A hybrid approach to urban traffic flow optimization: Integration of Karnaugh Maps and reinforcement learning

Abstract

This study presents a hybrid approach combining Karnaugh Maps (K-maps) and Reinforcement Learning (RL) to optimize traffic signal control in urban environments. K-maps are traditionally used for simplifying Boolean expressions in digital logic, and here they are leveraged to enhance decision-making efficiency in RL-based traffic systems. The proposed method aims to improve traffic flow, reduce congestion, and lower fuel consumption. Microsimulation experiments were conducted using software calibrated with historical traffic data from a mid-sized city. Sensor inputs-such as vehicle count, traffic density, and signal phase durations-were validated against real-world data provided by local traffic authorities. Results demonstrate that the hybrid K-map and RL system outperforms conventional methods in adaptability and performance. However, limitations remain due to the exclusion of unpredictable driver behavior and weather conditions, which may affect real-world applicability.

Keywords

• Traffic signal optimization
• Karnaugh maps
• Artificial Intelligence
• Machine Learning
• Reinforcement Learning
• Traffic flow optimization
• Urban transportation

Kentsel trafik akışı optimizasyonunda hibrit bir yaklaşım: Karnaugh Haritaları ve pekiştirmeli öğrenme entegrasyonu

Öz

Bu çalışma, kentsel trafik sinyal kontrolünü optimize etmek amacıyla Karnaugh Haritaları (K-haritaları) ile Pekiştirmeli Öğrenme (Reinforcement Learning - RL) yöntemini birleştiren hibrit bir yaklaşım sunmaktadır. Sayısal mantıkta Boolean ifadelerini sadeleştirmek için kullanılan K-haritaları, burada RL tabanlı trafik sistemlerinde karar verme verimliliğini artırmak amacıyla kullanılmaktadır. Önerilen yöntem, trafik akışını iyileştirmeyi, tıkanıklığı azaltmayı ve yakıt tüketimini düşürmeyi hedeflemektedir. Yapılan mikro-simülasyon deneyleri, orta büyüklükte bir kente ait tarihsel trafik verileriyle kalibre edilmiş bir yazılım üzerinde gerçekleştirilmiştir. Araç sayısı, trafik yoğunluğu ve sinyal süreleri gibi sensör verileri, yerel trafik otoritelerinden elde edilen saha verileriyle doğrulanmıştır. Sonuçlar, hibrit K-haritası ve RL sisteminin geleneksel yöntemlere kıyasla daha uyarlanabilir ve performanslı olduğunu göstermektedir. Bununla birlikte, simülasyonda sürücü davranışlarındaki öngörülemezlikler ve hava koşullarına bağlı değişkenler dikkate alınmamıştır; bu durum, gerçek saha uygulamaları açısından bir sınırlılık oluşturmaktadır.

Anahtar Kelimeler

• Trafik sinyali optimizasyonu
• Karnaugh haritaları
• Yapay Zekâ
• Makine Öğrenmesi
• Pekiştirmeli Öğrenme
• Trafik akışı optimizasyonu
• Kentsel ulaşım

Kaynakça

1. [1] “World Bank Open Data,” World Bank Open Data. [Online]. Available: https://data.worldbank.org. Accessed: Apr. 25, 2025.
2. [2] “S&P Global Mobility forecasts 89.6M auto sales worldwide in 2025,” News Release Archive. [Online]. Available: https://press.spglobal.com/2024-12-20-S-P-Global-Mobility-forecasts-89-6M-auto-sales-worldwide-in-2025. Accessed: Apr. 25, 2025.
3. [3] “Türkiye posts record 1.2 million auto sales in 2023.” [Online]. Available: https://www.aa.com.tr/en/turkiye/turkiye-posts-record-12-million-auto-sales-in-2023/3100674. Accessed: Apr. 25, 2025.
4. [4] P. Kumar, N. Pal, and H. Sharma, Optimization and techno-economic analysis of a solar photo-voltaic/biomass/diesel/battery hybrid off-grid power generation system for rural remote electrification in eastern India, Energy, vol. 247, p. 123560, 2022.
5. [5] “Environment-Friendly Biodiesel/Diesel Blends for Improving the Exhaust Emission and Engine Performance to Reduce the Pollutants Emitted from Transportation Fleets.” [Online]. Available: https://www.mdpi.com/1660-4601/17/11/3896. Accessed: Apr. 25, 2025.
6. [6] E. A. Mueller, Aspects of the history of traffic signals, IEEE Trans. Veh. Technol., vol. 19, no. 1, pp. 6–17, 1970.
7. [7] A. R. Kulkarni, Kumar Narendra, and K. Ramachandra Rao, 100 Years of the Ubiquitous Traffic Lights: An All-Round Review, IETE Tech. Rev., vol. 41, no. 2, pp. 212–225, 2024.
8. [8] G. Leduc, Road Traffic Data: Collection Methods and Applications.

