Intelligent Intersection Management Systems Considering Autonomous Vehicles: A Systematic Literature Review

Namazi, Elnaz; Li, Jingyue; Lu, Chaoru · 2019 · OpenAlex-citations

DOI: 10.1109/access.2019.2927412

archive: archived pipeline: cataloged verified

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

Summary

This systematic literature review addresses the critical need for intelligent intersection management systems (AIMS) in the context of rising autonomous vehicle (AV) adoption. Motivated by the significant economic and safety costs associated with traffic congestion and accidents at intersections, the study aims to synthesize existing methodologies for managing AV traffic. The authors specifically focus on four-way intersections, covering both signalized and unsignalized scenarios, and examine both pure AV traffic and mixed traffic environments involving human-driven vehicles. The review seeks to identify research gaps and evaluate how well current approaches meet goals such as efficiency, safety, ecology, and passenger comfort. The authors conducted a systematic literature review following the Kitchenham et al. protocol, searching digital libraries including Scopus, IEEE, and Web of Science for articles published between 2008 and May 2019. From an initial pool of 2,952 results, they identified 105 primary studies through a rigorous six-step filtering process. Using thematic analysis, the researchers categorized the extracted data into four main methodological classes: rule-based, optimization, hybrid, and machine learning methods. The analysis was structured around three research questions concerning the factors addressed in AIMS, the specific methodologies proposed for pure versus mixed traffic, and the remaining challenges and opportunities in the field. The findings reveal that the majority of studies focus on improving efficiency and safety. For pure AV traffic, optimization methods, such as dynamic programming and multi-objective optimization, frequently outperform traditional signal control systems by reducing delay, queue length, and evacuation time. For instance, some reservation-based and auction-based models reduced average travel time by over 70% compared to first-come-first-served policies. Safety-focused methodologies often employ decentralized control, model predictive control, or game theory to prevent collisions and resolve conflicts. In mixed traffic scenarios, the review highlights the complexity of coordinating AVs with human-driven vehicles, noting that many existing methods rely on simplified simulation environments. The study also identifies that while most methods improve performance metrics, challenges remain regarding computational overhead, communication failures, and scalability in dense traffic conditions. The significance of this work lies in its comprehensive categorization of AIMS methodologies and its identification of specific performance gaps. By comparing how well different approaches satisfy key goals, the review provides a clear roadmap for future research. It underscores the necessity of developing robust systems that can handle mixed traffic and unsignalized intersections, which are likely to dominate the next two decades. The authors conclude that while current methods show promise in simulation, further research is needed to address real-world complexities, including communication reliability and the integration of ecology and passenger comfort metrics into intersection management strategies.

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