Close

Presentation

Interactions Between Workers and Automated Guided Vehicles: Impact of eHMI Design
DescriptionAs manufacturing facilities increasingly integrate Autonomous Guided Vehicles (AGVs) to improve workflow efficiency, enhancing human-AGV interaction remains critical for workplace safety. While prior research has focused on vehicle and pedestrian motion prediction models, effective interaction requires two-way communication, where the AGVs clearly convey their intentions to the workers to enhance AGV predictability and workplace safety. This study investigates the impact of an external Human-Machine Interface (eHMI) integrated with a predictive model on AGV-worker interaction. We designed LED light strip patterns to convey AGV intentions and selected optimal designs through an online survey. After that, we deployed different types of AGVs in a virtual reality (VR) manufacturing environment. Three AGV types were shown in the VR: Control, Prediction, and eHMI+Prediction. Participants completed delivery tasks while interacting with AGVs, followed by subjective assessments of trust, perceived safety, perceived performance, and understandability. A one-way repeated measures ANOVA revealed a significant improvement in perceived safety under the eHMI+Prediction condition compared to the Control condition. These preliminary results suggest that explicit communication via eHMI enhances perceived safety in AGV interactions.