Object Recognition Through Active Sensing Using a Multi-Fingered Robot Hand with 3D Tactile Sensors
Satoshi Funabashi, Shu Morikuni, Andreas Geier, Alexander Schmitz, Shun Ogasa, Tito Pradhono Torno, Sophon Somlor, Shigeki Sugano
Abstract
This paper investigates tactile object recognition with relatively densely distributed force vector measurements and evaluates what kind of tactile information is beneficial for object recognition. The uSkin tactile sensors are embedded in an Allegro Hand, and provide 240 triaxial force vector measurements in total in all fingers. Active object sensing is used to gather time-series training and testing data. A simple feedforward, a recurrent, and a convolutional neural network are used for recognizing objects. Evaluations with different number of employed measurements, static vs. time series data and force vector vs. only normal force vector measurements show that the high-dimensional information provided by the sensors is indeed beneficial. An object recognition rate of up to 95% for 20 objects was achieved.
BibTeX
@inproceedings{iros2018_objectrecognitio,
title = {Object Recognition Through Active Sensing Using a Multi-Fingered Robot Hand with 3D Tactile Sensors},
author = {Satoshi Funabashi and Shu Morikuni and Andreas Geier and Alexander Schmitz and Shun Ogasa and Tito Pradhono Torno and Sophon Somlor and Shigeki Sugano},
booktitle = {IROS 2018},
year = {2018}
}