A Tactical Traffic Management Solution for Smart Cities Using Reinforcement Learning

Arkaprabha Rakshit; Pritam Karmakar; Sushruta Mishra; Tiansheng Yang; Ruikai Sun; Rajkumar Singh Rathore

doi:10.1007/978-981-96-7523-4_22

A Tactical Traffic Management Solution for Smart Cities Using Reinforcement Learning

Arkaprabha Rakshit
, Pritam Karmakar
, Sushruta Mishra^*
, Tiansheng Yang^*
, Ruikai Sun
, Rajkumar Singh Rathore

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

As urbanization accelerates, traffic congestion presents a significant challenge for smart cities, impacting mobility and air quality. The paper is all about traffic management solution using reinforcement learning (RL) for real-time traffic control. Our system is set to change the signal timings based on traffic conditions, pedestrian movements, and environmental factors learning it lively and accurately. Deploying a multi-layered architecture, where the medium manages their role unitedly to enhance traffic flow. Feedback mechanisms are there to process the model for effective intermediation. Simulations project that the approach is noticeable in reducing travel times and crowding. This research helps in the advancement of smarter, more flexible urban transportation systems, assisting ability to move and making the urban life easier.

Original language	English
Title of host publication	Innovative Computing and Communications - Proceedings of ICICC 2025
Editors	Aboul Ella Hassanien, Sameer Anand, Ajay Jaiswal, Prabhat Kumar
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	309-318
Number of pages	10
ISBN (Electronic)	9789819675234
ISBN (Print)	9789819675227
DOIs	https://doi.org/10.1007/978-981-96-7523-4_22
Publication status	Published - 1 Oct 2025
Event	8th International Conference on Innovative Computing and Communication, ICICC 2025 - New Delhi, India Duration: 14 Feb 2025 → 15 Feb 2025

Publication series

Name	Lecture Notes in Networks and Systems
Volume	1434 LNNS
ISSN (Print)	2367-3370
ISSN (Electronic)	2367-3389

Conference

Conference	8th International Conference on Innovative Computing and Communication, ICICC 2025
Country/Territory	India
City	New Delhi
Period	14/02/25 → 15/02/25

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 9 Industry, Innovation, and Infrastructure
SDG 11 Sustainable Cities and Communities

Keywords

Multi layered architecture
Real-time traffic control
Reinforcement learning
Traffic management
Urban transportation systems

Access to Document

10.1007/978-981-96-7523-4_22

Cite this

Rakshit, A., Karmakar, P., Mishra, S., Yang, T., Sun, R., & Rathore, R. S. (2025). A Tactical Traffic Management Solution for Smart Cities Using Reinforcement Learning. In A. E. Hassanien, S. Anand, A. Jaiswal, & P. Kumar (Eds.), Innovative Computing and Communications - Proceedings of ICICC 2025 (pp. 309-318). (Lecture Notes in Networks and Systems; Vol. 1434 LNNS). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-96-7523-4_22

Rakshit, Arkaprabha ; Karmakar, Pritam ; Mishra, Sushruta et al. / A Tactical Traffic Management Solution for Smart Cities Using Reinforcement Learning. Innovative Computing and Communications - Proceedings of ICICC 2025. editor / Aboul Ella Hassanien ; Sameer Anand ; Ajay Jaiswal ; Prabhat Kumar. Springer Science and Business Media Deutschland GmbH, 2025. pp. 309-318 (Lecture Notes in Networks and Systems).

@inproceedings{df2a2281bac34fe6bd687c4cac95b69c,

title = "A Tactical Traffic Management Solution for Smart Cities Using Reinforcement Learning",

abstract = "As urbanization accelerates, traffic congestion presents a significant challenge for smart cities, impacting mobility and air quality. The paper is all about traffic management solution using reinforcement learning (RL) for real-time traffic control. Our system is set to change the signal timings based on traffic conditions, pedestrian movements, and environmental factors learning it lively and accurately. Deploying a multi-layered architecture, where the medium manages their role unitedly to enhance traffic flow. Feedback mechanisms are there to process the model for effective intermediation. Simulations project that the approach is noticeable in reducing travel times and crowding. This research helps in the advancement of smarter, more flexible urban transportation systems, assisting ability to move and making the urban life easier.",

keywords = "Multi layered architecture, Real-time traffic control, Reinforcement learning, Traffic management, Urban transportation systems",

author = "Arkaprabha Rakshit and Pritam Karmakar and Sushruta Mishra and Tiansheng Yang and Ruikai Sun and Rathore, \{Rajkumar Singh\}",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.; 8th International Conference on Innovative Computing and Communication, ICICC 2025 ; Conference date: 14-02-2025 Through 15-02-2025",

year = "2025",

month = oct,

day = "1",

doi = "10.1007/978-981-96-7523-4\_22",

language = "English",

isbn = "9789819675227",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "309--318",

editor = "Hassanien, \{Aboul Ella\} and Sameer Anand and Ajay Jaiswal and Prabhat Kumar",

booktitle = "Innovative Computing and Communications - Proceedings of ICICC 2025",

