Safe, Occlusion-Aware Manipulation for Online Object Reconstruction in Confined Spaces

TL;DR

This paper introduces a safe, occlusion-aware manipulation framework for online object reconstruction in confined spaces, ensuring completeness and demonstrating superior performance over baselines in simulated cluttered environments.

Contribution

It formulates a general manipulation task with safety and completeness guarantees and develops an algorithm for monotone instances, validated through empirical evaluation.

Findings

Proposed algorithm outperforms random and greedy baselines

Maintains high success rate in cluttered scenes

Ensures safety and completeness in object reconstruction

Abstract

Recent work in robotic manipulation focuses on object retrieval in cluttered spaces under occlusion. Nevertheless, the majority of efforts lack an analysis of conditions for the completeness of the approaches or the methods apply only when objects can be removed from the workspace. This work formulates the general, occlusion-aware manipulation task, and focuses on safe object reconstruction in a confined space with in-place rearrangement. It proposes a framework that ensures safety with completeness guarantees. Furthermore, an algorithm, which is an instantiation of this abstract framework for monotone instances is developed and evaluated empirically by comparing against a random and a greedy baseline on randomly generated experiments in simulation. Even for cluttered scenes with realistic objects, the proposed algorithm significantly outperforms the baselines and maintains a high success rate across experimental conditions.