Metraipolis › archive › dc_bc7716e5ae25

Affordance-Conditioned Decision Making: Bridging the Semantic-Spatial Gap in Zero-Shot Cross-Floor Vision-and-Language Navigation — arXiv:2609.32292

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.32292
License (as archived)
CC0-1.0
Archived
2026-10-07T21:00:02.129Z
SHA-256 of the archived text
4d460e2820a80273763ee07a4d5acc2263cde1e6566afebf8cc383670bdb8780
Stable URL of this page
https://metraipolis.com/documento/dc_bc7716e5ae25

How to cite

Affordance-Conditioned Decision Making: Bridging the Semantic-Spatial Gap in Zero-Shot Cross-Floor Vision-and-Language Navigation — arXiv:2609.32292 — arXiv (en), https://arxiv.org/abs/2609.32292 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bc7716e5ae25 (Metraipolis archive dc_bc7716e5ae25, sha256 4d460e2820a80273763ee07a4d5acc2263cde1e6566afebf8cc383670bdb8780)
BibTeX
@misc{dcbc7716e5ae25,
  title = {Affordance-Conditioned Decision Making: Bridging the Semantic-Spatial Gap in Zero-Shot Cross-Floor Vision-and-Language Navigation — arXiv:2609.32292},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.32292},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bc7716e5ae25; sha256 4d460e2820a80273763ee07a4d5acc2263cde1e6566afebf8cc383670bdb8780},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.32292. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-and-language navigation increasingly relies on general-purpose semantic planners, yet translating correct high-level intent into reliable physical execution remains difficult in spatially constrained transitions. Reaching a staircase, doorway, or narrow passage does not ensure traversal; the agent must identify an executable affordance pose and recover from accumulated action errors. We propose PACE (Preference-refined Affordance-Conditioned Execution), a supervised local execution module that augments frozen zero-shot semantic planners for reliable cross-floor navigation. PACE grounds transition-related semantics into a long-horizon, agent-centric traversable affordance pose and conditions short-horizon action generation on this spatial target, thereby aligning semantic goals with physical execution. We further post-train PACE through failure-aware preference refinement using rollout-derived pairs that contrast normal or recovery behaviors with deviation-amplifying behaviors, thereby improving closed-loop correction. We integrate PACE into six open-source zero-shot VLN navigators and demonstrate consistent improvements on the cross-floor subsets of R2R-CE and RxR-CE, increasing the average success rate from 16.35% to 27.65% and from 4.76% to 12.06%, respectively. Real-world experiments further demonstrate PACE's applicability in unseen environments, highlighting the potential of traversable affordances to bridge semantic intent and reliable embodied behavior.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.32292 — 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 2026-10-07T20:29:02.279Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).