Open Access Open Access  Restricted Access Subscription Access

Smart Traffic Management System in Urban Congestion

Inchara D Bhairav, Kushal G V, Pradeep Madyala, Dr. Deepak NR

Abstract


Folks are moving into cities quicker than ever, so roads fill up fast with vehicles, slowing everything down in major spots. Most traffic lights stick to fixed schedules - meaning they won’t change even if lanes suddenly get jammed. Newer fixes rely on gadgets that talk to each other, spot patterns through trial-and-error systems, or sort out real-time info to keep cars rolling smoother, reduce holdups, also shrink dirty fumes. The paper checks how those upgrades function - the layout behind them, constant updates from road monitors, signals that react on the fly, yet handy route tips shaped by live conditions. They work great in cities, making trips faster while keeping things safer. Stuff like ChatGPT, self-learning tools, brainy machines, school help apps pops up here. Traffic lights that adjust themselves along with clever route planners are part of this mix. These smart setups can plug right into how we handle traffic today - cutting down drive times and lowering risks on city streets. Tags: ChatGPT; Teaching; Smart tech; Classwork helpers.


Full Text:

PDF

References


Wei along with N. Xu, H. Zhang but also G. Zheng, X. Zang then C. Chen, W. Zhang followed by Y. Zhu, K. Xu plus finally Z. Li – CoLight: training systems to cooperate across networks for better traffic light control. Found in CIKM 2019 conference papers.

Wei, C. Chen, G. Zheng, K. Wu, V. Gayah, K. Xu - Z. Li - PressLight: figuring out signal coordination using max pressure methods at KDD 2019.

Varaiya, P.(2013). Managing traffic lights in busy areas using max-pressure rules. Transport Res C, 36, 177–195.

López Alvarez, P. along with Behrisch, M., Bieker-Walz, L., Erdmann, J., Floëtterröd, Y.-P., Hilbrich, R., Lücken, L., Rummel, J., Wagner, P., plus Wießner, E. published in 2018 on smallscale traffic modeling via SUMO(linked toSUMO/ITSC). Mentioned often when simulating traffic scenarios.

Hunt, P.; Robertson, D. I.; Bretherton, R. D.; and Royle, M. C. (1982). The SCOOT On-line Traffic Signal Optimisation Technique (original description SCOOT/Conference papers).

Shanmugam, A. (2024). Integrated Traffic Management System: A review. ACM/ Communications (review paper covering vehicle detection, dynamic control, and ITS integration).

Yusuf, S. A., others (2024). Cars talking to everything when drivers aren't needed: what we know so far plus where it’s headed. Breakdown of today's tech behind vehicle chats - also how 5G helps them connect better.

Wang, Y., Xu, T., Niu, X., Tan, C., Chen, E., and H/Xiong. (2019). STMARL: A Spatio-Temporal Multi-Agent Reinforcement Learning Approach for Cooperative Traffic Light Control. arXiv/conference.

Wei, H., et al. 2019 - using multiple agents with deep reinforcement learning to manage big-city traffic lights; explores ways to scale up multi-agent systems for real-world use.

Guastella, D. A. along with others (2023) wrote a hands-on walkthrough about simulating road movement using SUMO - this paper on arXiv shows how to set up test environments while pulling in actual flow details from live sources.


Refbacks

  • There are currently no refbacks.