Autonomous Driving as System of Systems: roadmap for accelerating development

Assaad, Mohamad Ali; Talj, Reine; Charara, Ali · 2019 · Crossref

DOI: 10.1109/sysose.2019.8753886

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This paper addresses the challenge of accelerating the transition from human-driven to fully autonomous land transportation by modeling the domain as a System of Systems (SoS). While significant investment exists in autonomous vehicle technology, the authors argue that the primary obstacle is not technical readiness but the complexity of predicting the system's impact on its environment and managing the transition phase where human and autonomous vehicles coexist. To mitigate wasted effort and social or economic disruptions, the paper proposes a structured roadmap based on SoS engineering principles, specifically treating land transportation as a collaborative SoS within a larger global context. The methodology involves modeling Earth as a "super SoS" comprising multiple global SoS, such as economic, energy, communication, and intelligent transportation systems (ITS). The authors analyze land transportation as a constituent system within ITS, identifying four key pillars: legislation organizations, infrastructure, research and development (R&D) organizations, and people. Drawing parallels with the evolution of the Internet from a directed to a collaborative SoS, the authors propose an internet-inspired reference model for autonomous driving. This model envisions streets decomposed into sections with backbones monitoring traffic and providing services, utilizing technical standards and protocols to ensure interoperability among heterogeneous systems. The core contribution is a five-step roadmap for activity planning. First, it calls for establishing a collective authority, similar to the Internet Engineering Task Force (IETF), to perform SoS-level coordination, propose standards, and assess challenges. Second, it requires proposing multiple reference models for the future state of autonomous driving to provide context for development. Third, it involves creating detailed introspective and extrospective models to understand internal architectures and external relationships with other global SoS. Fourth, these models are used to simulate strategies, identify emergent behaviors, and prepare for challenges such as the disposal of human-driven vehicles or impacts on power grids. Finally, the process mandates regular updates and refinements of these models as new information becomes available. The significance of this work lies in shifting the focus from isolated technological development to holistic system planning. By adopting a collaborative SoS approach, the authors argue that stakeholders can anticipate and resolve integration challenges before they arise, thereby accelerating the deployment of autonomous driving. The proposed framework emphasizes the necessity of coordination among independent actors to ensure that the transition leads to desired outcomes in safety, capacity, and efficiency, while minimizing negative social and economic impacts.

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.

Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; 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).

• Synthesis & Review: research agenda
• Theoretical Contribution: conceptual framework