XClose

AI for People and Planet

Home
Menu

Transportation and mobility

tube
Find out more below about some of the key UCL research using AI to solve transportation and mobility issues.

AI is greatly enhancing our ability to predict and manage the implications of behaviour choice and equipment performance for things like route choice, travel disruption, road safety, decarbonisation and autonomous vehicles. In addition, insights from AI are relevant to uncovering and shaping new business models for mobility, such as mobility-as-a-service, and to helping governments predict and manage the regulatory environment for fast changing transport technology.

 

Forecasting Airport Transfer Passenger Flow Using Real-Time Data and Machine Learning (Bert De Reyck)

In collaboration with Heathrow airport, this project will develop a two-phased predictive system that produces forecasts of transfer passenger flows. In the first phase, the system predicts the distribution of transfer passengers’ connection times; in the second phase, the system samples from the distribution of individual connection times and produces distributional forecasts for the number of passengers arriving at the immigration and security areas.

This work is the first to apply machine learning for predicting real-time distributional forecasts of journeys in an airport, using passenger level data. Better forecasts of these journeys can help optimize passenger experience and improve airport resource deployment. The predictive system developed is based on a regression tree combined with copula-based simulations. The tree method is generalised to predict complete distributions, moving beyond point forecasts. This predictive system can produce accurate forecasts, frequently, and in real time. With these forecasts, an airport’s operating team can make data-driven decisions, identify late passengers and assist them to make their connections. The airport can also update its resourcing plans based on the prediction of passenger flows.

EnTimeMent (Nadia Berthouze, Nicolas Gold, Amanda CdC Williams)

EnTimeMent aims at a radical change in scientific research and enabling technologies for human movement qualitative analysis, entrainment and prediction, based on a novel neuro-cognitive approach of the multiple, mutually interactive time scales characterizing human behaviour.

This new approach will afford the development of AI computational models for the automated detection, measurement, and prediction of movement qualities from behavioural and affective signals, based on multi-layer parallel processes at non-linearly stratified temporal dimensions, and will radically transform and create AI-technology for human movement analysis. Case studies at UCL ranges from technology for Physical Rehabilitation, Affective Technology and Sport Technology. 

New MSc on Energy Systems and Data Analytics (UCL Energy Institute)

This new programme is the first of its kind in the UK, combining the study of Energy Systems with Data Science. This advanced degree programme is designed to provide a broad understanding of energy systems, statistics, programming, energy use in the built environment, energy use in the transport sector and the role of data and advanced analytics in solving relevant sustainability problems.
AI-TraWell (Bani Anvari, Nick Tyler, Peter Jones, Helge Wurdemann)

AI-powered, proactive TRAvel assistant to self-monitor user's experience and craft personalised travel solutions for promoting WELLbeing. Population growth in our cities results in increasing traffic, high demand for public transport and congestion due to limited capacity and lack of resilience. The negative health impacts include: Long daily commutes, multiple interchanges, unreliable journeys, overcrowding, journey delays, noise, and air pollution, all of which decrease travellers' health and wellbeing (mentally and physically). The AI-TraWell collaborative project is creating an AI-powered, proactive chat-bot to recommend personalised travel alternatives that fit travellers' needs/preferences and improves their travel experience.

AI-TraWell combines information on users' needs, preferences, physical/mental wellbeing with real-time and predictive information about all modes of transport to help users to manage the increasing complexity of mobility, to deliver better and more reliable mobility services, to improve efficiency and contributes to the overall wellbeing and health of people living in our cities. This is a project funded by EIT Urban Mobility and the AI-TraWell consortium is composed of six institutions from four European countries (two research and development institutions and two industrial partners): BMW Group, Fraunhofer Society, Achmea, Cities of Munich and Lublin, and UCL.