Classification of rigid and deformable objects using a novel tactile sensor

Alin Drimus, Gert Kootstra, Arne Bilberg, Danica Kragic

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

In this paper, we present a novel array tactile sensor for use in robotic grippers based on a flexible piezoresistive rubber. We start by describing the physical principles of piezoresistive materials and continue by outlining how to build a flexible array tactile sensor using stitch electrodes. A real time acquisition system scans the data from the array which is then further processed. We validate the properties of the sensor in an application that classifies a number of household objects while performing a palpation procedure with a robotic gripper. Based on the haptic feedback, we classify various rigid and deformable objects. We represent the array of tactile images for each grasped object to a time series of features and use this as the input for a KNN classifier. Dynamic time warping is used for calculating distances between different time series of features. In the end, we compare the results with the ones obtained from an experimental setup that uses a Weiss Robotics tactile sensor with similar characteristics and we conclude by exemplifying how the results of the classification can be used in different industrial applications.
Original languageEnglish
Title of host publication2011 15th International Conference on Advanced Robotics (ICAR 2011)
Number of pages8
Place of PublicationTallinn
PublisherIEEE
Publication dateJun 2011
Pages427 - 434
ISBN (Print)978-1-4577-1158-9
DOIs
Publication statusPublished - Jun 2011

Keywords

  • piezoresistive sensor, tactile sensing, object recognition

Fingerprint

Dive into the research topics of 'Classification of rigid and deformable objects using a novel tactile sensor'. Together they form a unique fingerprint.

Cite this