SOURCE-LINKED INTELLIGENCE

C$^2$Nav: Compare Before You Commit for Zero-Shot Vision-and-Language Navigation

arXiv · AI, language, vision and robotics · article · Sep 14, 2026 · UTC

Zero-shot vision-and-language navigation in continuous environments (VLN-CE) increasingly places foundation vision-language models (VLMs) inside the navigation loop. Existing systems commonly request cardinal outputs such as waypoints, pixels, headings, progress values, or absolute arrival decisions, coupling a generative response to geometric magnitude or an irreversible commitment. We study a complementary model-robot interface: the VLM compares controller-constructed alternatives, while geometry, thresholds, action magnitude, and execution remain on the physical side. We instantiate this id

Read original source ↗ Open in workspace

recordType

paper

region

Global