Using Reinforcement Learning to Combine Green Light Optimised Speed Advisory or Equivilent Systems and Adaptive Traffic Lights

With the number of road users increasing and road planning and building being expensive, time consuming and
environmentally damaging, many institutions are looking towards increasingly smarter infrastructure like new adaptive
traffic control systems and green light optimisation speed advisory systems. However, using current adaptive traffic
control systems green light optimisation speed advisory systems leads to inefficiency as accurate future signal plans are
not always available leading to inaccurate speed advisories. The aim of this thesis will be to employ techniques from
the eld of machine learning to train an AI to control future signal plans as well as decide on the details to send to
drivers. This thesis details the building of test bed that has been built in Python and used to demonstrate the
advantages of each system as well as the inefficiencies of using both.