Robotics: Science and Systems XVII
NeRP: Neural Rearrangement Planning for Unknown Objects
Ahmed H Qureshi, Arsalan Mousavian, Chris Paxton, Michael Yip, Dieter FoxAbstract:
Robots will be expected to manipulate a wide variety of objects in complex and arbitrary ways as they become more widely used in human environments. As such; the rearrangement of objects has been noted to be an important benchmark for AI capabilities in recent years. We propose NeRP (Neural Rearrangement Planning); a deep learning based approach for multi-step neural object rearrangement planning which works with never-before-seen objects; that is trained on simulation data; and generalizes to the real world. We compare NeRP to several naive and model-based baselines; demonstrating that our approach is measurably better and can efficiently arrange unseen objects in fewer steps and with less planning time. Finally; we demonstrate it on several challenging rearrangement problems in the real world.
Bibtex:
@INPROCEEDINGS{Qureshi-RSS-21, AUTHOR = {Ahmed H Qureshi AND Arsalan Mousavian AND Chris Paxton AND Michael Yip AND Dieter Fox}, TITLE = {{NeRP: Neural Rearrangement Planning for Unknown Objects}}, BOOKTITLE = {Proceedings of Robotics: Science and Systems}, YEAR = {2021}, ADDRESS = {Virtual}, MONTH = {July}, DOI = {10.15607/RSS.2021.XVII.072} }