Learning the velocity kinematics of ICUB for model-based control: XCSF versus LWPR

The model-based control of humanoid robots requires the availability of accurate mechanical models that can be hard to obtain in practice. One approach to this problem consists in calling upon machine learning methods. In this paper, using a standard control approach based on visual servoing, we compare the accuracy of two supervised learning methods, namely LWPR and XCSF, to extract the forward velocity kinematics of the upper body of the ICUB robot. Experiments are performed in simulation, using one arm and the head for reaching tasks. We show that both methods provide accurate models of the robot, with a slight advantage to XCSF over LWPR.

[1]  Martin V. Butz,et al.  Computational Complexity of the XCS Classifier System , 2005 .

[2]  Olivier Sigaud,et al.  From Motor Learning to Interaction Learning in Robots , 2010, From Motor Learning to Interaction Learning in Robots.

[3]  Martin V. Butz,et al.  Function approximation with LWPR and XCSF: a comparative study , 2012, Evol. Intell..

[4]  Giulio Sandini,et al.  The iCub humanoid robot: an open platform for research in embodied cognition , 2008, PerMIS.

[5]  Giorgio Metta,et al.  Towards long-lived robot genes , 2008, Robotics Auton. Syst..

[6]  Jun Nakanishi,et al.  Operational Space Control: A Theoretical and Empirical Comparison , 2008, Int. J. Robotics Res..

[7]  Stefan Schaal,et al.  LWPR: A Scalable Method for Incremental Online Learning in High Dimensions , 2005 .

[8]  L. Eld.  Partial least-squares vs. Lanczos bidiagonalization—I: analysis of a projection method for multiple regression , 2004 .

[9]  Lars Eldén,et al.  Partial least-squares vs. Lanczos bidiagonalization - I: analysis of a projection method for multiple regression , 2004, Comput. Stat. Data Anal..

[10]  Stewart W. Wilson,et al.  Noname manuscript No. (will be inserted by the editor) Learning Classifier Systems: A Survey , 2022 .

[11]  M. C. Deo,et al.  Locally weighted projection regression for predicting hydraulic parameters , 2010 .

[12]  Stefan Schaal,et al.  Scalable Techniques from Nonparametric Statistics for Real Time Robot Learning , 2002, Applied Intelligence.

[13]  Olivier Sigaud,et al.  On-line regression algorithms for learning mechanical models of robots: A survey , 2011, Robotics Auton. Syst..

[14]  Martin V. Butz,et al.  A comparative study: function approximation with LWPR and XCSF , 2010, GECCO '10.

[15]  Giulio Sandini,et al.  Computing robot internal/external wrenches by means of inertial, tactile and F/T sensors: Theory and implementation on the iCub , 2011, 2011 11th IEEE-RAS International Conference on Humanoid Robots.

[16]  Stefan Schaal,et al.  Learning to Control in Operational Space , 2008, Int. J. Robotics Res..

[17]  Martin V. Butz,et al.  Context-dependent predictions and cognitive arm control with XCSF , 2008, GECCO '08.

[18]  Olivier Sigaud,et al.  Control of redundant robots using learned models: An operational space control approach , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[19]  Jan Peters,et al.  Real-Time Local GP Model Learning , 2010, From Motor Learning to Interaction Learning in Robots.

[20]  Michel Tenenhaus.  La r?gression PLS: th?orie et pratique , 1998 .

[21]  Keith L. Doty,et al.  A Theory of Generalized Inverses Applied to Robotics , 1993, Int. J. Robotics Res..

[22]  Stefan Schaal,et al.  Locally Weighted Projection Regression : An O(n) Algorithm for Incremental Real Time Learning in High Dimensional Space , 2000 .

[23]  G. Metta,et al.  Learning precise 3D reaching in a humanoid robot , 2007, 2007 IEEE 6th International Conference on Development and Learning.

[24]  S. Chiaverini,et al.  Achieving user-defined accuracy with damped least-squares inverse kinematics , 1991, Fifth International Conference on Advanced Robotics 'Robots in Unstructured Environments.

[25]  Angelo Cangelosi,et al.  Integration of Speech and Action in Humanoid Robots: iCub Simulation Experiments , 2011, IEEE Transactions on Autonomous Mental Development.

[26]  Stewart W. Wilson.  Classifiers that approximate functions , 2002, Natural Computing.

[27]  Angelo Cangelosi,et al.  The iCub Humanoid Robot Simulator , 2008 .

[28]  H. Wold.  Soft Modelling by Latent Variables: The Non-Linear Iterative Partial Least Squares (NIPALS) Approach , 1975, Journal of Applied Probability.

[29]  Éric Marchand,et al.  Using the task function approach to avoid robot joint limits and kinematic singularities in visual servoing , 1996, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. IROS '96.