NeRP: Neural Rearrangement Planning for Unknown Objects


Ahmed H Qureshi (UC San Diego),
Arsalan Mousavian (NVIDIA),
Chris Paxton (NVIDIA),
Michael Yip (UC San Diego),
Dieter Fox (NVIDIA)
Paper Website
Code
Paper #072
Interactive Poster Session V Interactive Poster Session VIII

0d 00h 00m

0d 00h 00m


Abstract

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.

Spotlight Presentation

Previous Paper Paper Website Next Paper