ORIGINAL RESEARCH article
Front. Robot. AI
Sec. Human-Robot Interaction
Volume 12 - 2025 | doi: 10.3389/frobt.2025.1669952
Real-Time Traffic Signal Optimization for Urban Mobility: A Reinforcement Learning-Enhanced Framework with Application to Kuwait City
Provisionally accepted
- 1Centre for Applied Mathematics and Bioinformatics (CAMB), Gulf University for Science and Technology, Hawally, Kuwait
- 2Gulf University for Science & Technology Computer Science Department, Hawally, Kuwait
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
This study develops an intelligent, adaptable traffic control strategy using advanced management algorithms to enhance urban mobility in smart cities. It thoroughly investigates and evaluates rule-based (Fixed-Time), optimization-based (Max-Pressure and Delay-Based), and machine-learning-driven (Reinforcement Learning) algorithms under various traffic conditions, enabling the system to automatically select the one that most effectively minimizes wait times and reduces traffic congestion. The method not only improves traffic flow but also has a positive impact on environmental health by significantly reducing fuel consumption and carbon dioxide emissions. To evaluate the system's accuracy, we manipulate microscopic traffic simulations and perform various statistical analyses. We also utilize a Reinforcement Learning (RL) variant to verify the method's effectiveness compared to other approaches. The desired algorithms are executed on high-performance Field Programmable Gate Array (FPGA) platforms, which are particularly suitable for embedded, energy-constrained smart city environments. This is because FPGAs have lower latency and power consumption compared to general-purpose GPUs, allowing them to meet real-time operational requirements. The proposed system achieves a speedup of over 7× compared to modern high-speed general-purpose processing units (GPPUs), demonstrating the efficiency of the custom FPGA-based 1 pipelined architecture in real-time traffic management applications. The study further examines how this proposed solution can be utilized to address Kuwait's significant traffic issues and improve air quality in the region.
Keywords: Smart Cities, Traffic signal control, Field Programmable Gate Array(FPGA), Max-Pressure Algorithm 'Delay-Based Optimization, intelligent transportation systems (ITS), Real-time traffic management
Received: 20 Jul 2025; Accepted: 29 Aug 2025.
Copyright: © 2025 Almomany, Eedi and Sutcu. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Abedalmuhdi Almomany, Centre for Applied Mathematics and Bioinformatics (CAMB), Gulf University for Science and Technology, Hawally, Kuwait
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.