Intersection Safety Assist Draft Test Procedure Performability Validation

Davis, Ian J.; Forkenbrock, Garrick J. · 2021 · ROSA P / United States. Department of Transportation. National Highway Traffic Safety Administration

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 evaluates the performability of the National Highway Traffic Safety Administration’s (NHTSA) preliminary draft test procedure for Intersection Safety Assist (ISA) systems. The study aimed to determine if the protocol could facilitate objective, repeatable test track evaluations and to identify necessary refinements to improve test validity. The research was motivated by the need to standardize the assessment of ISA technologies, which are designed to help drivers avoid or mitigate intersection collisions by automatically applying brakes. The experimental design involved testing a 2017 Mercedes-Benz E300 4matic as the Subject Vehicle (SV) against a Principal Other Vehicle (POV) represented by a low-profile robotic vehicle, sometimes equipped with a guided soft target. Tests were conducted at a simulated four-way intersection using three scenarios: POV straight across SV path, POV left turn across SV path, and SV left turn across POV path. Each scenario included sub-scenarios with varying speed combinations and two choreographies: "crash-imminent," where a collision occurs without intervention, and "near-miss," where vehicles narrowly avoid contact. The SV was tested at three automation levels (manual, adaptive cruise control, and lane centering with ACC). Robotic controllers for steering, braking, and throttle were installed to ensure precise vehicle control and repeatability. Results indicated that while the preliminary test protocols were generally performable, they failed to satisfy certain validity criteria regarding vehicle speed and path tolerances. Consequently, revisions were made to the test procedure, including updates to robotic controller software and parameter optimization, which were incorporated into NHTSA’s September 2019 ISA draft test procedure. Regarding system performance, the SV’s ISA intervened in 11 of 12 trials where the POV accelerated from rest into the SV’s path (Scenario 1-B). However, none of these interventions prevented impact; they only reduced the SV’s impact speed by 1.2 to 18.0 mph. No ISA interventions occurred during near-miss trials or in scenarios involving left-turn maneuvers, consistent with the vehicle’s system design limitations. The study concludes that the refined test procedure, along with improved equipment usage, largely reconciles the ability to produce valid trials for each test condition. The findings provide a validated framework for objectively evaluating ISA technology performance, ensuring that future assessments are repeatable and technically sound. This work supports the broader goal of advancing motor vehicle safety research by establishing robust methods for testing advanced driver assistance systems.

Key finding

The ISA system reduced impact speed in straight-crossing trials but did not prevent collisions, and no interventions occurred during near-miss scenarios.

Methodology

simulator

Sample size: 1

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).

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.

• naturalistic crash near crash

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).

• Applied Guidance: standards test procedures
• Empirical Findings: crash risk outcomes