Touch begins where vision ends: Generalizable policies for contact-rich manipulation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Zifan, Haldar, Siddhant, Cui, Jinda, Pinto, Lerrel, Bhirangi, Raunaq
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908409122521088
author Zhao, Zifan
Haldar, Siddhant
Cui, Jinda
Pinto, Lerrel
Bhirangi, Raunaq
author_facet Zhao, Zifan
Haldar, Siddhant
Cui, Jinda
Pinto, Lerrel
Bhirangi, Raunaq
contents Data-driven approaches struggle with precise manipulation; imitation learning requires many hard-to-obtain demonstrations, while reinforcement learning yields brittle, non-generalizable policies. We introduce VisuoTactile Local (ViTaL) policy learning, a framework that solves fine-grained manipulation tasks by decomposing them into two phases: a reaching phase, where a vision-language model (VLM) enables scene-level reasoning to localize the object of interest, and a local interaction phase, where a reusable, scene-agnostic ViTaL policy performs contact-rich manipulation using egocentric vision and tactile sensing. This approach is motivated by the observation that while scene context varies, the low-level interaction remains consistent across task instances. By training local policies once in a canonical setting, they can generalize via a localize-then-execute strategy. ViTaL achieves around 90% success on contact-rich tasks in unseen environments and is robust to distractors. ViTaL's effectiveness stems from three key insights: (1) foundation models for segmentation enable training robust visual encoders via behavior cloning; (2) these encoders improve the generalizability of policies learned using residual RL; and (3) tactile sensing significantly boosts performance in contact-rich tasks. Ablation studies validate each of these insights, and we demonstrate that ViTaL integrates well with high-level VLMs, enabling robust, reusable low-level skills. Results and videos are available at https://vitalprecise.github.io.
format Preprint
id arxiv_https___arxiv_org_abs_2506_13762
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Touch begins where vision ends: Generalizable policies for contact-rich manipulation
Zhao, Zifan
Haldar, Siddhant
Cui, Jinda
Pinto, Lerrel
Bhirangi, Raunaq
Robotics
Computer Vision and Pattern Recognition
Data-driven approaches struggle with precise manipulation; imitation learning requires many hard-to-obtain demonstrations, while reinforcement learning yields brittle, non-generalizable policies. We introduce VisuoTactile Local (ViTaL) policy learning, a framework that solves fine-grained manipulation tasks by decomposing them into two phases: a reaching phase, where a vision-language model (VLM) enables scene-level reasoning to localize the object of interest, and a local interaction phase, where a reusable, scene-agnostic ViTaL policy performs contact-rich manipulation using egocentric vision and tactile sensing. This approach is motivated by the observation that while scene context varies, the low-level interaction remains consistent across task instances. By training local policies once in a canonical setting, they can generalize via a localize-then-execute strategy. ViTaL achieves around 90% success on contact-rich tasks in unseen environments and is robust to distractors. ViTaL's effectiveness stems from three key insights: (1) foundation models for segmentation enable training robust visual encoders via behavior cloning; (2) these encoders improve the generalizability of policies learned using residual RL; and (3) tactile sensing significantly boosts performance in contact-rich tasks. Ablation studies validate each of these insights, and we demonstrate that ViTaL integrates well with high-level VLMs, enabling robust, reusable low-level skills. Results and videos are available at https://vitalprecise.github.io.
title Touch begins where vision ends: Generalizable policies for contact-rich manipulation
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.13762