[Paper Review] Coordination of Autonomous Vehicles: Taxonomy and Survey

Stefano Mariani, Giacomo Cabri+1 more|arXiv (Cornell University)|Jan 8, 2020

Transportation and Mobility Innovations71 references17 citations

TL;DR

This paper presents a comprehensive taxonomy and survey of coordination challenges for autonomous vehicles, classifying problems by resource/task orientation and cooperation/competition. It proposes a unifying framework for coordination mechanisms based on the degree of autonomy in decision-making, identifying key technical and regulatory challenges for safe, scalable deployment in mixed-traffic environments.

ABSTRACT

In the near future, our streets will be populated by myriads of autonomous self-driving vehicles to serve our diverse mobility needs. This will raise the need to coordinate their movements in order to properly handle both access to shared resources (e.g., intersections and parking slots) and the execution of mobility tasks (e.g., platooning and ramp merging). In this paper, we firstly introduce the general issues associated to coordination of autonomous vehicles, by identifying and framing the key classes of coordination problems. Following, we overview the different approaches that can be adopted to manage such coordination problems, by classifying them in terms of the degree of autonomy in decision making that is left to autonomous vehicles during coordination. Finally, we overview some further peculiar challenges that research will have to address before autonomously coordinated vehicles can safely hit our streets.

Motivation & Objective

• To address the growing need for coordination among autonomous vehicles to ensure safe, efficient traffic flow and enable new mobility services.
• To identify and classify key coordination problems in autonomous vehicle systems, such as intersection crossing, platooning, and parking.
• To analyze coordination approaches based on the degree of autonomy left to individual vehicles during decision-making processes.
• To highlight cross-cutting challenges, including fairness, mixed human-autonomous vehicle operation, and regulatory frameworks.
• To provide a unified, comprehensive survey that fills a gap in existing literature focused on narrow, application-specific coordination solutions.

Proposed method

• Proposes a two-dimensional taxonomy for coordination problems: resource-oriented vs. task-oriented, and competitive vs. cooperative.
• Classifies coordination mechanisms by the degree of autonomy in decision-making assigned to vehicles, ranging from fully centralized to fully decentralized.
• Reviews coordination protocols and strategies, including auction-based mechanisms, argumentation frameworks, and consensus algorithms.
• Analyzes technical and social challenges such as fairness in priority allocation, safety in mixed-traffic scenarios, and privacy concerns.
• Integrates insights from coordination theory, concurrency theory, and multi-agent systems to frame coordination problems.
• Discusses the need for human-in-the-loop coordination mechanisms, especially for mixed fleets of human-driven and autonomous vehicles.

Experimental results

Research questions

• RQ1 How can coordination problems in autonomous vehicle systems be systematically classified based on their structural and behavioral characteristics?
• RQ2 What are the key differences in coordination mechanisms based on the degree of autonomy in decision-making assigned to individual vehicles?
• RQ3 How can fairness and social acceptability be ensured in coordination mechanisms that prioritize certain vehicles over others?
• RQ4 What technical and regulatory challenges arise when integrating human-driven vehicles into autonomous vehicle coordination frameworks?
• RQ5 What are the open challenges in enabling safe, scalable, and efficient coordination in mixed-traffic environments with heterogeneous vehicle types?

Key findings

• The taxonomy of coordination problems—based on resource/task orientation and competition/cooperation—provides a unifying framework for analyzing diverse vehicle coordination scenarios.
• Coordination mechanisms vary significantly in their reliance on centralized control versus decentralized autonomy, with trade-offs in scalability, robustness, and responsiveness.
• Auction-based coordination mechanisms, while efficient, risk creating mobility inequality if not regulated, as wealthier vehicles could consistently gain priority.
• Argumentation-based coordination is particularly suitable for mixed-traffic environments due to its dialogic, human-readable nature, enabling human drivers to participate meaningfully.
• The integration of human-driven vehicles into coordinated systems requires reliable communication infrastructure, intuitive interfaces, and tolerance for human behavioral variability.
• Significant open challenges remain in ensuring safety, fairness, and regulatory compliance in real-world deployments, especially in mixed-traffic scenarios.