Benchmark Radar™
Star —

HumanoidVLN Benchmark

Explore score history ↗

Evaluates vision-language navigation for humanoid robots across four embodiments in physics-grounded simulator scenarios. Includes 933 episodes with instructions and multiple stylistic variants, assessing success rate and normalized Dynamic Time Warping.

Released
2026-08-13
Institutions
University of Southern California
Evaluates
Multimodal, Robotics & Embodied AI
Openness
unknown
Importer
Claire Radar
Review status
unreviewed

HumanoidVLN paper

No reported scores are on record for this benchmark yet.

Which sources cite HumanoidVLN?

Related Multimodal, Robotics & Embodied AI benchmarks