Metraipolis › archive › dc_f9d2ec1afbaf

DPed-VLN: A Benchmark for Socially Compliant Vision-and-Language Navigation in Dynamic Pedestrian Environments — arXiv:2609.21504

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.21504
License (as archived)
CC0-1.0
Archived
2026-10-10T02:30:11.152Z
SHA-256 of the archived text
c5f4088097fbd11bb448e60d4e85e369dd1fb2bbc4c995ea74dd03c065359256
Stable URL of this page
https://metraipolis.com/documento/dc_f9d2ec1afbaf

How to cite

DPed-VLN: A Benchmark for Socially Compliant Vision-and-Language Navigation in Dynamic Pedestrian Environments — arXiv:2609.21504 — arXiv (en), https://arxiv.org/abs/2609.21504 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f9d2ec1afbaf (Metraipolis archive dc_f9d2ec1afbaf, sha256 c5f4088097fbd11bb448e60d4e85e369dd1fb2bbc4c995ea74dd03c065359256)
BibTeX
@misc{dcf9d2ec1afbaf,
  title = {DPed-VLN: A Benchmark for Socially Compliant Vision-and-Language Navigation in Dynamic Pedestrian Environments — arXiv:2609.21504},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21504},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f9d2ec1afbaf; sha256 c5f4088097fbd11bb448e60d4e85e369dd1fb2bbc4c995ea74dd03c065359256},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21504. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-and-language navigation (VLN) has advanced rapidly in static indoor environments, but robots operating in human-populated spaces must ground language while responding to moving pedestrians and social-safety constraints. We present DPed-VLN, a Habitat 3.0 benchmark for dynamic-pedestrian VLN that couples 33,093 navigation episodes with paired global and prior-augmented instructions, ORCA-controlled humanoid pedestrians, socially constrained expert paths, and metrics that jointly assess navigation efficiency and social safety. DPed-VLN separates ordinary goal-oriented route guidance from prior-augmented instructions that expose dynamic-pedestrian cues for controlled analysis. To instantiate the benchmark, we introduce DPet (Dynamic Pedestrian-aware Network), a pedestrian-aware policy network trained with reinforcement learning and imitation learning. We further adapt representative state-of-the-art VLM-based navigation models, including NaVILA and StreamVLN, to DPed-VLN through LoRA fine-tuning. Experiments show that LoRA adaptation improves zero-shot VLM baselines in several success and safety metrics, especially reducing StreamVLN's collision rate. Among the evaluated methods, DPet-RL achieves the highest SR, SPL, and STL.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-21 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.21504 — 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 2026-10-10T02:09:55.353Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).