Presentation

· Contributors · Organizations · Search Program · My Schedule

SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrations

DescriptionThis work addresses the challenge of learning robust interaction skills from limited demonstrations. By introducing novel data augmentation techniques for skill transitions and recovery patterns, combined with enhanced reinforcement imitation learning methods, we achieve superior performance in learning interaction skills, demonstrating improved generalization and recovery capabilities across diverse manipulation tasks.

Authors

Runyi Yu

Hong Kong University of Science and Technology

Shanghai Aritificial Intelligence Laboratory

Yinhuai Wang

Hong Kong University of Science and Technology

Qihan Zhao

Hong Kong University of Science and Technology

Hok Wai Tsui

Hong Kong University of Science and Technology

Jingbo Wang

Shanghai Aritificial Intelligence Laboratory