Embodied hyperacuity from Bayesian perception: Shape and position discrimination with an iCub fingertip sensor

Recent advances in modeling animal perception has motivated an approach of Bayesian perception applied to biomimetic robots. This study presents an initial application of Bayesian perception on an iCub fingertip sensor mounted on a dedicated positioning robot. We systematically probed the test system with five cylindrical stimuli offset by a range of positions relative to the fingertip. Testing the real-time speed and accuracy of shape and position discrimination, we achieved sub-millimeter accuracy with just a few taps. This result is apparently the first explicit demonstration of perceptual hyperacuity in robot touch, in that object positions are perceived more accurately than the taxel spacing. We also found substantial performance gains when the fingertip can reposition itself to avoid poor perceptual locations, which indicates that improved robot perception could mimic active perception in animals.

[1]  D. Knill,et al.  The Bayesian brain: the role of uncertainty in neural coding and computation , 2004, Trends in Neurosciences.

[2]  J. Wolfowitz,et al.  Optimum Character of the Sequential Probability Ratio Test , 1948 .

[3]  J M Loomis,et al.  An investigation of tactile hyperacuity. , 1979, Sensory processes.

[4]  A. Yuille,et al.  Object perception as Bayesian inference. , 2004, Annual review of psychology.

[5]  Maurizio Valle,et al.  Tactile-Data Classification of Contact Materials Using Computational Intelligence , 2011, IEEE Transactions on Robotics.

[6]  Gerald E. Loeb,et al.  Haptic feature extraction from a biomimetic tactile sensor: Force, contact location and curvature , 2011, 2011 IEEE International Conference on Robotics and Biomimetics.

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

[8]  Nathan F. Lepora,et al.  Brain-inspired Bayesian perception for biomimetic robot touch , 2012, 2012 IEEE International Conference on Robotics and Automation.

[9]  A. Wing,et al.  Active touch sensing , 2011, Philosophical Transactions of the Royal Society B: Biological Sciences.

[10]  Nikolaos G. Tsagarakis,et al.  iCub: the design and realization of an open humanoid platform for cognitive and neuroscience research , 2007, Adv. Robotics.

[11]  Jonathan D. Cohen,et al.  The physics of optimal decision making: a formal analysis of models of performance in two-alternative forced-choice tasks. , 2006, Psychological review.

[12]  Mathew H. Evans,et al.  Tactile Discrimination Using Template Classifiers: Towards a Model of Feature Extraction in Mammalian Vibrissal Systems , 2010, SAB.

[13]  Gerald E. Loeb,et al.  Bayesian Exploration for Intelligent Identification of Textures , 2012, Front. Neurorobot..

[14]  Oussama Khatib,et al.  Global Localization of Objects via Touch , 2011, IEEE Transactions on Robotics.

[15]  Giorgio Metta,et al.  A tactile sensor for the fingertips of the humanoid robot iCub , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[16]  R. Bajcsy.  Active perception , 1988 .

[17]  Robert Platt,et al.  Using Bayesian Filtering to Localize Flexible Materials During Manipulation , 2011, IEEE Transactions on Robotics.

[18]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[19]  J. Gold,et al.  The neural basis of decision making. , 2007, Annual review of neuroscience.

[20]  Gregory D. Hager,et al.  Tactile-Object Recognition From Appearance Information , 2011, IEEE Transactions on Robotics.

[21]  Giorgio Metta,et al.  A prototype fingertip with high spatial resolution pressure sensing for the robot iCub , 2008, Humanoids 2008 - 8th IEEE-RAS International Conference on Humanoid Robots.

[22]  Giorgio Metta,et al.  Methods and Technologies for the Implementation of Large-Scale Robot Tactile Sensors , 2011, IEEE Transactions on Robotics.

[23]  Venugopal V. Veeravalli,et al.  Multihypothesis sequential probability ratio tests - Part I: Asymptotic optimality , 1999, IEEE Trans. Inf. Theory.

[24]  Nathan F. Lepora,et al.  Naive Bayes texture classification applied to whisker data from a moving robot , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[25]  Giulio Sandini,et al.  Tactile Sensing—From Humans to Humanoids , 2010, IEEE Transactions on Robotics.

[26]  Kevin Gurney,et al.  Optimal decision-making in mammals: insights from a robot study of rodent texture discrimination , 2012, Journal of The Royal Society Interface.

[27]  Robert W. Platt,et al.  Using Bayesian filtering to interpret tactile data during flexible materials manipulation , 2010 .