Probable Object Location (POLo) Score Estimation for Efficient Object Goal Navigation
This addresses efficiency and memory issues in autonomous robotics for object goal navigation, though it appears incremental as it builds on existing map-based and RL approaches.
The paper tackles the problem of object search in unexplored environments by introducing the Probable Object Location (POLo) score and POLoNet, a neural network that approximates it, resulting in an agent that significantly outperforms baseline methods in the OVMM 2023 challenge.
To advance the field of autonomous robotics, particularly in object search tasks within unexplored environments, we introduce a novel framework centered around the Probable Object Location (POLo) score. Utilizing a 3D object probability map, the POLo score allows the agent to make data-driven decisions for efficient object search. We further enhance the framework's practicality by introducing POLoNet, a neural network trained to approximate the computationally intensive POLo score. Our approach addresses critical limitations of both end-to-end reinforcement learning methods, which suffer from memory decay over long-horizon tasks, and traditional map-based methods that neglect visibility constraints. Our experiments, involving the first phase of the OVMM 2023 challenge, demonstrate that an agent equipped with POLoNet significantly outperforms a range of baseline methods, including end-to-end RL techniques and prior map-based strategies. To provide a comprehensive evaluation, we introduce new performance metrics that offer insights into the efficiency and effectiveness of various agents in object goal navigation.