Design of a Machine Learning Based Traffic Control System
MetadataShow full item record
This report investigates the problem of traffic jam at one of the junctions in Kampala Uganda which is Wandegeya junction. At Wandegeya junction, the existing traffic light control causes long delay, air pollution, energy waste, accident and many more complications. The Government of Uganda through Kampala Capital City Authority (KCCA) has tried to solve this problem using different technologies like radar but all those solutions did not help. In this project, we studied the traffic signal’s duration based on the data we collected manually by counting cars and data we got from KCCA. We developed a machine learning-based model to control the traffic light(agent). In the model, Q-learning algorithm was used which is a free reinforcement algorithm to learn the actions of the agent and powers neural network to predict better actions to take. The model was evaluated via a simulator that is Simulation of Urban Mobility (SUMO) in a vehicular network, and the simulation results show the efficiency of our model in controlling traffic lights.