Deep Object-Centric Representations for Generalizable Robot Learning

@article{Devin2018DeepOR,
  title={Deep Object-Centric Representations for Generalizable Robot Learning},
  author={Coline Devin and Pieter Abbeel and Trevor Darrell and Sergey Levine},
  journal={2018 IEEE International Conference on Robotics and Automation (ICRA)},
  year={2018},
  pages={7111-7118}
}
Robotic manipulation in complex open-world scenarios requires both reliable physical manipulation skills and effective and generalizable perception. In this paper, we propose using an object-centric prior and a semantic feature space for the perception system of a learned policy. We devise an object-level attentional mechanism that can be used to determine relevant objects from a few trajectories or demonstrations, and then immediately incorporate those objects into a learned policy. A task… CONTINUE READING

From This Paper

Topics from this paper.
3 Citations
38 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 38 references

Mask r-cnn. arxiv preprint

  • K. He, G. Gkioxari, P. Dollár, R. Girshick
  • arXiv preprint arXiv:1703.06870, 2017.
  • 2017
1 Excerpt

Similar Papers

Loading similar papers…