[
    {
        "id": "osp-18414",
        "type": "article-journal",
        "title": "Learning Modular Policy for Multi-Floor Object Navigation:A Factorized Framework for Diagnostic Study",
        "author": [
            {
                "family": "Zhai",
                "given": "Shichao"
            },
            {
                "family": "Ye",
                "given": "Shuhao"
            },
            {
                "family": "Xiong",
                "given": "Rong"
            },
            {
                "family": "Wang",
                "given": "Yue"
            }
        ],
        "URL": "https://omanscience.com/en/articles/learning-modular-policy-for-multi-floor-object-navigation-a-factorized-framework-for-diagnostic-study",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Object-goal navigation (ObjectNav) in multi-floor scenarios presents a challenge due to sparse rewards caused by long-horizon decision-making. In this paper, we propose a diagnostic study based on a modular framework with an effective learnable policy to analyze failure factors in multi-floor scenarios. To achieve an effective policy for diagnosis, we design the hierarchical factorization policy that deconstructs a single global policy into an intra-floor exploration policy and an inter-floor switching policy. To providing an effective initialization for Reinforcement Learning (RL), the lightweight intra-floor policy is learned by distilling the exploration logic of Visual Language Models (VLMs). Under idealized assumptions, we show that the factorized policy is theoretically equivalent to a single global policy at the policy-representation level. Experiment results indicate that perception performance and stair climbing stability are the primary bottlenecks in multi-floor navigation."
    }
]