100 citations · 587 across the 34 of their papers we have counts for
3 papers · 1 filter
What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
Ajay Mandlekar, Danfei Xu, Josiah Wong +7
Imitating human demonstrations is a promising approach to endow robots with various manipulation capabilities. While recent advances have been made in imitation learning and batch…
Co-GAIL: Learning Diverse Strategies for Human-Robot Collaboration
Chen Wang, Claudia Pérez-D'Arpino, Danfei Xu +3
We present a method for learning a human-robot collaboration policy from human-human collaboration demonstrations. An effective robot assistant must learn to handle diverse human b…
Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Control
Chen Wang, Rui Wang, Ajay Mandlekar +3
Imitation Learning (IL) is an effective framework to learn visuomotor skills from offline demonstration data. However, IL methods often fail to generalize to new scene configuratio…