Decentralized Deep Reinforcement Learning based Real-World Applicable Traffic Signal Optimization

An AI traffic management system that analyzes real-time traffic using computer vision and machine learning to dynamically control signals, reducing congestion flow instead of relying on fixed timers.

dITC through RL Code Foundation

🚦 Next-generation AI Traffic Management System with real-time computer vision, reinforcement learning optimization, emergency vehicle detection, and immersive 3D visualization

A novel integration of Large Language Models, Graph Neural Networks, and Reinforcement Learning for intelligent network traffic prediction and adaptive routing optimization. Demonstrates 42.3% throughput improvement and effective multi-objective optimization.

SynapticGrid is an AI-driven system designed to make cities more efficient, sustainable, and livable by optimizing smart energy grids, waste management, and traffic flow through IoT sensors, real-time data processing, and reinforcement learning algorithms. The modular platform continuously learns and improves, helping urban environments

SUMO

Оптимизация дорожного трафика на графе городских улиц с использованием квантово‑вдохновлённых методов

An open-source Python implementation and evaluation of the Priority Bidding Mechanism (PBM) for adaptive traffic signal control. This is an active collaboration between the Illinois Mathematics and Science Academy and Southern Illinois University, Carbondale.

🧠 Deep RL framework for urban traffic signal optimization and spillback mitigation using SUMO

This project uses reinforcement learning to optimize traffic signals, reducing congestion and improving flow through dynamic adjustments and simulation analysis.

Production-style AI system integrating YOLOv8 vehicle detection, time-window aggregation, Random Forest congestion prediction, and FastAPI-based signal optimization API.

A centralized deep reinforcement learning framework for adaptive urban traffic signal control, leveraging simulation-based environments to minimize congestion and optimize traffic flow.

Traffic signal timing optimization using queueing theory (M/M/1, M/G/1) and metaheuristic algorithms (PSO, ACO). Discrete-event simulation of traffic networks with Python/SimPy. Master's dissertation project.

AI-powered traffic light optimization using a locally-run LLM — beats fixed-cycle baseline by 14%

Intelligent traffic flow optimization system using SUMO microscopic simulation. Intelligent traffic simulation system for urban intersections using SUMO & Python. Analyze vehicle flow patterns, optimize signal timing, and evaluate network performance with real-time metrics