arXiv cs.RO·· 6 days agoAI score31
Persona-based MLLM evaluation: how robot type and time of day affect perceived safety on urban streets
Summary
The study used 18 images of Seoul streets (split across daytime/nighttime, road class, and three conditions: no robot, delivery robot, or humanoid robot), having two multimodal large language models, Qwen3.8-27B and Gemma4-26B, each conditioned on 500 synthetic personas, choose the safer image in each pair, and compared the results with 25 human respondents.
This page provides a summary and source link only. Read the full article at the source.
Source: arXiv cs.RO · arxiv.org
Human-robot interaction and collaborationSafety and reliabilityResearch papers#Research#Human-robot interaction and collaboration#Safety and reliability
Part of the event: Multimodal large language models evaluate robot sense of safety in cities