Mobility is the lifeblood of human connectedness and economic progress, and roads are a critical component of the transportation system for both people and goods. Unfortunately, roads are potentially vulnerable to medium- to long-term disruptions (ie, lasting hours to days) due to extreme weather, infrastructure failures, accidents, maintenance, and unexpected demand all resulting in high cost to road users. Improving the resilience of road transportation to such events is therefore critically important. Such disruptions may happen at short notice, and require plans to be put in place quickly to allow traffic to progress.
As an exercise in assessing the emerging reasoning capability of recent Large Language Models supporting so-called Agentic AI, this project will explore how these models might be used to quickly develop detailed disruption evolution scenarios and draft response plans suitable for deployment by stakeholders including public authorities, road operators, public transportation and freight providers, and police and other emergency services.