Vol. 2 No. 2 (2022): Journal of AI-Assisted Scientific Discovery
Articles

Computational Intelligence for Adaptive Traffic Signal Control in Autonomous Vehicle Environments

PDF
  • Dr. Haejin Kim
Dr. Haejin Kim
Professor of Computer Science, Ulsan National Institute of Science and Technology (UNIST), South Korea
Cover

Published 30-12-2022

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

How to Cite

[1]
Dr. Haejin Kim, “Computational Intelligence for Adaptive Traffic Signal Control in Autonomous Vehicle Environments”, Journal of AI-Assisted Scientific Discovery, vol. 2, no. 2, pp. 75–96, Dec. 2022, Accessed: Sep. 18, 2024. [Online]. Available: https://scienceacadpress.com/index.php/jaasd/article/view/73

Abstract

This paper introduces CI-adaptive models, which extend the capabilities of traffic controllers, by modeling interactions among a few major intersections and provide useful future knowledge by means of a pre-estimation study. The estimation model is employed to allow drivers and control centers to make plans regarding intersection crossing, encouraged by the support from a communication system, which is automatically acting in cooperation with an adaptive signal control system.

In this context, Computational Intelligent (CI) adaptive models appear as a potential solution to offer sustainable urban traffic management. The main idea is transitioning the focus from vehicles to intersections and from both individual and instantaneous to collective and time-agnostic control. This collective approach concerns the decisions of some major intersections, attributing to explicit collective behavior performed by drivers in the vicinity of these intersections.

Future developments of an autonomous vehicle will challenge current traffic control systems in a manner that is yet to be fully understood. For instance, autonomous vehicles, equipped with a coordination and communication system, could potentially reduce intersection delays by selecting speeds to enable uninterrupted crossing of intersections, or even altering speeds to catch traffic light greens.

PDF

Downloads

Download data is not yet available.

