Adapt3R: Adaptive 3D Scene Representation for Domain Transfer in Imitation Learning
This addresses the problem of domain transfer in imitation learning for robotics, offering a general-purpose solution that is incremental but effective.
The paper tackles the brittleness of imitation learning policies to out-of-distribution observations by proposing Adapt3R, a 3D observation encoder that uses a pretrained 2D backbone for semantic information and 3D for localization, enabling zero-shot transfer to novel embodiments and camera poses across 93 simulated and 6 real tasks.
Imitation Learning can train robots to perform complex and diverse manipulation tasks, but learned policies are brittle with observations outside of the training distribution. 3D scene representations that incorporate observations from calibrated RGBD cameras have been proposed as a way to mitigate this, but in our evaluations with unseen embodiments and camera viewpoints they show only modest improvement. To address those challenges, we propose Adapt3R, a general-purpose 3D observation encoder which synthesizes data from calibrated RGBD cameras into a vector that can be used as conditioning for arbitrary IL algorithms. The key idea is to use a pretrained 2D backbone to extract semantic information, using 3D only as a medium to localize this information with respect to the end-effector. We show across 93 simulated and 6 real tasks that when trained end-to-end with a variety of IL algorithms, Adapt3R maintains these algorithms' learning capacity while enabling zero-shot transfer to novel embodiments and camera poses.