Industrial PhD: Micro-to-Macro Modelling of Traffic Flow with ML

Description


This proposal is concerned with developing a machine learning framework for macro-micro modelling of traffic flow. Micro models consider modelling individual drivers whereas macro models focus on collective vehicular flows. Micro models can provide more detail and accurate information, but with the cost of more expensive computations. Overfitting and dealing with noisy/incomplete data are other challenge of these types of models. Such issues limit the applicability of these models to large-scale networks and traffic control with many control decisions. Therefore, macro models are usually preferred due to higher efficiency and more generality, though they might abstract some detailed behavior of the drivers. The aim of this project is thus to develop advanced AI and machine learning methods for micro-to-macro modelling of traffic flow and to cope with the several issues and challenges of existing methods like availability of sufficient data, incremental nature of data, etc. In particular, we will use methods such as active learning, reinforcement learning, and multi-agent learning to develop a generic and unified framework for this purpose.


This project will be part of the Wallenberg AI, Autonomous Systems and Software Program (WASP) funded by the Knut and Alice Wallenberg Foundation. The PhD student will enjoy the benefits of the WASP graduate school https://wasp-sweden.org/graduate-school/, where skills can be acquired on artificial intelligence, autonomous systems and software. As a PhD student you will be given opportunities for many inspiring conversations, plenty of autonomous work and some travel. Short term visits may be organized to highly ranked universities under the WASP umbrella, such as Stanford University, UC Berkeley, Nanyang Technological University, or similar.


This project will provide knowledge which can be used by the heavy commercial vehicle industry to produce world-leading transport solutions. Volvo Trucks is the main applicant and provides industrial delivery. Academic supervision will be provided at Chalmers University of Technology (Department of Computer Science and Engineering, Data Science and AI Division). The PhD student will enjoy an office at Chalmers, and access to education and facilities.


The industrial PhD period is about 4.5 years.


Experience and knowledge
M.Sc. degree in Physics, Mathematics, Computer Science/Engineering, Electrical Engineering, or similar subjects. Good grades are expected in most of the courses.
Preferably hands-on experience with machine learning and data science tools and problems
Preferably experience with transport data analytics
Relevant industrial experience is a plus
Fluency in English, both written and spoken
Solid background in machine learning and AI
Good knowledge of statistics and probability
Knowledge in Python

Competencies
Deep interest in figuring out how things work and propose new innovative solutions to challenges
Collaborates effectively with others to meet shared objectives.
Problem solving: ability to make sense of complex, high quantity and sometimes contradictory information to effectively solve problems.
Being resilient: able to rebound from setbacks and adversity when facing difficult situations.
Ability to bring ideas from theory into practice, make them work in real situations.

Personal attributes:
Organized and good at handling the workload
Communicates effectively
Interest in research and science, building knowledge and long-term innovation
Reliable and accountable
Motivated and energetic to do a PhD

For question and further information please contact Rached Dardouri +46 76 5537328.


Kindly note that due to GDPR, we will not accept applications via mail. Please use our career site.