Efficient Object Rearrangement via Multi-view Fusion

TL;DR

This paper presents a multi-view fusion approach for assistive robot object rearrangement, significantly improving efficiency by reducing redundant manipulations through multi-view observations and accurate pose estimation.

Contribution

The paper introduces a novel multi-view fusion system for object rearrangement that enhances pose estimation accuracy and reduces manipulation steps compared to single-view methods.

Findings

Outperforms existing single-view systems in simulation

Validated effectiveness through physical experiments

Reduces redundant manipulations in object rearrangement

Abstract

The prospect of assistive robots aiding in object organization has always been compelling. In an image-goal setting, the robot rearranges the current scene to match the single image captured from the goal scene. The key to an image-goal rearrangement system is estimating the desired placement pose of each object based on the single goal image and observations from the current scene. In order to establish sufficient associations for accurate estimation, the system should observe an object from a viewpoint similar to that in the goal image. Existing image-goal rearrangement systems, due to their reliance on a fixed viewpoint for perception, often require redundant manipulations to randomly adjust an object's pose for a better perspective. Addressing this inefficiency, we introduce a novel object rearrangement system that employs multi-view fusion. By observing the current scene from multiple viewpoints before manipulating objects, our approach can estimate a more accurate pose without redundant manipulation times. A standard visual localization pipeline at the object level is developed to capitalize on the advantages of multi-view observations. Simulation results demonstrate that the efficiency of our system outperforms existing single-view systems. The effectiveness of our system is further validated in a physical experiment.