“Learning by Doing” to Develop AI Applications for Mobility
AiMTT aims to cultivate a highly skilled and diverse AI talent pool equipped to address the opportunities and challenges of AI in mobility, transport, and logistics. By combining real-world case studies with knowledge development, this initiative fosters deep expertise in the field.
Our project partners will build, test, and refine AI applications for mobility, transport, and logistics through seven real-world use cases. These tools will be ready for practical implementation. Equally important, however, is the learning process that comes with working hands-on with AI. To support this, AiMTT offers workshops, training programs, and co-creation sessions—ensuring continuous knowledge exchange and improvement.
More Than Twenty Partners
The AiMTT consortium brings together over twenty partners, carefully selected for their ability to address key mobility, transport, and logistics challenges, maximize impact, and create meaningful learning opportunities for stakeholders. This collaboration also offers strong potential for project-based training and education.
Learning Through Use Cases
AiMTT’s partners are learning and developing together through six use cases based on real-world challenges. The use cases range from crowd management at large events to smarter, more efficient solutions for inland shipping.
SEARCH OUR SITE
LATEST NEWS
-
AiMTT and TU Delft Now Offer Six MSc Thesis Projects
AiMTT and TU Delft have developed six MSc thesis projects that offer students an excellent opportunity to work on real-life traffic challenges using cutting-edge AI techniques. Two of the projects include an internship at Siemens Mobility in Zoetermeer. The six MSc thesis projects cover topics such as Active Inference, Long Short-Term Memory models, Graph Neural…
-
AI in Mobility Series: Tutorial on PINNs Published
AiMTT has published a new tutorial in its AI in Mobility series. In this article, Ying-Chuan Ni from ETH Zurich and Theivaprakasham Hari from TU Delft explain what Physics-Informed Neural Networks (PINNs) are and why they matter. The relatively new Physics-Informed Neural Networks combine the strengths of traditional traffic flow theory models with those of data-driven machine…