An ideal bus route would offer highly predictable journey times to travellers so that the same journey taken at the same time of day on different occasions would take the same amount of time. While there are many sources of variability in journey times such as traffic conditions, passenger boarding and offloading time, and the impact of traffic lights, as well as interference between buses themselves, e.g., queueing at bus stops, changing lanes, or crossing junctions. To address this issue, this project will explore how machine learning, especially reinforcement learning, might be used to improve bus travel-time reliability, possibly by improving journey time prediction or offering advice on driving behaviour to bus drivers via an advanced driver information system. The specific approach to be taken is not defined and hence the project will require both creativity and intuition.
School of Computer Science and Statistics