Saved in:
Bibliographic Details
Main Authors: Huang, Binghao, Xu, Jie, Akinola, Iretiayo, Yang, Wei, Sundaralingam, Balakumar, O'Flaherty, Rowland, Fox, Dieter, Wang, Xiaolong, Mousavian, Arsalan, Chao, Yu-Wei, Li, Yunzhu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.14930
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917026308554752
author Huang, Binghao
Xu, Jie
Akinola, Iretiayo
Yang, Wei
Sundaralingam, Balakumar
O'Flaherty, Rowland
Fox, Dieter
Wang, Xiaolong
Mousavian, Arsalan
Chao, Yu-Wei
Li, Yunzhu
author_facet Huang, Binghao
Xu, Jie
Akinola, Iretiayo
Yang, Wei
Sundaralingam, Balakumar
O'Flaherty, Rowland
Fox, Dieter
Wang, Xiaolong
Mousavian, Arsalan
Chao, Yu-Wei
Li, Yunzhu
contents Humans excel at bimanual assembly tasks by adapting to rich tactile feedback -- a capability that remains difficult to replicate in robots through behavioral cloning alone, due to the suboptimality and limited diversity of human demonstrations. In this work, we present VT-Refine, a visuo-tactile policy learning framework that combines real-world demonstrations, high-fidelity tactile simulation, and reinforcement learning to tackle precise, contact-rich bimanual assembly. We begin by training a diffusion policy on a small set of demonstrations using synchronized visual and tactile inputs. This policy is then transferred to a simulated digital twin equipped with simulated tactile sensors and further refined via large-scale reinforcement learning to enhance robustness and generalization. To enable accurate sim-to-real transfer, we leverage high-resolution piezoresistive tactile sensors that provide normal force signals and can be realistically modeled in parallel using GPU-accelerated simulation. Experimental results show that VT-Refine improves assembly performance in both simulation and the real world by increasing data diversity and enabling more effective policy fine-tuning. Our project page is available at https://binghao-huang.github.io/vt_refine/.
format Preprint
id arxiv_https___arxiv_org_abs_2510_14930
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VT-Refine: Learning Bimanual Assembly with Visuo-Tactile Feedback via Simulation Fine-Tuning
Huang, Binghao
Xu, Jie
Akinola, Iretiayo
Yang, Wei
Sundaralingam, Balakumar
O'Flaherty, Rowland
Fox, Dieter
Wang, Xiaolong
Mousavian, Arsalan
Chao, Yu-Wei
Li, Yunzhu
Robotics
Machine Learning
Humans excel at bimanual assembly tasks by adapting to rich tactile feedback -- a capability that remains difficult to replicate in robots through behavioral cloning alone, due to the suboptimality and limited diversity of human demonstrations. In this work, we present VT-Refine, a visuo-tactile policy learning framework that combines real-world demonstrations, high-fidelity tactile simulation, and reinforcement learning to tackle precise, contact-rich bimanual assembly. We begin by training a diffusion policy on a small set of demonstrations using synchronized visual and tactile inputs. This policy is then transferred to a simulated digital twin equipped with simulated tactile sensors and further refined via large-scale reinforcement learning to enhance robustness and generalization. To enable accurate sim-to-real transfer, we leverage high-resolution piezoresistive tactile sensors that provide normal force signals and can be realistically modeled in parallel using GPU-accelerated simulation. Experimental results show that VT-Refine improves assembly performance in both simulation and the real world by increasing data diversity and enabling more effective policy fine-tuning. Our project page is available at https://binghao-huang.github.io/vt_refine/.
title VT-Refine: Learning Bimanual Assembly with Visuo-Tactile Feedback via Simulation Fine-Tuning
topic Robotics
Machine Learning
url https://arxiv.org/abs/2510.14930