Metraipolis › archive › dc_cc230de99b6a

HumanoidVLN: A Physics-Grounded Simulator and Benchmark for Vision-Language Navigation Across Diverse Humanoid Embodiments — arXiv:2608.12860

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.12860
License (as archived)
CC0-1.0
Archived
2026-10-19T04:56:27.572Z
SHA-256 of the archived text
1347b74c90f69bd0d9e0286cecaa99c44bbb26d06821c73f6c5f46ffdc3db56c
Stable URL of this page
https://metraipolis.com/documento/dc_cc230de99b6a

How to cite

HumanoidVLN: A Physics-Grounded Simulator and Benchmark for Vision-Language Navigation Across Diverse Humanoid Embodiments — arXiv:2608.12860 — arXiv (en), https://arxiv.org/abs/2608.12860 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cc230de99b6a (Metraipolis archive dc_cc230de99b6a, sha256 1347b74c90f69bd0d9e0286cecaa99c44bbb26d06821c73f6c5f46ffdc3db56c)
BibTeX
@misc{dccc230de99b6a,
  title = {HumanoidVLN: A Physics-Grounded Simulator and Benchmark for Vision-Language Navigation Across Diverse Humanoid Embodiments — arXiv:2608.12860},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.12860},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cc230de99b6a; sha256 1347b74c90f69bd0d9e0286cecaa99c44bbb26d06821c73f6c5f46ffdc3db56c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12860. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-Language Navigation (VLN) for humanoid robots poses challenges existing benchmarks fail to address: bipedal locomotion imposes physical constraints absent from wheeled agents, humanoid morphologies vary across platforms, and egocentric observations are distorted by locomotion-induced camera dynamics. We present HumanoidVLN, a physics-grounded simulator and benchmark for VLN across diverse humanoid embodiments. Built on NVIDIA Isaac Sim, our platform supports an extensible set of humanoid configurations, demonstrated on four robots (Unitree G1, Unitree H1, Internal-A, Internal-B) spanning 10-12 lower-body DoF and heights from 1.17m to 1.80m, via a hierarchical control stack combining a reinforcement learning locomotion policy with interchangeable PD or MPC path trackers. New robots and VLN models integrate with minimal effort; we demonstrate compatibility with NaVILA, DualVLN, StreamVLN, and JanusVLN. Environments are drawn from artist-designed scenes and 3D Gaussian Splatting reconstructions, filtered for navigable areas exceeding 100 square meters. Instructions are generated by a dual generator-reviewer plus paraphraser multi-agent pipeline with human-in-the-loop verification, yielding 933 collision-aware reference episodes, each paired with one fine-grained instruction and three coarse-grained stylistic variants (formal, natural, casual). Across four models and four embodiments, JanusVLN achieves the highest mean success rate of 43.55% and nDTW of 48.38. In a 20-episode sim-to-real pilot with DualVLN and the Unitree G1, navigation errors correlate strongly (r=0.935), with a mean absolute difference of 0.68m and mean trajectory similarity of 0.782 (+/-0.188) nDTW. These results highlight the interaction between VLN models, controllers, and humanoid embodiments under physical execution. Code, benchmark, and data will be released upon acceptance at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-14 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.12860 — 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 2026-10-19T04:47:48.652Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).