Communicating Intent of Automated Vehicles to Pedestrians
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This study addresses the challenge of maintaining safe and clear interactions between pedestrians and automated vehicles (AVs). Currently, pedestrians rely on non-verbal cues from human drivers, such as eye contact and gestures, to negotiate right-of-way and assess intent. With the transfer of control to automation, these cues disappear, potentially leading to ambiguity and reduced perceived safety. The authors investigate whether an external vehicle interface that explicitly communicates the AV’s mode and intent can mitigate this issue and improve pedestrian experience. To test this, the researchers developed the Automated Vehicle Interaction Principle (AVIP), a visual interface consisting of a 1-meter RGB LED strip mounted on the windshield. The interface displays white/yellow light patterns to signal four states: automated mode activation, intent to yield, waiting, and intent to resume driving. The study employed a Wizard of Oz methodology to simulate fully automated driving in a Volvo V40, where a human operator concealed behind a dummy steering wheel controlled the vehicle and interface. Two experiments were conducted in real-world settings. Experiment I involved nine pedestrians at a zebra crossing to assess interface usability and initial emotional responses. Experiment II involved 24 pedestrians in a parking lot with ambiguous yielding rules, allowing for a more detailed assessment of perceived safety. In Experiment II, participants encountered the AV with the AVIP interface, the AV without the interface, and a conventional vehicle for comparison. The results indicated that the AVIP interface was easy for pedestrians to interpret after brief training. Crucially, pedestrians reported feeling significantly less safe when encountering the AV without the interface compared to both the conventional vehicle and the AV with the interface. The interface effectively replaced the missing non-verbal cues, contributing to a calmer interaction and improved perceived safety. The study found that explicitly communicating the vehicle’s future state and intent helped pedestrians align their expectations and reduced the stress associated with the lack of driver engagement. The significance of these findings lies in the potential for external intent communication to facilitate the public acceptance of automated vehicles. By addressing the communication gap created by the absence of human drivers, interfaces like AVIP can enhance pedestrian safety and comfort. The authors conclude that while the interface shows promise, further research with larger samples and more dynamic traffic conditions is necessary to refine the design and validate its effectiveness in broader contexts.
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | DOAJ | — | — | 1 | 2026-06-25 |
| archive | success | unpaywall | — | — | 1 | 2026-06-26 |
| extract | success | cached | — | — | 2 | 2026-06-26 |
| clean | success | clean | — | — | 1 | 2026-06-25 |
| chunk | success | chunk | — | — | 1 | 2026-06-25 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-25 |
| promote | success | — | — | — | 1 | 2026-06-25 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-26 |
| tag | success | vector_similarity | — | — | 6 | 2026-06-25 |
| verify | partial | — | — | — | 1 | 2026-06-26 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified_with_issues.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.