Advanced Test Tools for ADAS and ADS

Albrecht, Heath; Barickman, Frank S.; Schnelle, Scott C. · 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 details the advanced test tools and capabilities established at the National Highway Traffic Safety Administration’s (NHTSA) Vehicle Research and Test Center (VRTC) for evaluating the safety performance of Advanced Driver Assistance Systems (ADAS) and Automated Driving Systems (ADS). The research is motivated by the emergence of complex driving automation technologies, including Level 0 active safety systems, Level 1–2 automation, and higher-level ADS, which require precise, repeatable, and reproducible closed-course testing. The primary objective is to develop a scalable system capable of orchestrating multi-actor scenarios that replicate real-world conflict situations within the operational design domain of these systems, while maintaining high safety standards for test personnel. The methodology involves the integration of robotic control systems, surrogate actors, and data acquisition hardware to create coordinated test environments. Non-strikeable vehicles are controlled via robotic drop-in kits (AB Dynamics steering and pedal robots) or drive-by-wire interfaces, paired with Oxford Technical Solutions GPS/IMU units for high-accuracy positioning. For scenarios involving collision risk, VRTC employs strikeable surrogate actors, including the Guided Soft Target (GST)—a foam-based vehicle surrogate mounted on a low-profile robotic vehicle—and various pedestrian and bicyclist mannequins (4ActiveSystems poseable and articulated models, and static bicyclists). These surrogates are designed to mimic the visual, radar, and lidar signatures of real road users. The system utilizes software to enable closed-loop control between all actors, ensuring precise choreography relative to the subject vehicle under test. Data collection is managed through synchronized video, CAN bus, and Robot Operating System (ROS) acquisition systems. The report demonstrates the application of these tools through specific test scenarios, including Intersection Safety Assist, Traffic Jam Assist, and Oncoming Traffic Safety Assist. These examples illustrate how the system coordinates multiple actors, such as a subject vehicle, a principal other vehicle (often a strikeable surrogate), and significant other vehicles, to evaluate system responses to events like suddenly revealed stopped vehicles or lane changes. The hardware allows for the simulation of complex maneuvers involving pedestrians, cyclists, and multiple vehicles, with the ability to abort tests safely if necessary. The GST system, for instance, can sustain impacts at relative velocities up to 110 km/h and be reassembled quickly, facilitating efficient testing cycles. The significance of this work lies in providing a standardized, technology-neutral framework for assessing the safety of emerging automotive technologies. By enabling precise control over multi-actor scenarios, VRTC’s tools allow for the rigorous evaluation of ADAS and ADS performance in conditions that are difficult or dangerous to replicate with human drivers alone. This capability supports the development of robust test procedures and contributes to the broader goal of improving motor vehicle safety as automation technologies become more prevalent. The report serves as a technical reference for the specific hardware configurations and operational protocols required to conduct these advanced closed-course evaluations.

Key finding

The Vehicle Research and Test Center has developed an integrated advanced test system combining robotic vehicle control, strikeable surrogate targets, and synchronized data acquisition to enable precise, repeatable, and safe closed-course testing of multi-actor ADAS and ADS scenarios.

Methodology

other

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.

• driverless ads

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
• Methodological Resource: tool software, validation psychometrics