VIOLA: Object-Centric Imitation Learning for Vision-Based Robot ManipulationDownload PDF

16 Jun 2022, 10:45 (modified: 06 Nov 2022, 15:11)CoRL 2022 PosterReaders: Everyone
Student First Author: yes
Keywords: Imitation Learning, Robot Manipulation, Object-Centric Representation
TL;DR: We introduce an object-centric imitation learning approach for robot manipulation that acquire robust, closed-loop visuomotor poicy.
Abstract: We introduce VIOLA, an object-centric imitation learning approach to learning closed-loop visuomotor policies for robot manipulation. Our approach constructs object-centric representations based on general object proposals from a pre-trained vision model. VIOLA uses a transformer-based policy to reason over these representations and attend to the task-relevant visual factors for action prediction. Such object-based structural priors improve deep imitation learning algorithm's robustness against object variations and environmental perturbations. We quantitatively evaluate VIOLA in simulation and on real robots. VIOLA outperforms the state-of-the-art imitation learning methods by $45.8%$ in success rate. It has also been deployed successfully on a physical robot to solve challenging long-horizon tasks, such as dining table arrangement and coffee making. More videos and model details can be found in supplementary material and the project website:
Supplementary Material: zip
20 Replies