Towards Optimal Correlational Object Search

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.

Authors

• Kaiyu Zheng
• Rohan Chitnis
• Yoonchang Sung
• George Konidaris 0001
• Stefanie Tellex

Keywords

• Correlation
• Brushes
• Automation
• Detectors
• Aerospace electronics
• Search problems
• Robot sensing systems
• State Space
• Object Detection
• Target Object
• Field Of View
• Detection Model
• Object Classification
• Object Location
• Term In Eq
• Transition Model
• Reward Function
• Success Criteria
• Graph Topology
• Observation Space
• Robot State
• Belief State
• Conditional Independence Assumption
• Room Type
• Robot Capabilities
• Alarm Clock
• Training Scenes
• True Positive Detection
• Orientation Of The Robot
• True Detection
• Target State
• Objective Conditions
• Search Efficiency