Bystander Interactions With Failing Vehicle Autonomy
archive: archived pipeline: cataloged verified
Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)
Summary
This research report addresses the human factors challenge of how autonomous vehicles (AVs) should communicate failure states or operational intentions to bystanders, specifically pedestrians. The authors argue that unclear AV behavior risks incorrect pedestrian reactions, leading to collisions, and may negatively impact public trust and brand perception, thereby hindering AV adoption. While driver-to-driver communication methods like hazard lights are established, equivalent signals for AVs interacting with pedestrians remain undefined. The study aims to identify communication methods that are both safe and perceived as appropriate by the public. The research employed two primary methodologies: a field study and a display study. The field study involved interviewing 32 pedestrians in nine settings around Pittsburgh, PA, where autonomous Uber vehicles were being tested. Interviews assessed pedestrian understanding, trust, and perceptions of AV capabilities and brand influence. The display study tested specific communication interfaces using a parked conventional car equipped with programmable LED strips and a tablet. Three display states were evaluated: red LEDs with "Please Wait," green LEDs with "Safe to Cross," and a tracking mode where LEDs followed the pedestrian. Additionally, the study evaluated three hand gestures (Stop, Hail, Slow Down) for pedestrian-to-AV communication, interviewing ten participants on city streets. Findings from the field study revealed five core themes: pedestrians often lack awareness of AV capabilities, leading to mistrust and fabricated explanations for vehicle behavior; there is a prevalent belief that AV technology is immature; an "innocent until proven guilty" mentality exists regarding AV trust; AVs are frequently associated with detrimental AI; and brand reputation significantly influences perceived trustworthiness. The display study highlighted significant confusion regarding vehicle intent. For instance, red LEDs were misinterpreted as decoration or ambiguous commands, and only 75% of participants correctly interpreted the tracking LED segment. Conversely, the tested hand gestures were widely understood, though some participants expressed concern about learning new gesture languages. Participants preferred displays that conveyed AV intent rather than issuing commands. The study concludes that greater transparency and public outreach by the AV industry are necessary to reduce confusion and support pedestrian decision-making. The authors suggest that displays should focus on communicating vehicle intent rather than commanding pedestrian action. They also note that leveraging the perception that AVs are "still learning" may help calibrate pedestrian trust. These findings have been disseminated to industry stakeholders and policymakers to inform the development of safer, more acceptable human-AV interaction protocols.
Key finding
Pedestrians exhibited significant confusion regarding the intent of autonomous vehicle visual displays, while hand gestures for communication were widely understood but raised concerns about adoption barriers.
Methodology
mixed_methods
Sample size: 54
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. Discovered via bulk_ingest_rosap on 2026-05-23 (6 acquisition events logged).
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | rosap | — | — | 2 | 2026-05-23 |
| archive | success | — | — | — | 1 | 2026-05-23 |
| extract | success | cached | — | — | 2 | 2026-06-10 |
| clean | success | — | — | — | 1 | 2026-06-01 |
| chunk | success | — | — | — | 1 | 2026-06-01 |
| embed | success | — | — | — | 1 | 2026-06-02 |
| enrich | success | — | — | — | 1 | 2026-05-23 |
| promote | success | — | — | — | 1 | 2026-05-23 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 3 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 19 | 2026-06-11 |
| verify | partial | — | — | — | 2 | 2026-06-10 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified_with_issues.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
Information type
What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).
- Empirical Findings: self report data