Saved in:
Bibliographic Details
Main Authors: Xu, Zhengtong, Uppuluri, Raghava, Zhang, Xinwei, Fitch, Cael, Crandall, Philip Glen, Shou, Wan, Wang, Dongyi, She, Yu
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.06481
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917973338357760
author Xu, Zhengtong
Uppuluri, Raghava
Zhang, Xinwei
Fitch, Cael
Crandall, Philip Glen
Shou, Wan
Wang, Dongyi
She, Yu
author_facet Xu, Zhengtong
Uppuluri, Raghava
Zhang, Xinwei
Fitch, Cael
Crandall, Philip Glen
Shou, Wan
Wang, Dongyi
She, Yu
contents UniT is an approach to tactile representation learning, using VQGAN to learn a compact latent space and serve as the tactile representation. It uses tactile images obtained from a single simple object to train the representation with generalizability. This tactile representation can be zero-shot transferred to various downstream tasks, including perception tasks and manipulation policy learning. Our benchmarkings on in-hand 3D pose and 6D pose estimation tasks and a tactile classification task show that UniT outperforms existing visual and tactile representation learning methods. Additionally, UniT's effectiveness in policy learning is demonstrated across three real-world tasks involving diverse manipulated objects and complex robot-object-environment interactions. Through extensive experimentation, UniT is shown to be a simple-to-train, plug-and-play, yet widely effective method for tactile representation learning. For more details, please refer to our open-source repository https://github.com/ZhengtongXu/UniT and the project website https://zhengtongxu.github.io/unit-website/.
format Preprint
id arxiv_https___arxiv_org_abs_2408_06481
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle UniT: Data Efficient Tactile Representation with Generalization to Unseen Objects
Xu, Zhengtong
Uppuluri, Raghava
Zhang, Xinwei
Fitch, Cael
Crandall, Philip Glen
Shou, Wan
Wang, Dongyi
She, Yu
Robotics
UniT is an approach to tactile representation learning, using VQGAN to learn a compact latent space and serve as the tactile representation. It uses tactile images obtained from a single simple object to train the representation with generalizability. This tactile representation can be zero-shot transferred to various downstream tasks, including perception tasks and manipulation policy learning. Our benchmarkings on in-hand 3D pose and 6D pose estimation tasks and a tactile classification task show that UniT outperforms existing visual and tactile representation learning methods. Additionally, UniT's effectiveness in policy learning is demonstrated across three real-world tasks involving diverse manipulated objects and complex robot-object-environment interactions. Through extensive experimentation, UniT is shown to be a simple-to-train, plug-and-play, yet widely effective method for tactile representation learning. For more details, please refer to our open-source repository https://github.com/ZhengtongXu/UniT and the project website https://zhengtongxu.github.io/unit-website/.
title UniT: Data Efficient Tactile Representation with Generalization to Unseen Objects
topic Robotics
url https://arxiv.org/abs/2408.06481