Quo-Vadis Multi-Agent Automotive Research? Insights from a Participatory Workshop and Questionnaire

2025-08-05

AI Summary

Research on multi-agent interactions among autonomous vehicles, human-driven vehicles, and vulnerable road users in mixed-traffic environments remains severely underdeveloped, with most existing studies adhering to a single-agent paradigm. Method: Through participatory workshops, structured surveys, and qualitative analysis, this study systematically identifies methodological bottlenecks hindering multi-agent research across real-world testing, driving simulation, and computational modeling. Contribution/Results: We uncover three critical barriers: (1) absence of cross-disciplinary collaboration mechanisms; (2) lack of scalable, high-fidelity simulation tools; and (3) shortage of ethically compliant, large-scale simulation environments. To address these, we propose an integrated framework comprising a cross-disciplinary research architecture, a modular simulation toolchain, and an ethics-embedded research paradigm—shifting human-centered transportation research from isolated agent optimization toward collaborative co-driving. This work establishes a methodological foundation and actionable pathway for developing safe, equitable, and interpretable mixed-traffic systems.

Technology Category

• Multiagent Systems: Teamwork
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Research challenges in human and human-AI computation
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

The transition to mixed-traffic environments that involve automated vehicles, manually operated vehicles, and vulnerable road users presents new challenges for human-centered automotive research. Despite this, most studies in the domain focus on single-agent interactions. This paper reports on a participatory workshop (N = 15) and a questionnaire (N = 19) conducted during the AutomotiveUI '24 conference to explore the state of multi-agent automotive research. The participants discussed methodological challenges and opportunities in real-world settings, simulations, and computational modeling. Key findings reveal that while the value of multi-agent approaches is widely recognized, practical and technical barriers hinder their implementation. The study highlights the need for interdisciplinary methods, better tools, and simulation environments that support scalable, realistic, and ethically informed multi-agent research.

Problem

• Challenges in mixed-traffic environments with automated and manual vehicles
• Lack of focus on multi-agent interactions in automotive research
• Need for better tools and methods for multi-agent studies

Innovation

• Participatory workshop for multi-agent research insights
• Questionnaire to assess practical technical barriers
• Interdisciplinary scalable simulation environments needed