4 papers
Transformer Transformer: A Unified Model for Motion-Conditioned Robot Co-design
Huy Ha, C. Karen Liu, Shuran Song
An often overlooked factor of robot manipulation performance is the embodiment of the robot itself. Motivated by this problem, we study motion-conditioned robot co-design, where th…
UMI-Underwater: Learning Underwater Manipulation without Underwater Teleoperation
Hao Li, Long Yin Chung, Jack Goler +5
Underwater robotic grasping is difficult due to degraded, highly variable imagery and the expense of collecting diverse underwater demonstrations. We introduce a system that (i) au…
UMI-on-Air: Embodiment-Aware Guidance for Embodiment-Agnostic Visuomotor Policies
Harsh Gupta, Xiaofeng Guo, Huy Ha +6
We introduce UMI-on-Air, a framework for embodiment-aware deployment of embodiment-agnostic manipulation policies. Our approach leverages diverse, unconstrained human demonstration…
DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
Alexander Khazatsky, Karl Pertsch, Suraj Nair +98
The creation of large, diverse, high-quality robot manipulation datasets is an important stepping stone on the path toward more capable and robust robotic manipulation policies. Ho…