Stable Object Reorientation using Contact Plane Registration

Richard Li; Carlos Esteves; Ameesh Makadia; Pulkit Agrawal

ICRA 2022poster3 citations

Stable Object Reorientation using Contact Plane Registration

Richard Li, Carlos Esteves, Ameesh Makadia, Pulkit Agrawal

Abstract

We present a system for accurately predicting stable orientations for diverse rigid objects. We propose to overcome the critical issue of modelling multimodality in the space of rotations by using a conditional generative model to accurately classify contact surfaces. Our system is capable of operating from noisy and partially-observed pointcloud observations captured by real world depth cameras. Our method substantially outperforms the current state-of-the-art systems on a simulated stacking task requiring highly accurate rotations, and demonstrates strong sim2real zero-shot transfer results across a variety of unseen objects on a real world reorientation task.

BibTeX

@inproceedings{icra2022_stableobjectreor,
  title = {Stable Object Reorientation using Contact Plane Registration},
  author = {Richard Li and Carlos Esteves and Ameesh Makadia and Pulkit Agrawal},
  booktitle = {ICRA 2022},
  year = {2022}
}