@COMMENT This file was generated by bib2html.pl <http://www.cs.cmu.edu/~pfr/misc_software/index.html#bib2html> version 0.90
@COMMENT written by Patrick Riley <http://www.cs.cmu.edu/~pfr>
@COMMENT This file came from Peter Stone's publication pages at
@COMMENT http://www.cs.utexas.edu/~pstone/papers
@inproceedings{corl2022-zhu,
  title={VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priors},
  author={Yifeng Zhu and Abhishek Joshi and Peter Stone and Yuke Zhu},
  booktitle={Proceedings of the 6th Conference on Robot Learning (CoRL 2022)},
  location = {Auckland, New Zealand},
  month={December},
  year={2022},
  doi={},
  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 percents 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.},
  wwwnote={<a href="https://ut-austin-rpl.github.io/VIOLA" target="_blank">Project page</a><br><a href="https://github.com/UT-Austin-RPL/VIOLA">Code</a>}
}