Learning to Exploit Proximal Force Sensing: A Comparison Approach

We present an evaluation of different techniques for the estimation of forces and torques measured by a single six-axis force/torque sensor placed along the kinematic chain of a humanoid robot arm. In order to retrieve the external forces and detect possible contact situations, the internal forces must be estimated. The prediction performance of an analytically derived dynamic model as well as two supervised machine learning techniques, namely Least Squares Support Vector Machines and Neural Networks, are investigated on this problem. The performance are evaluated on the normalized mean square error (NMSE) and the comparison is made with respect to the dimension of the training set, the information contained in the input space and, finally, using a Euclidean subsampling strategy.

[1]  David G. Stork,et al.  Pattern Classification , 1973 .

[2]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[3]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[4]  Kazuhiro Kosuge,et al.  Collision detection system for manipulator based on adaptive impedance control law , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[5]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[6]  Alessandro De Luca,et al.  Collision Detection and Safe Reaction with the DLR-III Lightweight Manipulator Arm , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[7]  Bruno Siciliano,et al.  Modeling and Control of Robot Manipulators , 1995 .

[8]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[9]  Gavin C. Cawley,et al.  Leave-One-Out Cross-Validation Based Model Selection Criteria for Weighted LS-SVMs , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

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

[11]  Steven A. Velinsky,et al.  Human-Robot Collision Detection and Identification Based on Wrist and Base Force/Torque Sensors , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[12]  Jan Swevers,et al.  Optimal robot excitation and identification , 1997, IEEE Trans. Robotics Autom..

[13]  Giulio Sandini,et al.  An embedded artificial skin for humanoid robots , 2008, 2008 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems.

[14]  Giulio Sandini,et al.  James: A Humanoid Robot Acting over an Unstructured World , 2006, 2006 6th IEEE-RAS International Conference on Humanoid Robots.

[15]  Bernard Widrow,et al.  Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[16]  Jun Nakanishi,et al.  A Bayesian Approach to Nonlinear Parameter Identification for Rigid Body Dynamics , 2006, Robotics: Science and Systems.

[17]  Guangjun Liu,et al.  A base force/torque sensor approach to robot manipulator inertial parameter estimation , 1998, Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146).

[18]  Kenneth Levenberg.  A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

[19]  Philippe Gaussier,et al.  Proprioception and Imitation: On the Road to Agent Individuation , 2010, From Motor Learning to Interaction Learning in Robots.

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

[21]  Krzysztof Kozłowski,et al.  Modelling and Identification in Robotics , 1998 .

[22]  J. Denavit,et al.  A kinematic notation for lower pair mechanisms based on matrices , 1955 .

[23]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machines , 2002 .