5 papers
SOPD-SocialNav: Selective On-Policy Distillation for Vision-Language Social Navigation
Xinyu Zhang, Zishuo Wang, Ling Xiao
Vision-language models have shown strong potential for social robot navigation by leveraging rich semantic understanding of complex environments and human behaviors. However, large…
MUSON: A Reasoning-oriented Multimodal Dataset for Socially Compliant Navigation in Urban Environments
Zhuonan Liu, Xinyu Zhang, Zishuo Wang +8
Socially compliant navigation requires structured reasoning about dynamic pedestrians and physical constraints to ensure safe and interpretable decisions. Vision-language models (V…
VL2Spike: Spike-driven Distillation from VLMs for Low-Power Visual Perception in Embodied AI
Zinan Liu, Eric Zheng, Soumyaratna Debnath +3
Spiking neural networks (SNNs) are brain-inspired, event-driven models that compute with sparse spikes, which enables highly efficient visual perception in resource-constrained emb…
MAction-SocialNav: Multi-Action Socially Compliant Navigation via Reasoning-enhanced Prompt Tuning
Zishuo Wang, Xinyu Zhang, Zhuonan Liu +4
Socially compliant navigation requires robots to move safely and appropriately in human-centered environments by respecting social norms. However, social norms are often ambiguous,…
SocialNav-MoE: A Mixture-of-Experts Vision Language Model for Socially Compliant Navigation with Reinforcement Fine-Tuning
Tomohito Kawabata, Xinyu Zhang, Ling Xiao
For robots navigating in human-populated environments, safety and social compliance are equally critical, yet prior work has mostly emphasized safety. Socially compliant navigation…