Research Analyzer
← Back ICRA 2026

Evaluating Multimodal Communication Methods for Autonomous Buses in Pedestrian-Dense University Environments

Abdalla Ahmed Roshdi Mohamed, Ashita Ashok, Qazi Hamza Jan, Franziska Babel, Karsten Berns

PDF

AI summary

Key figure (auto-extracted from paper)
Visual communication cues significantly outperform auditory ones in pedestrian awareness, while trust and yielding behavior are driven by perceived safety and social status rather than prior AV exposure.
Autonomous Vehicles Pedestrian Interaction External Human-Machine Interfaces Multimodal Communication Human-Robot Interaction Field Deployment

Problem

Autonomous vehicles lack traditional human driving cues, creating a communication gap in unstructured, pedestrian-dense shared spaces where public acceptance and safety are critical.

Approach

The team deployed an autonomous shuttle bus on a university campus equipped with adaptive visual and auditory external interfaces, tracking pedestrian behavior via skeleton tracking and collecting post-interaction surveys from 58 participants.

Key results

  • Visual cues were consistently recognized more frequently than auditory ones
  • Trust in AV safety depended on perceived relative safety rather than prior exposure
  • Willingness to yield correlated positively with the AV's perceived social status
  • Pedestrians predominantly displayed neutral or positive facial expressions during interactions

Why it matters

Provides actionable design guidelines for external human-machine interfaces to enhance safety, trust, and intuitive pedestrian-vehicle interactions in shared urban environments.

Abstract

In urban pedestrian zones where autonomous vehicles (AVs) increasingly operate alongside humans, clear communication between AVs and pedestrians is essential for safety and trust. This study conducted an exploratory re- search on pedestrian reactions to an autonomous shuttle bus (AutoBus) operating on a university campus. Using a real- world deployment, the effectiveness of visual and auditory communication cues in a real-world setting was evaluated. The AutoBus continuously looped a 480-meter path on campus during lunchtime, and pedestrians who walked toward and crossed the bus were invited to complete an online survey following this interaction. Data was collected from 58 partici- pants at a technical university through behavioral observations and post-interaction surveys. The results reveal that visual cues were more consistently recognized than auditory ones, influencing pedestrian awareness and response. Trust in AV’s safety was shaped more by its perceived safety than by prior experiences with the AutoBus. Moreover, willingness to yield was positively associated with the perceived social status of the AV, but not whether it was perceived as an autonomous robot or as representing its passengers. These findings offer practical insights for improving AV communication design to support safer, more intuitive interactions in shared spaces.

Index terms

Field Robots Autonomous Agents Social HRI

Related papers