Active touch for robust perception under position uncertainty
- 1 May 2013
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3020-3025
- https://doi.org/10.1109/icra.2013.6630996
Abstract
In this paper, we propose that active perception will help attain autonomous robotics in unstructured environments by giving robust perception. We test this claim with a biomimetic fingertip that senses surface texture under a range of contact depths. We compare the performance of passive Bayesian perception with a novel approach for active perception that includes a sensorimotor loop for controlling sensor position. Passive perception at a single depth gave poor results, with just 0.2mm uncertainty impairing performance. Extending passive perception over a range of depths gave non-robust performance. Only active perception could give robust, accurate performance, with the sensorimotor feedback compensating the position uncertainty. We expect that these results will extend to other stimuli, so that active perception will offer a general approach to robust perception in unstructured environments.Keywords
This publication has 23 references indexed in Scilit:
- Bayesian Exploration for Intelligent Identification of TexturesFrontiers in Neurorobotics, 2012
- Texture Classification through Tactile SensingLecture Notes in Computer Science, 2012
- Majority Voting: Material Classification by Tactile Sensing Using Surface TextureIEEE Transactions on Robotics, 2011
- Using Bayesian Filtering to Localize Flexible Materials During ManipulationIEEE Transactions on Robotics, 2011
- Methods and Technologies for the Implementation of Large-Scale Robot Tactile SensorsIEEE Transactions on Robotics, 2011
- The Spatial Spectrum of Tangential Skin Displacement Can Encode Tactual TextureIEEE Transactions on Robotics, 2011
- Tactile-Data Classification of Contact Materials Using Computational IntelligenceIEEE Transactions on Robotics, 2011
- Naive Bayes texture classification applied to whisker data from a moving robotPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2010
- Object identification with tactile sensors using bag-of-featuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- The iCub humanoid robotPublished by Association for Computing Machinery (ACM) ,2008