A Lane Change Assistance System Based on Prediction of Driver Intention
DOI: 10.48550/arxiv.2409.10551
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 limitation of existing lane change assistance systems (LCAS), which typically warn drivers of surrounding traffic without accounting for the driver’s intended maneuvers. The authors argue that warnings based solely on vehicle presence, ignoring driver intention, may lead to habitual ignoring of alerts. The study aims to integrate predicted driver intention (lane keeping, lane change left, or lane change right) into the warning logic to provide context-aware alerts that reduce collision risk and improve driver compliance. The researchers developed an individualized lane change intention recognition model using a Fuzzy-Random Forest (Fuzzy-RF) classifier. This model utilized 24 input variables, including ego-vehicle states (speed, steering angle, indicator status) and surrounding vehicle data (distance, time-to-collision [TTC] in six directions). The system was tested in a driving simulator study involving 44 participants. Twenty-two participants formed an experimental group that received intention-based audiovisual warnings via a head-up display, while the other 22 formed a control group receiving no such warnings. The experimental group underwent an initial training phase to generate personalized intention models. Warning thresholds were determined using TTC values adjusted for the specific maneuver (e.g., 5.5 s for adjacent vehicles during a lane change) and validated by experienced drivers. Results indicated that the intention-based assistance system significantly reduced near misses (TTC < 1 s) for the experimental group during lane changes to the left and right, compared to the control group. Specifically, performance improved regarding front vehicles during left lane changes and front-right/back-right vehicles during right lane changes. However, no significant improvement was observed for lane-keeping maneuvers. Participant feedback from mid-experiment questionnaires showed that at least 75% rated the system as helpful, timely, and beneficial for situational awareness. Nevertheless, some participants ignored warnings, citing a need for the system to anticipate the behaviors of surrounding vehicles rather than just reacting to their current positions. The study concludes that integrating driver intention recognition into LCAS enhances safety by reducing collision risks during active lane changes and increasing driver trust through context-relevant warnings. The findings suggest that future systems should incorporate predictive models for surrounding vehicle behaviors to further improve warning acceptance and effectiveness. The work highlights the importance of individualized intention recognition and tailored warning thresholds in developing robust assisted driving technologies.
Key finding
Intention-based lane change assistance warnings significantly reduced near misses during left and right lane change maneuvers but did not improve safety during lane keeping.
Methodology
simulator
Sample size: 44
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 | — | — | 1 | 2026-06-04 |
| extract | success | cached | — | — | 3 | 2026-06-15 |
| 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 | 2026-06-15 |
| tag | success | vector_similarity | — | — | 15 | 2026-06-11 |
| verify | success | — | — | — | 1 | 2026-06-04 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-15; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
- lane changing
- signaling behavior
- anticipation
- situational awareness
- automation surprise
- in vehicle coaching
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: behavioral performance data
- Methodological Resource: tool software
- Theoretical Contribution: computational model