Title
Embodied hyperacuity from Bayesian perception: Shape and position discrimination with an iCub fingertip sensor
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.
Year
DOI
Venue
2012
10.1109/IROS.2012.6385649
Intelligent Robots and Systems
Keywords
Field
DocType
Bayes methods,biomimetics,position control,robots,tactile sensors,Bayesian perception,active perception,animal perception modeling,biomimetic robot,cylindrical stimuli offset,fingertip position,fingertip reposition,iCub fingertip sensor,object position,perceptual hyperacuity,perceptual location,position discrimination,positioning robot,robot perception,robot touch,shape discrimination,submillimeter accuracy,tactile sensor
Computer vision,iCub,Active perception,Computer science,Hyperacuity,Embodied cognition,Artificial intelligence,Robot,Perception,Offset (computer science),Tactile sensor
Conference
ISSN
ISBN
Citations 
2153-0858
978-1-4673-1737-5
3
PageRank 
References 
Authors
0.42
0
8