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 等 11 人
Ropedia
在最新榜 #109 本站收录于 2026-10-23
一句话要点
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。
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.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：视觉理解与 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
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-23。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。