Scalable Multi-Objective Optimization for Robust Traffic Signal Control in Uncertain Environments Based on Hierarchical Reinforcement Learning
IEEE Transactions on Intelligent Transportation Systems · 2026-07 · 27 (7) · 7984-7999
DOI: 10.1109/tits.2026.3670486 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2026-07. Verfasst von Weian Guo und 9 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: National Natural Science Foundation of China, 14th Five-Year Plan National Key Research and Development Program of China Ministry of Science and Technology of the People's Republic of China, Chinese Academy of Engineering Strategic Research and Consulting Projects.
Abstract (Originalsprache)
Effective urban traffic signal control in large-scale networks remains challenging due to complex interdependencies among intersections and unpredictable fluctuations in traffic conditions. To address these challenges, this paper proposes a novel Adaptive Hybrid Multi-Objective Optimization Algorithm with Reinforcement Learning (AHMOA-RL) for robust and scalable traffic signal management. The core innovation of AHMOA-RL lies in a hierarchical optimization framework that efficiently decomposes the problem into global region-level coordination and local intersection-level refinements, significantly reducing computational complexity while ensuring synchronized control across extensive urban networks. A Q-learning agent dynamically selects among multiple evolutionary operators—Genetic Algorithm, Differential Evolution, Particle Swarm Optimization, and Local Search—to strategically balance exploration and exploitation during optimization. Additionally, a memory-based evaluation mechanism leveraging historical data is integrated to smooth transient traffic anomalies and provide stable performance estimates. Extensive simulations on large-scale city networks inspired by Manhattan, Paris, São Paulo, and Istanbul demonstrate that AHMOA-RL consistently outperforms state-of-the-art methods, achieving substantial reductions in average vehicle delays, improved network stability, and enhanced robustness under diverse traffic conditions. The algorithm’s compact Pareto fronts and superior convergence characteristics validate its effectiveness for practical deployment in complex urban environments.
Förderung
- National Natural Science Foundation of China
- 14th Five-Year Plan National Key Research and Development Program of China Ministry of Science and Technology of the People's Republic of China
- Chinese Academy of Engineering Strategic Research and Consulting Projects
- Aeronautical Science Foundation of China
- Shanghai Municipal Science and Technology Major Project
- Natural Science Foundation of Shanghai
Zitieren
APA
Guo, W., Xiao, Y., Zhang, Z., Li, W., Zhang, L., Li, L., Li, D., Rohmann, C., Bachem, H. K., & Hinz, M. (2026). Scalable Multi-Objective Optimization for Robust Traffic Signal Control in Uncertain Environments Based on Hierarchical Reinforcement Learning. IEEE Transactions on Intelligent Transportation Systems, 27(7), 7984-7999. https://doi.org/10.1109/tits.2026.3670486
Vancouver
Guo W, Xiao Y, Zhang Z, Li W, Zhang L, Li L, et al. Scalable Multi-Objective Optimization for Robust Traffic Signal Control in Uncertain Environments Based on Hierarchical Reinforcement Learning. IEEE Transactions on Intelligent Transportation Systems. 2026;27(7):7984-7999. doi:10.1109/tits.2026.3670486
BibTeX
@article{Guo2026,
author = {Guo, Weian and Xiao, Yao and Zhang, Zhiou and Li, Wuzhao and Zhang, Lun and Li, Li and Li, Dongyang and Rohmann, Christoph and Bachem, Harald Konrad and Hinz, Marcin},
title = {Scalable Multi-Objective Optimization for Robust Traffic Signal Control in Uncertain Environments Based on Hierarchical Reinforcement Learning},
journal = {IEEE Transactions on Intelligent Transportation Systems},
year = {2026},
volume = {27},
number = {7},
pages = {7984--7999},
doi = {10.1109/tits.2026.3670486}
}
EUVIMED