CUBic: Coordinated Unified Bimanual Perception and Control Framework

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Xingyu, Ding, Pengxiang, Xu, Jingkai, Wang, Donglin, Fan, Zhaoxin
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917491192627200
author Wang, Xingyu
Ding, Pengxiang
Xu, Jingkai
Wang, Donglin
Fan, Zhaoxin
author_facet Wang, Xingyu
Ding, Pengxiang
Xu, Jingkai
Wang, Donglin
Fan, Zhaoxin
contents Recent advances in visuomotor policy learning have enabled robots to perform control directly from visual inputs. Yet, extending such end-to-end learning from single-arm to bimanual manipulation remains challenging due to the need for both independent perception and coordinated interaction between arms. Existing methods typically favor one side -- either decoupling the two arms to avoid interference or enforcing strong cross-arm coupling for coordination -- thus lacking a unified treatment. We propose CUBic, a Coordinated and Unified framework for Bimanual perception and control that reformulates bimanual coordination as a unified perceptual modeling problem. CUBic learns a shared tokenized representation bridging perception and control, where independence and coordination emerge intrinsically from structure rather than from hand-crafted coupling. Our approach integrates three components: unidirectional perception aggregation, bidirectional perception coordination through two codebooks with shared mapping, and a unified perception-to-control diffusion policy. Extensive experiments on the RoboTwin benchmark show that CUBic consistently surpasses standard baselines, achieving marked improvements in coordination accuracy and task success rates over state-of-the-art visuomotor baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2605_13452
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle CUBic: Coordinated Unified Bimanual Perception and Control Framework
Wang, Xingyu
Ding, Pengxiang
Xu, Jingkai
Wang, Donglin
Fan, Zhaoxin
Robotics
Artificial Intelligence
Recent advances in visuomotor policy learning have enabled robots to perform control directly from visual inputs. Yet, extending such end-to-end learning from single-arm to bimanual manipulation remains challenging due to the need for both independent perception and coordinated interaction between arms. Existing methods typically favor one side -- either decoupling the two arms to avoid interference or enforcing strong cross-arm coupling for coordination -- thus lacking a unified treatment. We propose CUBic, a Coordinated and Unified framework for Bimanual perception and control that reformulates bimanual coordination as a unified perceptual modeling problem. CUBic learns a shared tokenized representation bridging perception and control, where independence and coordination emerge intrinsically from structure rather than from hand-crafted coupling. Our approach integrates three components: unidirectional perception aggregation, bidirectional perception coordination through two codebooks with shared mapping, and a unified perception-to-control diffusion policy. Extensive experiments on the RoboTwin benchmark show that CUBic consistently surpasses standard baselines, achieving marked improvements in coordination accuracy and task success rates over state-of-the-art visuomotor baselines.
title CUBic: Coordinated Unified Bimanual Perception and Control Framework
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2605.13452