Paper page - DONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations

Source: https://huggingface.co/papers/2610.29997

Abstract

DONIC is a generalist bimanual tracker trained on diverse human-motion data that uses reinforcement learning with recycled demonstrations and per-hand rewards to achieve high success on unseen objects without fine-tuning.

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-richbimanual manipulationdata 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 combinesproximal policy optimizationwithbehavioral cloningin a feedback loop that recycles verified successful executions into training demonstrations. An object-centeredper-hand rewardmaintains object-motion feedback while supervising each hand according to its reference contact role.Clip-Centered Advantagesremove 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.

View arXiv pageView PDFProject pageGitHub20Add to collection

Get this paper in your agent:

hf papers read 2610\.29997

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.29997 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.29997 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.29997 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.