Metraipolis › archive › dc_ae39b04cf6fc

UniNav: A Unified World-Action Diffusion Model for Visual Navigation — arXiv:2608.03244

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03244
License (as archived)
CC0-1.0
Archived
2026-10-31T12:15:40.620Z
SHA-256 of the archived text
b941fe583a24c525b620ec02ecb2e160dbe17bfee296d6e9fea8b3d26d752c13
Stable URL of this page
https://metraipolis.com/documento/dc_ae39b04cf6fc

How to cite

UniNav: A Unified World-Action Diffusion Model for Visual Navigation — arXiv:2608.03244 — arXiv (en), https://arxiv.org/abs/2608.03244 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ae39b04cf6fc (Metraipolis archive dc_ae39b04cf6fc, sha256 b941fe583a24c525b620ec02ecb2e160dbe17bfee296d6e9fea8b3d26d752c13)
BibTeX
@misc{dcae39b04cf6fc,
  title = {UniNav: A Unified World-Action Diffusion Model for Visual Navigation — arXiv:2608.03244},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03244},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ae39b04cf6fc; sha256 b941fe583a24c525b620ec02ecb2e160dbe17bfee296d6e9fea8b3d26d752c13},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03244. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Image-goal visual navigation is a fundamental capability for embodied agents. Existing navigation policies efficiently predict waypoint trajectories but lack visual foresight, while navigation world models can anticipate future observations but often require costly planning rollouts. We present UniNav, a unified world-action model that generates future visual observations and continuous waypoint trajectories through a single diffusion process. Given history frames and a goal image, UniNav jointly denoises visual and waypoint tokens within a single transformer, unifying future prediction and action generation in a shared framework. To improve spatial grounding, we incorporate geometry-aware camera tokens. We also train on both trajectory-labeled navigation data and video-only data, enabling the model to benefit from diverse videos without waypoint annotations. Based on this unified framework, we introduce two variants: UniNav-Full jointly predicts interpretable future observations and their corresponding trajectories, while UniNav-Fast removes future-image tokens at inference for efficient trajectory prediction. Experiments on navigation benchmarks show that UniNav outperforms the strongest baseline in ATE across all datasets. With one-step inference, UniNav-Fast achieves a latency of 0.1s without a substantial accuracy drop. Code will be released.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.03244 — 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 2026-10-31T12:05:52.769Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).