ERA Chair in Artificial Intelligence for Robotics



AIFORS is a Horizon 2020 ERA Chair project which aims to create an ERA Chair in Artificial Intelligence for Robotics at the University of Zagreb Faculty of Electrical Engineering and Computing (UNIZG-FER). It will enable UNIZG-FER to attract an outstanding researcher and five team members to independently implement an ambitious research strategy in AI for robotics. This will open UNIZG-FER to a new research direction with a high potential for research outputs and technology innovation. The ERA Chair holder will establish and lead a Research Group for Artificial Intelligence for Robotics assigned to the Laboratory for Autonomous Systems and Mobile Robotics (LAMOR).

4th G2Net Training School

AIFORS' PhD students Vladimir and Athanasios together with prof. Bonsignorio attended the COST Action CA17137 - G2net school on Machine Learning for Gravitational Waves, Geophysics, Control System and Robotics in Thessaloniki Greece, from March 28-31, 2023. The school was focused on neural networks for sensing low-frequency signals, accelerating surrogate models with machine learning, and denoising using machine learning. 

Vladimir actively participated in the school and took the bronze place at the hackathon where the goal was to determine the range of signal-to-noise ratios of different signals. Apart from that, there was an outreach activity of short storytelling, understanding the target audience and preparing a script for a monologue/video and Vladimir was selected as one of the best.

There were 15 lecturers from different countries and universities and participants learned about data collection methods and discovering open data, different data representations including the spectrogram and Q-transform, obtaining the waveform with given parameters, finding a peak in noisy signal and estimating its significance, parameter estimation neural networks for different cases such as Gaussian distribution with diagonal (learnable) covariance and Normalizing flow (RealNVP).

News list






This project has received funding from the European Union's Horizon 2020 research and innovation programme under the Grant Agreement No. 952275