Get Started
Research questionHow can dexterous robot hands generalize a manipulation skill from one demonstration to varied objects despite sim-to-real gaps?Dexterous hands must reproduce useful contact strategies with limited real-world training data. Variation in object properties and discrepancies between simulation and reality make reliable transfer difficult.
Machine Learning
Reinforcement Learning
Robotics
Latest papersRecent research connected to this question, newest first.One Demonstration, Many Objects: Generalizing Manipulation via Local Contact GeometryThe source studies a policy trained from human demonstrations for multi-fingered hands, targeting objects that vary in shape, scale, mass, and friction. Real-world evidence covers 16 objects, four tasks, and two robot-hand embodiments, reporting 71% success; the source does not establish broader deployment performance.research paper · Sep 3, 2026
Related questions
How can robots learn robust, generalist bimanual household manipulation from limited human demonstrations?How can web videos provide relevant human demonstrations for long-tail dexterous robot manipulation?How can robots safely learn dynamic manipulation skills online despite sim-to-real mismatch?How can robot perception encode action-relevant scene dynamics to improve manipulation generalization?
Home
Topics
Search
Library