LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation
Research
Source: arXiv cs.ROPublish time unverified
arXiv:2608.30935v1 Announce Type: new Abstract: Embodied navigation requires agents to translate heterogeneous goals and visual observations into actions across tasks, environments, and robot embodiments. Modern vision-language models (VLMs) already encode spatial priors for visual grounding, spatial reasoning, and pointing, but these capabilities are rarely elicited directly for robot control.