MAIA
22065
From 2023 to 2025
TML is collaborating on a data analysis toolbox and models developed to support informed design and implementation of multimodal airport access solutions. This toolbox draws on two innovative mobility solutions: autonomous vehicle fleets and unmanned aerial vehicle fleets.
Air transport is multimodal by nature, as every passenger using air transport services needs to combine different modes of transport to have a seamless door-to-door journey. However, the emergence of new technologies such as cooperative, connected, and automated mobility (CCAM) and urban air mobility (UAM) has great potential to improve airport accessibility, increase trip reliability and reduce environmental impacts. Therefore, the MAIA project is developing a data analysis and modelling toolbox to support informed design and implementation of multimodal airport access solutions. This toolbox relies on two innovative mobility solutions: autonomous vehicle fleets and unmanned aerial vehicle fleets. The effectiveness of these solutions will be demonstrated through two comprehensive case studies: Madrid Barajas Airport and Brussels Airport.
MAIA will provide three tools based on CCAM and UAM technologies to optimise the implementation and operation of innovative multimodal airport access services:
The proposed research methodology is structured around five axes:
TML will develop and validate the MAIA Engine by collecting data and developing algorithms for passenger profiling, airport access monitoring and demand modelling.
Air transport is multimodal by nature, as every passenger using air transport services needs to combine different modes of transport to have a seamless door-to-door journey. However, the emergence of new technologies such as cooperative, connected, and automated mobility (CCAM) and urban air mobility (UAM) has great potential to improve airport accessibility, increase trip reliability and reduce environmental impacts. Therefore, the MAIA project is developing a data analysis and modelling toolbox to support informed design and implementation of multimodal airport access solutions. This toolbox relies on two innovative mobility solutions: autonomous vehicle fleets and unmanned aerial vehicle fleets. The effectiveness of these solutions will be demonstrated through two comprehensive case studies: Madrid Barajas Airport and Brussels Airport.
MAIA will provide three tools based on CCAM and UAM technologies to optimise the implementation and operation of innovative multimodal airport access services:
- MAIA-Engine: a set of tools for passenger-centric implementation.
- MAIA-CCAM: a vehicle allocation tool to support the operation of shared autonomous vehicle fleets.
- MAIA-UAM: a framework for selecting suitable vertiport locations for unmanned aerial vehicle services.
The proposed research methodology is structured around five axes:
- Axis 1: Problem definition: the project starts by characterising baseline conditions based on spatial analysis techniques.
- Axis 2: Development and validation of the MAIA Engine, including the creation of a data inventory, the use of machine learning classification models, synthetic algorithms for population generation, data-driven models for predicting demand for shared mobility and discrete choice models for airport access services.
- Axis 3 and Axis 4: Development and validation of MAIA-CCAM and MAIA-UAM, respectively, both guided by a Design Thinking approach.
- Axis 5: Cross-sectional demonstration in case studies, where MAIA will model passenger behaviour in two specific cases using the MAIA Engine, with the aim of providing input for MAIA-CCAM and MAIA-UAM. Simulations will be conducted to compare multimodal performance indicators before and after the implementation of new innovative mobility services.
TML will develop and validate the MAIA Engine by collecting data and developing algorithms for passenger profiling, airport access monitoring and demand modelling.
