Towards Optimal Correlational Object Search

TL;DR

This paper introduces COS-POMDP, a hierarchical planning approach that models correlations for efficient object search in complex environments, improving success rates especially for hard-to-detect objects.

Contribution

The paper presents the COS-POMDP framework and a hierarchical planning algorithm that effectively incorporates correlations while maintaining optimality in object search tasks.

Findings

Outperforms baselines in object search success rate

More efficient search for hard-to-detect objects

Validated with AI2-THOR and YOLOv5

Abstract

In realistic applications of object search, robots will need to locate target objects in complex environments while coping with unreliable sensors, especially for small or hard-to-detect objects. In such settings, correlational information can be valuable for planning efficiently. Previous approaches that consider correlational information typically resort to ad-hoc, greedy search strategies. We introduce the Correlational Object Search POMDP (COS-POMDP), which models correlations while preserving optimal solutions with a reduced state space. We propose a hierarchical planning algorithm to scale up COS-POMDPs for practical domains. Our evaluation, conducted with the AI2-THOR household simulator and the YOLOv5 object detector, shows that our method finds objects more successfully and efficiently compared to baselines,particularly for hard-to-detect objects such as srub brush and remote control.