Communicating intent on the road through human-inspired control schemes
DOI: 10.1109/iros.2016.7759471
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This paper addresses the challenge of enabling autonomous vehicles (AVs) to operate safely in mixed traffic environments by improving their ability to communicate intent to human drivers. The authors argue that while AVs have advanced in sensing and control, they often lack the nuanced social interaction skills required for cooperative maneuvers, such as lane changes. Since humans naturally convey intent through subtle motion cues—specifically edging toward a target lane before merging—the study aims to develop a human-inspired control scheme that mimics these behaviors to enhance predictability and social acceptance. The methodology involves modeling driving as a hybrid system with discrete modes of intent: lane keeping, preparing to change lanes, and lane changing. The authors utilized a dataset of over 200 lane changes per driver from ten subjects, where drivers labeled their intent in real-time. By analyzing the spatial distributions of vehicle positions relative to lead vehicles, the researchers constructed empirical "cost maps" to identify nominal trajectories for each mode. These trajectories were integrated into a Model Predictive Control framework, where the cost function penalizes deviation from the human-derived nominal path rather than the lane center. To validate the approach, the authors conducted a human-subject study using a motion platform simulator. Nine participants experienced three control schemes: a standard method (minimizing deviation from lane center), the proposed human-inspired method (following human-derived trajectories), and a human-controlled baseline (replayed human driving data). Participants acted as both passengers in the AV and as drivers in adjacent vehicles, pressing a button when they predicted the AV would change lanes. No turn signals were used to isolate motion cues. The results demonstrated that the human-inspired control scheme significantly improved predictability. Subjects predicted lane changes approximately 40% earlier with the human-inspired method compared to the standard method, achieving an average prediction time of over 1.4 seconds. This increase in prediction time provides a critical buffer for human reaction. While the human-controlled baseline offered the highest predictability, subjects often described it as erratic and least trusted. Conversely, the standard method was perceived as smoother but less predictable. The study confirms that humans communicate intent through motion and that AVs can effectively replicate this communication by adopting human-like trajectory planning, thereby improving safety and interaction in shared road spaces.
Key finding
Implementing a human-inspired control scheme that mimics natural lane positioning cues increased the time available for human observers to predict autonomous vehicle lane changes by 40% compared to standard control methods.
Methodology
simulator
Sample size: 9
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 author_sweep_intake on 2026-05-28.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | author_sweep | — | — | 2 | 2026-05-28 |
| archive | success | canonical_url | — | — | 7 | 2026-06-06 |
| extract | success | cached | — | — | 3 | 2026-06-10 |
| clean | success | clean | — | — | 1 | 2026-06-04 |
| chunk | success | chunk | — | — | 1 | 2026-06-04 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-04 |
| enrich | success | — | — | — | 1 | 2026-05-28 |
| promote | success | — | — | — | 1 | 2026-06-04 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 2 | 2026-06-10 |
| tag | success | vector_similarity | — | — | 15 | 2026-06-11 |
| verify | success | — | — | — | 2 | 2026-06-10 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified.
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).
- Theoretical Contribution: computational model