Dex-One2Many: Learning Dexterous Manipulation from a Single Human Demonstration
Dex-One2Many: Learning Dexterous Manipulation from a Single Human Demonstration
Dex-One2Many is a real-to-sim-to-real framework that learns a generalizable dexterous manipulation policy from a single human video. By abstracting the video into sequential scene graphs, the method guides reinforcement learning to enable efficient exploration and broad generalization. It outperforms baselines by 6.5% in seen configurations and achieves a 71% performance gap in unseen scenarios when transferred to a real multi-fingered hand.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Environment
- SimulationOpen source S5
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
oration short and guided. Trained entirely in simulation, Dex-One2Many transfers zero-shot to a real multi-fingered hand. Across five tool-use and manipulation tasks, Dex-One2Many exceeds baselines by 6.5% in seen configurations, while its robust generalization widens this gap to 71% in unseen scenarios.
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org