Improved Models for Automated Planning-based Urban Traffic Control

The increasing urbanisation and traffic congestion have driven interest in AI-based traffic signal optimisation, particularly through automated planning techniques that offer transparency and explainability. Existing automated planning models range from those that are highly flexible and assume minimal infrastructure constraints, to those that are fully deployable and accommodate the constraints of existing legacy systems. In this work, we introduce Trade, a novel knowledge model for planning-based traffic signal optimisation. It bridges the gap between highly flexible and fully deployable models by enforcing practical constraints, such as cycle length limitations and consistency between consecutive cycles, while maintaining the benefits of flexible approaches. Empirical evaluation using real-world data from West Yorkshire, UK, shows that the Trade model delivers comparable performance to fully flexible models while enhancing deployability, thus contributing to more practical and effective AI-driven traffic control solutions.