References

  1. P. Varaiya, "The Max-Pressure Controller for Arbitrary Networks of Signalized Intersections," in IFAC Proceedings Volumes, vol. 45, no. 26, pp. 77-82, 2012.
  2. T. Li, S. Liu, B. De Schutter, H. Hellendoorn, and H. Wang, "Robust Optimal Control-Based Adaptive Coordination of Traffic Signals in Urban Traffic Networks," in IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 1, pp. 380-392, Jan. 2021.
  3. X. Zhang, D. Zhao, and Y. Zhang, "Deeplight: Deep Reinforcement Learning for Signal Control," in Proceedings of the 2018 ACM on Multimedia Conference, pp. 2018-2026, 2018.
  4. W. Zhang, J. Tang, J. Zheng, H. Zhang, Z. Sun, and Y. Cai, "An Adaptive Traffic Signal Control in a Connected Vehicle Environment: A Distributed Reinforcement Learning Approach," in IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 1, pp. 467-481, Jan. 2021.
  5. Tatineni, Sumanth. "Cost Optimization Strategies for Navigating the Economics of AWS Cloud Services." International Journal of Advanced Research in Engineering and Technology (IJARET) 10.6 (2019): 827-842.
  6. Vemoori, Vamsi. "Comparative Assessment of Technological Advancements in Autonomous Vehicles, Electric Vehicles, and Hybrid Vehicles vis-à-vis Manual Vehicles: A Multi-Criteria Analysis Considering Environmental Sustainability, Economic Feasibility, and Regulatory Frameworks." Journal of Artificial Intelligence Research 1.1 (2021): 66-98.
  7. Mahammad Shaik, et al. “Envisioning Secure and Scalable Network Access Control: A Framework for Mitigating Device Heterogeneity and Network Complexity in Large-Scale Internet-of-Things (IoT) Deployments”. Distributed Learning and Broad Applications in Scientific Research, vol. 3, June 2017, pp. 1-24, https://dlabi.org/index.php/journal/article/view/1.
  8. Tatineni, Sumanth. "Deep Learning for Natural Language Processing in Low-Resource Languages." International Journal of Advanced Research in Engineering and Technology (IJARET) 11.5 (2020): 1301-1311.
  9. Y. Chen, J. Zhang, H. Liu, and X. Lian, "Adaptive Traffic Signal Control System Based on a Dynamic Queueing Model," in IEEE Transactions on Intelligent Transportation Systems, vol. 21, no. 6, pp. 2422-2434, June 2020.
  10. C. Li, X. Liang, Y. Liu, H. Yu, and G. Zheng, "Multi-Agent Deep Reinforcement Learning for Urban Traffic Light Control in Vehicular Networks," in IEEE Transactions on Vehicular Technology, vol. 68, no. 2, pp. 1856-1869, Feb. 2019.
  11. S. Mannion, J. Duggan, and E. Howley, "An Experimental Review of Reinforcement Learning Algorithms for Adaptive Traffic Signal Control," in Proceedings of the 2016 SAI Computing Conference (SAI), London, 2016, pp. 33-40.
  12. A. Belletti, M. Farina, F. Scibilia, and R. Scattolini, "A Decentralized Model Predictive Control Scheme for Urban Traffic Control," in IEEE Transactions on Control Systems Technology, vol. 26, no. 3, pp. 903-914, May 2018.
  13. H. L. Vu, J. Harwood, and B. Logan, "Agent-Based Adaptive Traffic Signal Control With Deep Reinforcement Learning," in IEEE Transactions on Intelligent Transportation Systems, vol. 21, no. 5, pp. 1787-1795, May 2020.
  14. Y. Wang, Y. Chen, J. Zhang, and C. Wu, "Adaptive Traffic Signal Control for Urban Intersections Based on Reinforcement Learning," in IEEE Access, vol. 7, pp. 99612-99624, 2019.
  15. A. E. Papageorgiou, A. E. Kouvelas, E. Kosmatopoulos, and I. Papamichail, "An Integrated Control Approach for Traffic Responsive Signal Control and Ramp Metering," in IEEE Transactions on Intelligent Transportation Systems, vol. 11, no. 1, pp. 173-183, March 2010.
  16. M. Liang, L. Cheng, Y. Zhang, J. Zhang, and X. Qu, "Adaptive Traffic Signal Control with Reinforcement Learning in a Connected Vehicle Environment," in IEEE Transactions on Intelligent Transportation Systems, vol. 20, no. 12, pp. 4756-4769, Dec. 2019.
  17. J. Wei, L. Chen, Y. Xie, and Z. Wang, "Deep Q-Learning Based Adaptive Traffic Signal Control for Multiple Intersections," in Proceedings of the 2019 IEEE Intelligent Vehicles Symposium (IV), Paris, France, 2019, pp. 1898-1903.
  18. X. Mao, J. Sun, X. Qu, and Q. Han, "Urban Traffic Signal Control Using Fuzzy Logic and Reinforcement Learning," in IEEE Transactions on Intelligent Transportation Systems, vol. 21, no. 1, pp. 1-9, Jan. 2020.
  19. Y. Jin, B. Liu, and Y. Zhang, "Adaptive Traffic Signal Control for Heterogeneous Connected Vehicles Using Deep Reinforcement Learning," in IEEE Transactions on Intelligent Transportation Systems, vol. 21, no. 5, pp. 2321-2331, May 2020.
  20. H. K. Yin, Y. Wang, and L. Zhu, "A Survey of Machine Learning Techniques Applied to Adaptive Traffic Signal Control Systems," in Proceedings of the 2020 IEEE International Conference on Artificial Intelligence and Knowledge Engineering (AIKE), Laguna Hills, CA, USA, 2020, pp. 197-204.
  21. J. Koonce and B. Coifman, "Machine Learning-Based Adaptive Traffic Signal Control for Congestion Management," in IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 4, pp. 2433-2443, April 2021.