A Probabilistic Representation for Dynamic Movement Primitives , 2016, ArXiv.

[11]  Peter I. Frazier,et al.  Distance dependent Chinese restaurant processes , 2009, ICML.

[12]  Ole Madsen,et al.  Robot skills for manufacturing , 2016 .

[13]  Sung-Hyuk Cha.  Comprehensive Survey on Distance/Similarity Measures between Probability Density Functions , 2007 .

[14]  T. Ferguson.  A Bayesian Analysis of Some Nonparametric Problems , 1973 .

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

[16]  Marco Mirolli,et al.  GRAIL: A Goal-Discovering Robotic Architecture for Intrinsically-Motivated Learning , 2016, IEEE Transactions on Cognitive and Developmental Systems.

[17]  Nikolaos G. Tsagarakis,et al.  Statistical dynamical systems for skills acquisition in humanoids , 2012, 2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012).