This project examines future forms of transport services and infrastructure which are likely to be transformed by vehicle automation and sharing platforms in the near future.

This includes the introduction of ultra-low emissions vehicles and Connected/Automated Vehicles (CAV), and the development of various types of shared mobility services - Mobility-As-A-Service (MaaS) - that will affect labour markets, job accessibility, travel demands, and traffic congestion.

Aims and Objectives

The aim of this project is to explore future forms of transport services and infrastructure which are likely to be transformed by automation and sharing platforms in the near future.

Our first objective is to study the spatial and regional effects of automation and MaaS by using novel sources of sensor, synthetic, and private sector data on infrastructure, transport connectivity and job accessibility in the transport network. To this end, UBDC has licensed data from the online jobs listings aggregator Burning Glass. For this study, we employ innovative Artificial Intelligence/Machine Learning methods that integrate a series of metadata features into a unified model, so as to effectively capture various indices affecting labour markets and job accessibility.

The second objective is to ascertain “last-mile” transport solutions by developing micro- and macro-simulation models that integrate various levels of vehicle automation and shared mobility services. A number of operational scenarios with low-energy vehicles (LEV), connected/automated vehicles (CAV), and demand-response services will be considered to bring high-quality, socially equitable forms of transport accessibility in selected areas. Regional models of Scotland and England will be used for this study.

Impact

We are currently working together and engaging with Peter Brett Associates (PBA), MaaS Scotland, and PTV/UK to evaluate the spatial and regional effects of varying degrees of automation and sharing mobility. It is expected that the methods and results being proposed will help our industry partners to reach new markets to a global pipeline of contracts in integrating CAVs into infrastructure planning and construction, and MaaS solutions in addressing expensive last-mile problems facing city managers worldwide.

Researchers

Lead: Dr. Konstantinos Ampountolas
Team: Dr. Long Chen, Prof. Vonu Thakuriah

Partners

Latest Outputs

  • Conference item: L. Chen, P. Thakuriah, and Y. Sun. Predicting Individual Salaries in UK with Graphical Convolutional Network. The 18th International Conference on Hybrid Intelligent Systems (HIS 2018), Porto, Portugal.
  • Conference item: L. Chen, P. Thakuriah, and K. Ampountolas. Predicting Uber Demands in NYC with WaveNet. The Fourth International Conference on Universal Accessibility in the Internet of Things and Smart Environments (SMART ACCESSIBILITY 2019 ), Athens, Greece.

 

JOINTLY FUNDED BY