Newest papers

DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations

Mingze Sun, Ziang Cao, Yuan Fei, Qiankuan Tao, Zihan Wang, Tianqi Liu, Junhao Chen, Haiwen Diao, Fangzhou Hong, Zhaoxi Chen, Ziwei Liu · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29997 · cited by 0 works (OpenAlex) · open-access PDF

Arabic

على الرغم من التقدم السنوي في تسريع بيانات المرجعية الفردية، فإن النماذج الحالية تركز بشكل رئيسي على تسريع بيانات المرجعية الفردية والعديد من التفاعلات، مما يترتب عن ذلك 1) DONIC، أول مرجعي بيانات المرجعية الفردية المشتركة في الحياة الحقيقية، التي تم تدريبها بشكل مشترك على مختلف فئات العمليات ومصادر الحركة البشرية، جنبا إلى جنب مع 2) BiHOI، مجموعة من البيانات المتعددة المرتبطة بالمرجعية الفردية المرتبطة بالمرجعيات المرتبطة بالمرجعيات المرتبطة بالمرجعيات المرتبطة بالمرجعيات المرتبطة بالمرجعيات المرتبطة بالمرجعيات المرتبطة بالمر

Machine translation (Meta M2M100); the English original follows.

Abstract

Despite recent progress in dexterous reference tracking, existing models focus primarily on single-hand manipulation and a limited range of interactions, leaving the bimanual dexterous behaviors common in real life unaddressed. The scarcity of contact-rich bimanual manipulation data and the increased complexity of coordinating contacts make developing a generalist bimanual tracker particularly challenging. Therefore, we present 1) DONIC, the first generalist bimanual tracker jointly trained across operation categories and human-motion sources, together with 2) BiHOI, a multi-view dataset of 1,575 sequences spanning 229 objects and emphasizing sustained bimanual interaction, where reconstructed interactions are retargeted into robot references. DONIC combines proximal policy optimization with behavioral cloning in a feedback loop that recycles verified successful executions into training demonstrations. An object-centered per-hand reward maintains object-motion feedback while supervising each hand according to its reference contact role. Clip-Centered Advantages remove reference-dependent advantage offsets while preserving within-trajectory differences. Together, these designs enable one single policy to learn coordinated manipulation across heterogeneous references. Without finetuning, a single checkpoint achieves 86.79% success on unseen trajectories of training objects and 57.32% on held-out objects, surpassing the state-of-the-art bimanual tracking baselines by 77.36 and 45.73 percentage points.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Artificial intelligence, Tracking (education), Generalist and specialist species, Robot, Control (management)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange