UT Austin & Sony AI’s VIOLA Object-Centric Imitation Learning Method for Robot Manipulation Outperforms the SOTA by 45.8%

In the new paper VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priors, researchers from the University of Texas at Austin and Sony AI present VIOLA (Visuomotor Imitation via Object-centric LeArning), an object-centric imitation learning model that endows imitation learning with awareness regarding objects and their interactions.