G2-Nav: Grounded and Guarded Vision-Language Costmaps for Robot Social Navigation
Robotics
Summary
The authors developed G2-Nav, a system that helps robots navigate busy places safely and politely. Instead of letting a big language-vision model decide everything at once, their system turns the model's smart understanding into easy-to-read maps showing where it’s safe to go and where people are. They also add extra safety checks to make sure the robot doesn’t make sudden mistakes. Their tests in real settings show that G2-Nav helps robots move around efficiently without bumping into people or breaking social rules.
Authors
Yuwen Liao, Yihang Lan, Yizhuo Yang, Ruimeng Liu, Xinhang Xu, Shenghai Yuan, Lihua Xie
Abstract
Social navigation requires the robot to reason and respond in complex real-world environments. While recent works attempt to incorporate human-level intelligence into robot planning using large Vision-Language Models (VLMs), end-to-end frameworks often create an unpredictable black-box, and existing instruction-following methods are not designed for full autonomy. To bridge this gap, we present G2-Nav, a novel framework that grounds abstract social reasoning and guards safe real-world deployment. Instead of asking the VLM for direct planning decisions, G2-Nav translates its semantic reasoning into a vision-language costmap with reliability and interpretability. The VLM evaluates traversable regions and social agents from open-set perception, mapping social context into the costmap. To improve real-world robustness, the VLM performs semantic verification on upstream tracking, and we introduce a high-frequency safety check to guard against system latency prior to trajectory generation. We demonstrate through real-world experiments that G2-Nav delivers safe, efficient, and socially compliant autonomous navigation in unstructured environments. Code will be made publicly available.