CUBic: Coordinated Unified Bimanual Perception and Control Framework

2026-05-13

AI Summary

This work addresses the challenge in visuomotor control for dual-arm robots, where existing approaches either decouple the arms to avoid interference or rely on handcrafted, strongly coupled mechanisms, thereby compromising either independence or coordination. To overcome this limitation, the authors propose the CUBic framework, which uniquely formulates dual-arm coordination as a unified perception problem. CUBic intrinsically balances coordination and independence through a shared tokenized representation, eliminating the need for manual coupling design. The framework integrates unidirectional perception aggregation, bidirectional perception coordination—enabled by two shared mapping codebooks—and a unified perception-to-control diffusion policy. Evaluated on the RoboTwin benchmark, CUBic significantly outperforms current methods, achieving notable improvements in both coordination accuracy and task success rate.

Abstract

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.

Problem

• bimanual manipulation
• visuomotor policy
• perception and control
• coordination
• robotic learning

Innovation

• bimanual manipulation
• unified perception
• tokenized representation
• diffusion policy
• visuomotor control