Collaborative Research Framework for Automated Driving System Developers and Infrastructure Owners and Operators

Eddy, Martha Morecock; Mandokhot, Mohit; Habtemichael, Filmon · 2021 · ROSA P / United States. Department of Transportation. Federal Highway Administration. Office of Operations

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 presents a Collaborative Research Framework developed by the Federal Highway Administration (FHWA) to facilitate cooperation between Automated Driving System (ADS) developers and Infrastructure Owners and Operators (IOOs). The research addresses the critical need for structured collaboration to ensure the safe and efficient integration of ADSs into the roadway network. The motivation stems from the observation that ADS components are often developed by industry with little consultation from roadway stakeholders, leading to fragmented testing and potential safety gaps. The framework aims to advance a "safe system approach" by leveraging the distinct knowledge of both sectors to accelerate development, reduce testing costs, and improve the identification of technical and organizational issues. The framework was developed through extensive stakeholder engagement, including document reviews, webinars, and interviews with automotive original equipment manufacturers, technology suppliers, and federal, state, and regional government entities. It structures collaboration across four primary testing phases: Pre-Test, Test Definition, Test Execution, and Post-Test. The methodology emphasizes establishing "Common Ground" through shared goals, standardized terminology (referencing standards like SAE J3016 and UL 4600), and uniform metrics. It also addresses test logistics, covering what, how, and where to test across simulation, closed-track, and public road environments. The framework provides specific tools, including checklists, data management plans, and real-world examples, such as a PennDOT project on work zone navigation and a smart intersection initiative in Marysville, Ohio. Key findings indicate that effective collaboration requires early engagement and clear definition of roles and responsibilities to mitigate implementation risks. The report highlights that while ADS developers often use agile problem-solving approaches and IOOs use linear waterfall methods, awareness of these differences can facilitate common ground. The framework identifies that collaboration enables better data sharing, more comprehensive use-case selection, and improved fidelity in driving environment simulations. It provides a taxonomy for ADS/world interaction and outlines data sources for vehicle, roadway, environment, and object elements to support consistent evaluation. The framework asserts that collaborative testing leads to shorter timelines for realizing a safely integrated fleet and benefits both developers and infrastructure operators. The significance of this work lies in providing a standardized, non-binding resource for conducting collaborative ADS research and development. By offering a structured approach to testing phases, the framework helps bridge the gap between private sector innovation and public infrastructure management. It supports the creation of a safer transportation network by ensuring that ADS capabilities are validated against real-world roadway conditions through joint efforts. The framework is applicable to all levels of driving automation and can extend to other transportation technologies, serving as a learning tool for developers, IOOs, first responders, and transportation professionals.

Key finding

The framework establishes that structured collaboration between ADS developers and infrastructure owners is essential for improving test outcomes, reducing implementation risks, and accelerating the safe deployment of automated driving systems.

Methodology

review

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: dataset resource, tool software