From Obstacles to Etiquette: Robot Social Navigation with VLM-Informed Path Selection

TL;DR

This paper introduces a social robot navigation system that combines geometric path planning with vision-language model-based social reasoning, enabling real-time, socially-aware navigation in human environments.

Contribution

It presents a novel framework integrating VLM-based social reasoning with geometric planning for improved socially compliant robot navigation.

Findings

Achieves lowest personal space violation duration

Minimizes pedestrian-facing time

Prevents social zone intrusions

Abstract

Navigating socially in human environments requires more than satisfying geometric constraints, as collision-free paths may still interfere with ongoing activities or conflict with social norms. Addressing this challenge calls for analyzing interactions between agents and incorporating common-sense reasoning into planning. This paper presents a social robot navigation framework that integrates geometric planning with contextual social reasoning. The system first extracts obstacles and human dynamics to generate geometrically feasible candidate paths, then leverages a fine-tuned vision-language model (VLM) to evaluate these paths, informed by contextually grounded social expectations, selecting a socially optimized path for the controller. This task-specific VLM distills social reasoning from large foundation models into a smaller and efficient model, allowing the framework to perform real-time adaptation in diverse human-robot interaction contexts. Experiments in four social navigation contexts demonstrate that our method achieves the best overall performance with the lowest personal space violation duration, the minimal pedestrian-facing time, and no social zone intrusions. Project page: https://path-etiquette.github.io