VLM-Social-Nav: Socially Aware Robot Navigation through Scoring using Vision-Language Models

TL;DR

VLM-Social-Nav introduces a vision-language model-based approach for socially aware robot navigation, improving success and collision rates while ensuring human-friendly behavior in real-world environments.

Contribution

The paper presents a novel VLM-based scoring method for socially compliant robot navigation, reducing training data reliance and improving adaptability.

Findings

27.38% improvement in success rate

19.05% reduction in collision rate

Most socially compliant behavior in user study

Abstract

We propose VLM-Social-Nav, a novel Vision-Language Model (VLM) based navigation approach to compute a robot's motion in human-centered environments. Our goal is to make real-time decisions on robot actions that are socially compliant with human expectations. We utilize a perception model to detect important social entities and prompt a VLM to generate guidance for socially compliant robot behavior. VLM-Social-Nav uses a VLM-based scoring module that computes a cost term that ensures socially appropriate and effective robot actions generated by the underlying planner. Our overall approach reduces reliance on large training datasets and enhances adaptability in decision-making. In practice, it results in improved socially compliant navigation in human-shared environments. We demonstrate and evaluate our system in four different real-world social navigation scenarios with a Turtlebot robot. We observe at least 27.38% improvement in the average success rate and 19.05% improvement in the average collision rate in the four social navigation scenarios. Our user study score shows that VLM-Social-Nav generates the most socially compliant navigation behavior.