Towards Optimal Correlational Object Search
This work addresses the challenge of object search for robots in realistic settings, representing an incremental improvement by scaling up existing POMDP models with hierarchical planning.
The paper tackles the problem of robots locating target objects in complex environments with unreliable sensors by introducing the Correlational Object Search POMDP (COS-POMDP) to model correlations for efficient planning, resulting in more successful and efficient object finding, especially for hard-to-detect objects like scrub brushes and remote controls.
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.