}

Rakshit, A, Karmakar, P, Mishra, S, Yang, T, Sun, R & Rathore, RS 2025, A Tactical Traffic Management Solution for Smart Cities Using Reinforcement Learning. in AE Hassanien, S Anand, A Jaiswal & P Kumar (eds), Innovative Computing and Communications - Proceedings of ICICC 2025. Lecture Notes in Networks and Systems, vol. 1434 LNNS, Springer Science and Business Media Deutschland GmbH, pp. 309-318, 8th International Conference on Innovative Computing and Communication, ICICC 2025, New Delhi, India, 14/02/25. https://doi.org/10.1007/978-981-96-7523-4_22

A Tactical Traffic Management Solution for Smart Cities Using Reinforcement Learning. / Rakshit, Arkaprabha; Karmakar, Pritam; Mishra, Sushruta et al.
Innovative Computing and Communications - Proceedings of ICICC 2025. ed. / Aboul Ella Hassanien; Sameer Anand; Ajay Jaiswal; Prabhat Kumar. Springer Science and Business Media Deutschland GmbH, 2025. p. 309-318 (Lecture Notes in Networks and Systems; Vol. 1434 LNNS).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Tactical Traffic Management Solution for Smart Cities Using Reinforcement Learning

AU - Rakshit, Arkaprabha

AU - Karmakar, Pritam

AU - Mishra, Sushruta

AU - Yang, Tiansheng

AU - Sun, Ruikai

AU - Rathore, Rajkumar Singh

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

PY - 2025/10/1

Y1 - 2025/10/1

N2 - As urbanization accelerates, traffic congestion presents a significant challenge for smart cities, impacting mobility and air quality. The paper is all about traffic management solution using reinforcement learning (RL) for real-time traffic control. Our system is set to change the signal timings based on traffic conditions, pedestrian movements, and environmental factors learning it lively and accurately. Deploying a multi-layered architecture, where the medium manages their role unitedly to enhance traffic flow. Feedback mechanisms are there to process the model for effective intermediation. Simulations project that the approach is noticeable in reducing travel times and crowding. This research helps in the advancement of smarter, more flexible urban transportation systems, assisting ability to move and making the urban life easier.

AB - As urbanization accelerates, traffic congestion presents a significant challenge for smart cities, impacting mobility and air quality. The paper is all about traffic management solution using reinforcement learning (RL) for real-time traffic control. Our system is set to change the signal timings based on traffic conditions, pedestrian movements, and environmental factors learning it lively and accurately. Deploying a multi-layered architecture, where the medium manages their role unitedly to enhance traffic flow. Feedback mechanisms are there to process the model for effective intermediation. Simulations project that the approach is noticeable in reducing travel times and crowding. This research helps in the advancement of smarter, more flexible urban transportation systems, assisting ability to move and making the urban life easier.

KW - Multi layered architecture

KW - Real-time traffic control

KW - Reinforcement learning

KW - Traffic management

KW - Urban transportation systems

UR - https://www.scopus.com/pages/publications/105020169679

U2 - 10.1007/978-981-96-7523-4_22

DO - 10.1007/978-981-96-7523-4_22

M3 - Conference contribution

AN - SCOPUS:105020169679

SN - 9789819675227

T3 - Lecture Notes in Networks and Systems

SP - 309

EP - 318

BT - Innovative Computing and Communications - Proceedings of ICICC 2025

A2 - Hassanien, Aboul Ella

A2 - Anand, Sameer

A2 - Jaiswal, Ajay

A2 - Kumar, Prabhat

PB - Springer Science and Business Media Deutschland GmbH

T2 - 8th International Conference on Innovative Computing and Communication, ICICC 2025

Y2 - 14 February 2025 through 15 February 2025

ER -

Rakshit A, Karmakar P, Mishra S, Yang T, Sun R, Rathore RS. A Tactical Traffic Management Solution for Smart Cities Using Reinforcement Learning. In Hassanien AE, Anand S, Jaiswal A, Kumar P, editors, Innovative Computing and Communications - Proceedings of ICICC 2025. Springer Science and Business Media Deutschland GmbH. 2025. p. 309-318. (Lecture Notes in Networks and Systems). doi: 10.1007/978-981-96-7523-4_22