Metraipolis › archive › dc_07aafae68576

SoGuDiff: Socially Guided Diffusion for Steerable, Norm-Grounded Robot Navigation — arXiv:2609.30560

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30560
License (as archived)
CC0-1.0
Archived
2026-10-08T03:14:45.392Z
SHA-256 of the archived text
26319b17ccaee04007e39a491f8df964273f8e7cad2324d74f8cdf67387aa6b1
Stable URL of this page
https://metraipolis.com/documento/dc_07aafae68576

How to cite

SoGuDiff: Socially Guided Diffusion for Steerable, Norm-Grounded Robot Navigation — arXiv:2609.30560 — arXiv (en), https://arxiv.org/abs/2609.30560 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_07aafae68576 (Metraipolis archive dc_07aafae68576, sha256 26319b17ccaee04007e39a491f8df964273f8e7cad2324d74f8cdf67387aa6b1)
BibTeX
@misc{dc07aafae68576,
  title = {SoGuDiff: Socially Guided Diffusion for Steerable, Norm-Grounded Robot Navigation — arXiv:2609.30560},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30560},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_07aafae68576; sha256 26319b17ccaee04007e39a491f8df964273f8e7cad2324d74f8cdf67387aa6b1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30560. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Beyond collision avoidance, socially competent robot navigation requires adherence to implicit social conventions that vary across contexts, cultures, and deployment requirements. Many conventional navigation policies learn a single normative behavior, either through reinforcement learning against a fixed reward function or imitation of human demonstrations, exposing no interface for adjusting that conduct at runtime. We present a diffusion-based navigation framework whose social behavior can be tuned at deployment: a desired style is specified, such as how closely the robot passes, which side it yields to, or how much it defers to groups, and the planner adapts accordingly. Continuous style axes can be followed independently or composed, spanning a behavioral space rather than discrete, primitive-based specifications. A feasibility projection layer separates learned social behavior from kinematic feasibility and collision avoidance. A single-axis sweep illustrates a tradeoff curve that strictly dominates the evaluated fixed-behavior baseline configurations, and stylistic differences are replicated in real-world demonstrations.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-28 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.30560 — 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 2026-10-08T02:58:08.811Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).