Metraipolis › archive › dc_77f435d5970b

Learning Modular Policy for Multi-Floor Object Navigation:A Factorized Framework for Diagnostic Study — arXiv:2610.06958

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.06958
License (as archived)
CC0-1.0
Archived
2026-10-07T13:11:40.211Z
SHA-256 of the archived text
c997ae17878b7e8ffb156ac0b3774d8e14b6bb997998ac6544d0fc81dd616439
Stable URL of this page
https://metraipolis.com/documento/dc_77f435d5970b

How to cite

Learning Modular Policy for Multi-Floor Object Navigation:A Factorized Framework for Diagnostic Study — arXiv:2610.06958 — arXiv (en), https://arxiv.org/abs/2610.06958 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_77f435d5970b (Metraipolis archive dc_77f435d5970b, sha256 c997ae17878b7e8ffb156ac0b3774d8e14b6bb997998ac6544d0fc81dd616439)
BibTeX
@misc{dc77f435d5970b,
  title = {Learning Modular Policy for Multi-Floor Object Navigation:A Factorized Framework for Diagnostic Study — arXiv:2610.06958},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.06958},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_77f435d5970b; sha256 c997ae17878b7e8ffb156ac0b3774d8e14b6bb997998ac6544d0fc81dd616439},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.06958. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.06958 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T12:42:33.490Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).