Using tactile sensation for learning contact knowledge: Discriminate collision from physical interaction

Detecting and interpreting contacts is a crucial aspect of physical Human-Robot Interaction. In order to discriminate between intended and unintended contact types, we derive a set of linear and non-linear features based on physical contact model insights and from observing real impact data that may even rely on proprioceptive sensation only. We implement a classification system with a standard non-linear Support Vector Machine and show empirically both in simulations and on a real robot the high accuracy in off- as well as on-line settings of the system. We argue that these successful results are based on our feature design derived from first principles.

[1]  Alin Albu-Schäffer,et al.  Kick it with elasticity: Safety and performance in human-robot soccer , 2009, Robotics Auton. Syst..

[2]  Jae-Bok Song,et al.  Collision analysis and safety evaluation using a collision model for the frontal robot–human impact , 2014, Robotica.

[3]  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.

[4]  Alberto Rodriguez,et al.  Failure detection in assembly: Force signature analysis , 2010, 2010 IEEE International Conference on Automation Science and Engineering.

[5]  Antonio Bicchi,et al.  Biomechanisch sichere Geschwindigkeitsregelung für die Mensch-Roboter Interaktion , 2014, Autom..

[6]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[7]  Alessandro De Luca,et al.  Sensorless Robot Collision Detection and Hybrid Force/Motion Control , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.

[8]  M. Small Applied Nonlinear Time Series Analysis: Applications in Physics, Physiology and Finance , 2005 .

[9]  Alessandro De Luca,et al.  Collision detection and reaction: A contribution to safe physical Human-Robot Interaction , 2008, 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[10]  Alin Albu-Schäffer,et al.  Requirements for Safe Robots: Measurements, Analysis and New Insights , 2009, Int. J. Robotics Res..

[11]  Siddhartha S. Srinivasa,et al.  Abort and retry in grasping , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[12]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[13]  Oussama Khatib,et al.  A unified approach for motion and force control of robot manipulators: The operational space formulation , 1987, IEEE J. Robotics Autom..

[14]  Herman Bruyninckx,et al.  Bayesian time-series models for continuous fault detection and recognition in industrial robotic tasks , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[15]  Herman Bruyninckx,et al.  Hierarchical Dirichlet Process Hidden Markov Models for abnormality detection in robotic assembly , 2012 .

[16]  B. Hjorth EEG analysis based on time domain properties. , 1970, Electroencephalography and clinical neurophysiology.

[17]  Sami Haddadin,et al.  Towards Safe Robots - Approaching Asimov's 1st Law , 2013, Springer Tracts in Advanced Robotics.

[18]  Milad Geravand,et al.  Human-robot physical interaction and collaboration using an industrial robot with a closed control architecture , 2013, 2013 IEEE International Conference on Robotics and Automation.