Landmark Policy Optimization for Object Navigation Task
This addresses the problem of robust and optimal navigation for AI agents in unseen environments, though it appears incremental as it builds on existing hierarchical and modular approaches.
The paper tackles object goal navigation in unseen environments by proposing a hierarchical method that incorporates landmarks and skill-based algorithms, achieving a 0.75 success rate in simulation and validating results in real-world tests.
This work studies object goal navigation task, which involves navigating to the closest object related to the given semantic category in unseen environments. Recent works have shown significant achievements both in the end-to-end Reinforcement Learning approach and modular systems, but need a big step forward to be robust and optimal. We propose a hierarchical method that incorporates standard task formulation and additional area knowledge as landmarks, with a way to extract these landmarks. In a hierarchy, a low level consists of separately trained algorithms to the most intuitive skills, and a high level decides which skill is needed at this moment. With all proposed solutions, we achieve a 0.75 success rate in a realistic Habitat simulator. After a small stage of additional model training in a reconstructed virtual area at a simulator, we successfully confirmed our results in a real-world case.