DONIC Dual Arm Tracking Model Released
The story so far
DONIC, through reinforcement learning and cyclic demonstration training, has become the first general two-arm tracking model to achieve an 86.79% success rate on unseen objects without fine-tuning, surpassing existing baselines by 77.36 percentage points. The model combines proximal policy optimization with behavioral cloning and employs an object-centered per-hand reward mechanism.
AI-written from the reports · Updated 27 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- Hugging Face Daily PapersDONIC: Generalist Dexterous Bimanual Tracking Control from Human Demonstrations
DONIC is the first general-purpose two-arm tracking model, achieving 86.79% success rate on unseen objects without fine-tuning, surpassing existing two-arm tracking baselines by 77.36 percentage points; it combines near-end strategy optimization with behavior cloning and employs an object-centered per-hand reward mechanism.