Metraipolis › archive › dc_89cf5446ee41

GS-PRM: Gaussian Visual Roadmap for Image-Goal Navigation — arXiv:2610.19541

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.19541
License (as archived)
CC0-1.0
Archived
2026-10-15T21:57:52.073Z
SHA-256 of the archived text
234fe6fde29ca8c00e82943d056b3a729fcaed128d6e8d016aee7d015e362eaf
Stable URL of this page
https://metraipolis.com/documento/dc_89cf5446ee41

How to cite

GS-PRM: Gaussian Visual Roadmap for Image-Goal Navigation — arXiv:2610.19541 — arXiv (en), https://arxiv.org/abs/2610.19541 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_89cf5446ee41 (Metraipolis archive dc_89cf5446ee41, sha256 234fe6fde29ca8c00e82943d056b3a729fcaed128d6e8d016aee7d015e362eaf)
BibTeX
@misc{dc89cf5446ee41,
  title = {GS-PRM: Gaussian Visual Roadmap for Image-Goal Navigation — arXiv:2610.19541},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19541},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_89cf5446ee41; sha256 234fe6fde29ca8c00e82943d056b3a729fcaed128d6e8d016aee7d015e362eaf},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19541. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Image-goal navigation requires a global planner that connects visually specified endpoints while providing observations that a local policy can follow. Three-dimensional Gaussian Splatting (3DGS) provides map-registered RGB, opacity, and depth renderings, but does not explicitly encode navigable topology. We introduce \method, a Gaussian visual roadmap whose milestones, local connections, and visual references are constructed directly through 3DGS rendering without deriving an occupancy grid or signed distance field. We define render-based collision-free (RC-free) configurations and paths. Panoramic depth supplies conservative clearance for milestone validation and adaptive coverage, while edge-aligned orthographic rendering tests the robot's swept volume. We establish conditional soundness and sufficient conditions for deterministic query completeness and probabilistic construction completeness of GS-PRM. To validate the performance of GS-PRM, we conduct experiments in both simulated and real-world environments, demonstrating long-horizon navigation using goal-conditioned policies guided by GS-PRM. Compared with a state-of-the-art 3DGS-based navigation system, our GS-PRM-based navigation system achieves up to a twice higher average success rate and reduces travel time by up to 57.2% when both systems complete the navigation task.

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/2610.19541 — 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 2026-10-15T21:38:44.453Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).