Mauro Vallati is currently Professor of AI at the University of Huddersfield, where he leads the AI4UTMC (AI for Urban Traffic Management and Control https://www.ai4utmc.info/ ) research team. He is an ACM Senior Member, and ACM Distinguished Speaker on artificial intelligence (AI) for the UK. He has extensive experience in real-world applications of AI methods and techniques, spanning from healthcare to train dispatching. Since 2016, he has led several research grants and contracts in the field of urban traffic control, leading to numerous high-impact academic publications, and patents filed in United Kingdom, China, and United States.
In 2021 he was awarded a prestigious UKRI Future Leaders Fellowship for investigating AI-based autonomic urban traffic monitoring and control, with the aim of designing intelligent systems that can autonomously recognise the insurgence of traffic congestion and implement traffic light strategies to mitigate its impact on the urban traffic network.

The Power of Good Old-Fashioned AI for Urban Traffic Control

Abstract

The current increase in urbanisation, coupled with the socio-economic motivation for increasing mobility, is pushing the transport infrastructure well beyond its capacity. Traditional urban traffic control techniques are struggling to cope with the dramatic rise of traffic, and have limited ability to react. In response, more intelligent control mechanisms are required to better monitor and exploit the available infrastructure. Despite the growing number of studies leveraging on machine learning techniques to perform traffic control tasks, the good old model-based AI is gaining traction, thanks to its ability to provide approaches that can smoothly deal with unusual and unexpected conditions.
In this talk we will focus on the recent application of AI planning to urban traffic control. First, we will look into how urban traffic control is currently performed and what are the main challenges faced. Then, we will present how AI planning techniques have been used to improve common practices, and to provide useful tools for traffic engineers, domain experts, and practitioners.