Cooperative Driving Automation — Highway Driving Simulator Architecture: High-Level Architecture Design
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 high-level software architecture for integrating the Federal Highway Administration’s (FHWA) Cooperative Driving Automation (CDA) capabilities with its Highway Driving Simulator (HDS). The research is motivated by the need to understand how human drivers adjust to automated vehicles (AVs) and connected automated vehicles (CAVs). Existing HDS capabilities relied on scripted behaviors that were difficult to approximate accurately, particularly for proprietary original equipment manufacturer systems. By integrating the open-source CARMA℠ Ecosystem—a suite of CDA software developed by FHWA—into the HDS, the project aims to enable realistic human-in-the-loop and software-in-the-loop simulations. This integration supports human factors research critical to the safety, effectiveness, and acceptance of emerging automation technologies. The project team evaluated two integration approaches: modifying the existing HDS rendering software (ARCHER) to host CDA logic, or integrating HDS components into an existing 3D simulation platform. The report recommends the latter, termed the Unified Simulation Engineering Platform (USEP) approach. In this architecture, a 3D simulation platform, such as the open-source CARLA simulator, serves as the host for the world simulation and maintains a single master world model containing the ground truth dynamic-state data for all entities. The ARCHER software and CARMA CDA software operate as external modules connected to this platform. This design leverages industry-standard simulation tools rather than recreating them, allowing for a clear delineation of responsibilities between vehicle physics/behavior and the human sensory experience. The architecture supports various scenarios, including simulating ADS vehicles as background traffic, CDA-enabled vehicles interacting with human drivers, and CDA-enabled infrastructure. The proposed USEP architecture enables the HDS to incorporate prototype ADS and CDA algorithms directly into the simulation loop. By using a unified world model, the system ensures consistency across different subsystems, eliminating data discrepancies between the HDS cab vehicle dynamics and the surrounding traffic environment. The report identifies key design considerations, including the need for flexible application programming interfaces, realistic physics simulations, and robust time synchronization mechanisms. While CARLA is the primary candidate for the USEP due to its existing integration with the CARMA Ecosystem via the CDASim cosimulation tool, the report notes that other platforms like NVIDIA DRIVE Sim or rFpro may be considered if rendering or real-time computation requirements are not met. The significance of this work lies in its ability to expand the HDS’s research capabilities beyond scripted automation levels. The integrated CDA-HDS system facilitates more rapid development cycles and verification testing for CDA algorithms. Furthermore, adopting a widely used simulation engineering platform aligns with long-term goals to connect the HDS to FHWA’s Distributed Testing Framework. This architecture provides a scalable, modular foundation for future human factors studies, allowing specialized teams to focus on specific subsystems while ensuring that simulated cooperative driving behaviors accurately reflect the complexities of real-world V2X communications and automated decision-making.
Key finding
The recommended high-level architecture utilizes a Unified Simulation Engineering Platform to host the simulation world and ground truth data, enabling the integration of open-source Cooperative Driving Automation software with the Highway Driving Simulator for enhanced human factors research.
Methodology
theoretical
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 (7 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 | 4 | 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: tool software, validation psychometrics
- Theoretical Contribution: computational model