Real work from students tackling how artificial intelligence reshapes freight routing, fleet management, and supply chain decisions.
A student research project exploring how machine learning models can reduce fuel costs and delivery delays across regional freight networks.
A critical analysis and prototype project examining where current computer vision models struggle in dense urban transit environments — and what that means for safety design.
Each project is evaluated across six dimensions that reflect real competency in applying AI concepts to transport and logistics challenges.
The chart shows the average skill profile across submitted projects — a rough picture of where students are strongest and where the curriculum still has room to push harder.
Projects combine written analysis with interactive quizzes and a scored simulation. Students pick a real logistics problem and apply an AI method they studied during the module.
Feedback arrives within 48 hours and covers both the technical reasoning and how clearly the findings are communicated.
Topics range from predictive maintenance for fleet vehicles to demand forecasting for last-mile delivery networks. The goal is practical familiarity, not theoretical perfection.
"The route optimisation module was the first time I actually understood why a greedy algorithm fails on large datasets. Working through a real dispatch scenario made the gap obvious in a way that slides never did."
Odette Vanbelle — logistics coordinator, completed AI in Transport module
Students enrolled in any active module can submit work directly through the platform. Check the module page for submission windows and assessment criteria.
Get in touch