His name is Andrea Micheli, he was born in 1987 and has just won the EurAI award for best PhD thesis in the field of Artificial Intelligence at European level.
The prize was officially awarded August 31, 2016 during the ECAI 2016 Conference, the most important European conference on Artificial Intelligence.
The study of the Italian researcher crushed the fierce international competition and is the result of a four-year work done thanks to a scholarship by the Bruno Kessler Foundation in Trento at the Embedded Systems Research Unit led by Alessandro Cimatti. The thesis, entitled Planning and Scheduling in Uncertain temporally Domains, has been discussed this year at the ICT School of the University of Trento where he completed the doctoral program.
Andrea Micheli explains how this passion for Artificial Intelligence was borne, and what he is planning in the future: "During my studies in Computer Science at the University of Trento I had a part-time co-operation agreement to the Bruno Kessler Foundation, at the Embedded Systems Unit. Here I learned about this dedicated area, which was the subject of my thesis for the Master degree, supervised by Alessandro Cimatti. I continued my studies in the same field with my PhD thesis, working in team with FBK researchers. I currently work at the Bruno Kessler Foundation with a research contract. I see my future in the research field”.
The thesis lies in the field of Artificial Intelligence studies called planning. The goal of planning is to automatically generate the commands to be imparted to a system (for example a robot or an industrial system) to achieve a given objective. In particular, the study covered the temporal uncertainty problem, that is, when the duration of certain assets is not controllable. For example, if we ask to an exploration robot to move between two geographical points, the time of the travel may depend on the weather conditions or the roughness of the terrain: these are factors that the robot cannot control.
In this sense, the planning must take into account the uncertainty in the duration of the actions to build strategies that guarantee the achievement of the objective in all situations. The techniques that have been developed in the thesis precisely serve to ensure the achievement of the objective taking limited uncertainty, which is specified by an expert in this field (for example, the robot can assume a minimum and a maximum duration for the travel and the execution will be ensured assuming the correctness of these constraints). This kind of problem is particularly important in the field of space exploration. During the PhD studies Andrea Micheli has also spent six months at the NASA Ames Research Center in Mountain View (California).