Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Urban traffic congestion seriously challenges
transportation efficiency, safety, and sustainability, usually leading to excessive delays, higher fuel usage, and environmental pollution. In this paper, we introduce a decentralized traffic signal control system using
Reinforcement Learning (RL), where every intersection
acts as an autonomous agent using tabular Q-learning
for decision-making. As opposed to traditional deep
learning or centralized methods, ours focuses on
simplicity, scalability, and practical applicability. For
improving training stability and coverage, we use a pseudo-random event-based simulation method with the SUMO traffic simulator to allow the agent to generalize over diverse traffic patterns. Our system has a minimum
green signal duration constraint to mimic real traffic policies and to provide smoother transition. In addition, we couple the model with Arduino hardware to test its viability in real-world settings. Testing on several traffic grid settings shows considerable minimization of vehicle waiting time and enhanced overall traffic flow, revealing
the viability of our method for real-world
implementations in intelligent transportation systems.
Keywords:
Reinforcement Learning, Traffic Signal Control, Smart Cities, SUMO Simulator, Q-learning, Decentralized Systems, Arduino Integration, Intelligent Transportation Systems, Event-Based Simulation, Real- Time Decision Making
Cite Article:
"Traffic Optimisation using Reinforcement Learning: A Decentralized and Hardware - Based Solution", International Journal for Research Trends and Innovation (www.ijrti.org), ISSN:2455-2631, Vol.10, Issue 5, page no.a655-a659, May-2025, Available :http://www.ijrti.org/papers/IJRTI2505077.pdf
Downloads:
000422
ISSN:
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator