The sense of touch is fundamental in several manipulation tasks, but rarely used in robot manipulation. In this work we tackle the problem of learning rich touch features from cross-modal self-supervision. We evaluate them identifying objects and their properties in a few-shot classification setting. Two new datasets are introduced using a simulated anthropomorphic robotic hand equipped with tactile sensors on both synthetic and daily life objects. Several self-supervised learning methods are benchmarked on these datasets, by evaluating few-shot classification on unseen objects and poses. Our experiments indicate that cross-modal self-supervision effectively improves touch representation, and in turn has great potential to enhance robot manipulation skills.
@article{arxiv.2101.08616,
title = {Learning rich touch representations through cross-modal self-supervision},
author = {Martina Zambelli and Yusuf Aytar and Francesco Visin and Yuxiang Zhou and Raia Hadsell},
journal= {arXiv preprint arXiv:2101.08616},
year = {2021}
}