This year we received 5 nominations, which were all reviewed by several SAIS board members. Although we received many high-quality nominations, after the review process the highest ranked thesis by the reviewers, at the same time the one considered most interesting for a presentation at the SAIS workshop, was selected by the board as this years winner.
The SAIS Best AI Master’s Thesis Award 2025 goes to:
Hannes Nilsson and Rikard Johansson, for the thesis entitled “Learning
to Navigate Over Stochastic Transport Networks Using Multi-Armed
Bandits”, conducted at Chalmers University of Technology under the
supervision of Morteza Haghir Chehreghani.
Motivation:
The thesis addresses the important practical challenge of energy
efficient route selection, when navigating a road network with an
electric vehicle. This contributes both to the area of intelligent
transportation systems, as well as sustainability and the transition
away from fossil fuel vehicles. In the thesis the problem is studied
within a realistic setting, further enhancing the applicability of the
results. The work provides a scientific contribution within AI, studying
the application of multi-armed bandit algorithms to this problem, and
assessing different implementations of the algorithms. The thesis is
additionally very well written, has a clear motivation and relevance to
the field, and includes a thorough experimental validation.
The thesis will be invited to be presented at the SAIS workshop 2025 (see: https://slawomir-nowaczyk.github.io/SAIS-2025), at Halmstad University on June 16-17 2025.
Congratulations to the winners, and a big thanks to everyone who nominated a thesis as well as the reviewers for their assessment effort!
The SAIS board,
through Eva Blomqvist, SAIS secretary