The AI@ORU research seminar series
At Örebro University, we truly believe that AI and autonomous systems will help solve some of our biggest societal challenges as well as make life better for billions of people around the world. That’s why we love what we do. Our aim with the research seminar series AI@ORU is to raise awareness of the breadth of perspectives on AI found at Örebro University, and to facilitate and inspire new collaborations.
AI@ORU, 14 March: Advancing deep learning-based driver and road user intent recognition
14 March, 13:00-14:00. Hörsal T, Teknikhuset
In this presentation, Professor Alessandro Saffiotti will introduce Örebro University's latest research on intention recognition systems for advanced driver assistance systems and autonomous driving systems.
The researchers have explored the following questions: How well do ego-vehicle driver intention recognition systems generalize across geographical locations and diverse sensor setups? Does training on sensors that are unavailable during testing improve intention recognition performance? How good are humans at recognizing road user intentions from videos compared to state-of-the-art deep learning approaches?
Finally, the researchers empirically evaluated several probabilistic deep learning methods to understand the limitations of the systems better and formalized an approach combining optimization-based pre-training with MCMC sampling.
Affiliation: Industrial PhD student at Volvo Cars and the Artificial Intelligence lab at the university of Skövde.
The seminar will be in English and is open to everyone, no pre-registration is required.
