Dexterity from Touch: Self-Supervised Pre-Training of Tactile Representations with Robotic PlayDownload PDF

Published: 30 Aug 2023, Last Modified: 25 Oct 2023CoRL 2023 PosterReaders: Everyone
Keywords: Tactile, Dexterity, Manipulation
TL;DR: Tactile pretraining from play data for dexterous manipulation.
Abstract: Teaching dexterity to multi-fingered robots has been a longstanding challenge in robotics. Most prominent work in this area focuses on learning controllers or policies that either operate on visual observations or state estimates derived from vision. However, such methods perform poorly on fine-grained manipulation tasks that require reasoning about contact forces or about objects occluded by the hand itself. In this work, we present T-Dex, a new approach for tactile-based dexterity, that operates in two phases. In the first phase, we collect 2.5 hours of play data, which is used to train self-supervised tactile encoders. This is necessary to bring high-dimensional tactile readings to a lower-dimensional embedding. In the second phase, given a handful of demonstrations for a dexterous task, we learn non-parametric policies that combine the tactile observations with visual ones. Across five challenging dexterous tasks, we show that our tactile-based dexterity models outperform purely vision and torque-based models by an average of 1.7X. Finally, we provide a detailed analysis on factors critical to T-Dex including the importance of play data, architectures, and representation learning.
Student First Author: yes
Supplementary Material: zip
Instructions: I have read the instructions for authors (https://corl2023.org/instructions-for-authors/)
Video: https://www.youtube.com/watch?v=lzJdVBe4lrI
Website: https://tactile-dexterity.github.io/
Code: https://github.com/irmakguzey/tactile-dexterity
Publication Agreement: pdf
Poster Spotlight Video: mp4
14 Replies

Loading