Social-LLaVA: Enhancing Robot Navigation through Human-Language Reasoning in Social Spaces
Published in IROS 2025, 2025
Recommended citation: Payandeh, A., Song, D., Nazeri, M., Liang, J., Mukherjee, P., Raj, A. H., Kong, Y., Manocha, D., & Xiao, X. (2025). "Social-LLaVA: Enhancing Robot Navigation through Human-Language Reasoning in Social Spaces." IROS 2025. https://arxiv.org/pdf/2501.09024
This paper presents Social-LLaVA, a novel approach for enhancing robot navigation through human-language reasoning in social spaces. The method leverages vision-language models to improve social awareness and navigation performance in crowded environments.