arXiv 2610.29997 · cs.RO · 2026-10-21
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 and 3 more
Ropedia
In latest · #109 Added on 2026-10-23
One-line takeaway
DONIC is the first generalist bimanual dexterous tracker trained jointly across operation categories and human-motion sources, combining PPO with behaviour cloning and recycling successful runs; it ships with BiHOI, a 1,575-sequence, 229-object multi-view dataset.
DONIC 是首个跨操作类别、跨人体动作来源联合训练的通用双手灵巧追踪控制器，结合 PPO 与行为克隆并回收成功轨迹；同时发布含 229 个物体、1575 段序列的多视角双手交互数据集 BiHOI。
Read on arXiv PDF Hugging Face discussion Code Project page
Topics & disciplines
More on Vision & 3D
- VisionHOPE: Visual Backbones as Self-Modifying Learning Systems ▲296
- EgoXperience: Learning World-Grounded Egocentric Representations from Human Experience ▲187
- Holi-World: Building Holistic World Intelligence from Human-Ego Experience ▲170
- GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed ▲94
- Spectral-Spatial Interpretation ▲81
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-23.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.