A Hybrid Automated Planning Approach for Urban Real-time Routing of Connected Vehicles

One of the pivotal challenges presented to urban road traffic controllers is the effective utilisation of transport infrastructure, as a result of growing urbanisation, the finite network capacity, and of the increasing number of road vehicles. The arrival of connected autonomous vehicles (CAVs) represents a unique opportunity for a fundamental change in urban mobility, and urban traffic control should take an active role in integrating CAVs into the mobility ecosystem in order to maximise benefits. A practical way to exploit CAVs for urban traffic control is to build an intelligent control mechanism that can distribute traffic in the controlled region. In this context, automated planning, a well-studied Artificial Intelligence topic, can provide techniques to dynamically generate plans to distribute traffic -thus maximising the network utilisation and reduce congestion. In this paper, we present an approach based on hybrid discrete continuous planning, and we demonstrate its impact using real-world historical data of a large UK town.