9. [9] M. J. Chase and R. J. Hensen, Traffic Control Systems—Past, Present, and Future, J. Transp. Eng., vol. 116, no. 6, pp. 703–713, 1990.
10. [10] M. Cecchi, Integration of Computerized Systems for Centralized Traffic Control, Prevention Routiere Internationale, Tokyo, Japan, Jun. 1990. [Online]. Available: https://trid.trb.org/View/367335. Accessed: Apr. 25, 2025.
11. [11] T. Lomax et al., Refining the Real-Timed Urban Mobility Report, UTCM 11-06-73, Mar. 2012. [Online]. Available: https://rosap.ntl.bts.gov/view/dot/24337. Accessed: Jun. 18, 2025.
12. [12] M. Papageorgiou, E. Kosmatopoulos, and I. Papamichail, Effects of Variable Speed Limits on Motorway Traffic Flow, Transp. Res. Rec., vol. 2047, no. 1, pp. 37–48, 2008.
13. [13] E. Walraven, M. T. Spaan, and B. Bakker, Traffic flow optimization: A reinforcement learning approach, Eng. Appl. Artif. Intell., vol. 52, pp. 203–212, 2016.
14. [14] M. T. Riaz et al., The Intelligent Transportation Systems with Advanced Technology of Sensor and Network, in Proc. Int. Conf. Computing, Electronic and Electrical Engineering (ICE Cube), pp. 1–6, 2021.
15. [15] M. Makys and S. Kozak, Effective method for design of traffic lights control, IFAC Proc. Vol., vol. 44, no. 1, pp. 14934–14939, 2011.
16. [16] H. Ceylan, Ö. Başkan, H. Ceylan, and S. Haldenbilen, Mathematical solutions of vehicular delay components at signalized intersections based on approximate calculation method, Pamukkale Univ. J. Eng. Sci., vol. 13, no. 2, pp. 279–288, 2007.
17. [17] D. Helbing, Traffic and related self-driven many-particle systems, Rev. Mod. Phys., vol. 73, no. 4, pp. 1067–1141, 2001.
18. [18] K. C. Dey et al., Vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication in a heterogeneous wireless network – Performance evaluation, Transp. Res. Part C, vol. 68, pp. 168–184, 2016.
19. [19] C. F. Daganzo, The cell transmission model: A dynamic representation of highway traffic consistent with the hydrodynamic theory, Transp. Res. Part B, vol. 28, no. 4, pp. 269–287, 1994.
20. [20] M. Wang et al., Urban traffic signal control with reinforcement learning from demonstration data, in Proc. Int. Joint Conf. Neural Networks (IJCNN), IEEE, pp. 1–8, 2022. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/9892538/. Accessed: Jun. 18, 2025.
21. [21] C. Passmann, C. Brenzel, and R. Meschenmoser, Wireless vehicle to vehicle warning system, SAE Tech. Paper, 2000. [Online]. Available: https://www.sae.org/publications/technical-papers/content/2000-01-1307/. Accessed: Apr. 25, 2025.
22. [22] A. Fares and W. Gomaa, Freeway ramp-metering control based on reinforcement learning, in Proc. IEEE Int. Conf. Control & Automation (ICCA), pp. 1226–1231, 2014.
23. [23] K. Rezaee, B. Abdulhai, and H. Abdelgawad, Application of reinforcement learning with continuous state space to ramp metering in real-world conditions, in Proc. IEEE Int. Conf. Intelligent Transportation Systems, pp. 1590–1595, 2012.
24. [24] M. Davarynejad et al., Motorway ramp-metering control with queuing consideration using Q-learning, in Proc. IEEE Int. Conf. Intelligent Transportation Systems, pp. 1652–1658, 2011.
25. [25] J. C. Spall and D. C. Chin, Traffic-responsive signal timing for system-wide traffic control, Transp. Res. Part C, vol. 5, no. 3, pp. 153–163, 1997.
26. [26] M. A. Wiering, Multi-agent reinforcement learning for traffic light control, in Proc. Int. Conf. Machine Learning (ICML), pp. 1151–1158, 2000. [Online]. Available: https://www.researchgate.net/profile/Marco-Wiering/publication/221346141_Multi-Agent_Reinforcement_Learning_for_Traffic_Light_Control/links/00b7d518130154c9bc000000/Multi-Agent-Reinforcement-Learning-for-Traffic-Light-Control.pdf. Accessed: Apr. 25, 2025.
27. [27] J. Vrancken et al., A hierarchical network model for road traffic control, in Proc. Int. Conf. Networking, Sensing and Control, pp. 340–344, 2009.
28. [28] I. Kamkar, M.-R. Akbarzadeh-T, and M. Yaghoobi, Intelligent water drops: A new optimization algorithm for solving the Vehicle Routing Problem, in Proc. IEEE Int. Conf. Systems, Man and Cybernetics, pp. 4142–4146, 2010.
29. [29] B. Capali and H. Ceylan, A multi-objective meta-heuristic approach for the transit network design and frequency setting problem, Transp. Plan. Technol., vol. 43, no. 8, pp. 851–867, 2020.
30. [30] M. Karnaugh, The map method for synthesis of combinational logic circuits, Trans. Am. Inst. Electr. Eng., Part I: Commun. Electron., vol. 72, no. 5, pp. 593–599, 1953.