Physically rearranging objects is an important capability for embodied agents. Visual room rearrangement evaluates an agent's ability to rearrange objects in a room to a desired goal based solely on visual input. We propose a simple yet effective method for this problem: (1) search for and map which objects need to be rearranged, and (2) rearrange each object until the task is complete. Our approach consists of an off-the-shelf semantic segmentation model, voxel-based semantic map, and semantic search policy to efficiently find objects that need to be rearranged. On the AI2-THOR Rearrangement Challenge, our method improves on current state-of-the-art end-to-end reinforcement learning-based methods that learn visual rearrangement policies from 0.53% correct rearrangement to 16.56%, using only 2.7% as many samples from the environment.
@article{arxiv.2206.13396,
title = {A Simple Approach for Visual Rearrangement: 3D Mapping and Semantic Search},
author = {Brandon Trabucco and Gunnar Sigurdsson and Robinson Piramuthu and Gaurav S. Sukhatme and Ruslan Salakhutdinov},
journal= {arXiv preprint arXiv:2206.13396},
year = {2022}
}
Comments
Winner of the Rearrangement Challenge at CVPR 2022