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

Abstract

ReuseUnless indicated otherwise, fulltext items are protected by copyright with all rights reserved. The copyright exception in section 29 of the Copyright, Designs and Patents Act 1988 allows the making of a single copy solely for the purpose of non-commercial research or private study within the limits of fair dealing. The publisher or other rights-holder may allow further reproduction and re-use of this version -refer to the White Rose Research Online record for this item. Where records identify the publisher as the copyright holder, users can verify any specific terms of use on the publisher's website. TakedownIf you consider content in White Rose Research Online to be in breach of UK law, please notify us by emailing eprints@whiterose.ac.uk including the URL of the record and the reason for the withdrawal request.Embodied hyperacuity from Bayesian perception: Shape and position discrimination with an iCub fingertip sensor Nathan F. Lepora, Uriel Martinez-Hernandez, Hector Barron-Gonzalez, Mat Evans, Giorgio Metta, Tony J. Prescott Abstract-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.

Active Bayesian Perception for Simultaneous Object Localization and Identification

“…A strength of the formalism is that it connects closely with leading work in neuroscience, allowing insights from animal perception to be transferred to robot perception. For example, these methods have enabled the first demonstration of hyperacuity in robot touch [9], giving perceptual acuity finer than the sensor resolution, as is common in animal perception. That study also found that active perception helped the hyperacuity, although those methods do suffer from being somewhat ad hoc by not making best use of the 'where' and 'what' aspects of the problem.…”

“…Our algorithm for active perception is based on including a sensorimotor feedback loop in an existing method for passive Bayesian perception [9,12]. Both methods assume that the sensor makes a discrete contact measurement (here a tap) onto an object, from which the joint likelihoods of object location and identity are used to update the posterior beliefs for those perceptual classes.…”

“…4A), analogous to those of mechanoreceptors (touch) and photoreceptors (vision). Bayesian perception then gives perceptual hyperacuity [9], a phenomenon associated with animal perception. Given the taxel spacing is 4 mm, our results display extreme hyperacuity.…”

Active Bayesian perception and reinforcement learning

“…In a series of papers [4], [5], [6], [7], [8], we have formalized a Bayesian perception approach for robotics based on this recent progress in understanding animal perception. Our formalism extends naturally to active perception, by moving the sensor with a control strategy based on evidence received during decision making.…”

“…Thus far, the belief threshold has been treated as a free parameter that adjusts the balance between mean errors and reaction times (e.g. [7,Fig. 5]).…”