This workshop on Machine Learning in Smart Mobility will gather both the ML community and transportation practitioners to discuss how cutting-edge ML technologies can be effectively applied to improve the performance of transportation and mobility systems on a sustainable basis, according to three important dimensions: economic, environmental, and social. This forum also aims to generate new ideas towards building innovative applications of machine learning into smarter, greener, and safer mobility systems, stimulating contributions that emphasise on how theory and practice are effectively coupled to solve real-life problems in contemporary transportation, naturally including all sorts of mobility modes and their intrinsic interactions. Indeed, contemporary transportation is evolving rapidly on a more intelligent basis, and the concept of Intelligent Transportation Systems (ITS) has become already a reality among us, supporting the infrastructure leading to the emergence of the so-called Smart Mobility, and to a whole bunch of Mobility- as-a-Service (MaaS) options as we witness today. Also, when placed within the framework of Smart Cities, smart mobility gains more and more complexity and brings about new performance measures such as equity and social impact, privacy and security, ethical and legal compliance, explainable decision-support, while environmental sustainability is strongly emphasised.
Therefore, this workshop is within the application-oriented, integrative, and multi-disciplinary perspectives of Machine Learning, and contributes to the IDEAL Conference with an appropriate forum to foster discussions on emerging and challenging topics in intelligent data analysis, data mining and their associated learning systems and paradigms in the very dynamic and evolving domain of urban mobility. It is intended to leverage the cross-fertilisation between ML and Smart Mobility, offering the appropriate support for a more effective and improved decision-making platform underlying urban mobility planning and management tasks, to which data is paramount. This workshop is also being promoted as an initiative of the IEEE ITS Society’s Technical Activities Sub-committee on Artificial Transportation Systems and Simulation, and as part of the H2020 SIMUSAFE Project.