Active Slip Control for In-Hand Object Manipulation using Deep Predictive Models
RSS 2017: Workshop on Tactile Sensing for Manipulation: Hardware, Modeling, and Learning, 2017
Workshop
Content
We discuss a machine learning methodology for actively controlling slip, in order to increase robot dexterity. Leveraging recent insights in Deep Learning, we propose a Deep Predictive Model that uses tactile sensor information to reason about slip and its future influence on the manipulated object. We show in a set of experiments that this approach can be used to increase a robot’s repertoire of skills.
Citation
@misc{stepputtis2017rss1,
title={Active Slip Control for In-Hand Object Manipulation using Deep Predictive Models},
author={Simon Stepputtis and Heni Ben Amor},
year={2017},
booktitle = {RSS 2017: Workshop on Tactile Sensing for Manipulation: Hardware, Modeling, and Learning},
}