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

Hindi

एक अद्वितीय उद्देश्य संदर्भ ट्रैकिंग में हाल के प्रगति के बावजूद, मौजूदा मॉडल मुख्य रूप से एकल-हाउस संदर्भ ट्रैकिंग और इंटरैक्शन की एक सीमित श्रृंखला पर ध्यान केंद्रित करते हैं, जिससे वास्तविक जीवन में आम दो-हाउस संदर्भ व्यवहारों को अनियंत्रित किया जाता है। संपर्क समृद्ध दो-हाउस संदर्भ ट्रैकिंग डेटा की कमी और समन्वय संदर्भों की बढ़ी हुई जटिलता 229 वस्तुओं को फैलाती है और स्थायी दो-हाउस ट्रैकर का विकास विशेष रूप से चुनौतीपूर्ण बनाती है। इसलिए, हम प्रस्तुत करते हैं 1) DONIC, पहला सामान्य दो-हाउस ट्रैकर संयुक्त रूप से ऑपरेशन श्रेणियों और मानव-मोशन स्रोतों के बीच प्रशिक्षित

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