Run-Off-Road Collision Avoidance Countermeasures Using IVHS Countermeasures: Task 3, Volume 1
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 report documents the findings of Task 3 within the National Highway Traffic Safety Administration’s (NHTSA) Run-Off-Road Collision Avoidance Using IVHS Countermeasures program. The research addresses the critical safety issue of single-vehicle roadway departure (SVRD) crashes, which accounted for approximately 20% of police-reported crashes and 41.5% of in-vehicle fatalities in the United States in 1992. Motivated by the high injury and fatality rates associated with these incidents, the study aims to evaluate existing Intelligent Vehicle Highway System (IVHS) technologies capable of preventing or mitigating crashes caused by driver inattention, incapacitation, excessive speed, or loss of directional control. The methodology involved testing hardware and software components against functional goals established in prior tasks. The research team, led by Carnegie Mellon University, categorized countermeasures into two primary types: lateral systems designed to detect lane departure due to driver error, and longitudinal systems designed to detect excessive speed relative to road geometry and conditions. Testing was conducted using a mobile testbed vehicle (Navlab 5), laboratory experiments, restricted track tests at the Vehicle Research and Test Center, and driving simulator experiments. The study evaluated sensing functions (such as vision systems and GPS), decision-making algorithms (including Time-to-Line-Crossing and Time-to-Trajectory-Divergence), and driver interface mechanisms. Notably, no complete commercial countermeasure systems were available for testing; thus, the team integrated commercially available components with custom-developed technologies to create functional prototypes. The results detailed the performance of various sensing and algorithmic technologies. For lateral countermeasures, the report assesses forward and downward-looking vision systems, analyzing their ability to detect lane markings and estimate vehicle position under varying visibility and road conditions. For longitudinal countermeasures, the study evaluates methods for determining upcoming road geometry using GPS, commercial map databases, and custom-built maps, as well as techniques for sensing degraded roadway conditions like friction coefficients. The findings provide quantitative data on the accuracy, repeatability, and limitations of these technologies, such as the variability in GPS position estimates and the performance of neural network-based lane tracking systems. Driver interface tests, conducted separately on a simulator, evaluated the effectiveness of audible and haptic alerts in preventing roadway departures. The significance of this work lies in its contribution to the development of preliminary performance specifications for run-off-road collision avoidance systems. The technical results from Task 3 serve as the foundation for Task 4, which involves developing computer models of countermeasure effectiveness. By identifying the capabilities and boundaries of existing sensing and processing technologies, the report informs the design of future integrated safety systems. The findings support the broader goal of the Intelligent Transportation Systems program to reduce the severity and frequency of single-vehicle crashes through advanced technological interventions.
Key finding
Existing vision-based lane detection and GPS/map-based positioning technologies demonstrated varying levels of accuracy and robustness across different road conditions and visibility levels, providing critical data for defining functional requirements for run-off-road collision avoidance systems.
Methodology
mixed_methods
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 | 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).
- Methodological Resource: validation psychometrics
- Theoretical Contribution: computational model