Skip to main content
Menu

ORI Anniversary Series Seminar 7

Location

Online

Date & Time

Monday 01 Jan 0001 -

This seminar has been postponed, new date to be advised 

The Oxford Robotics Institute is celebrating its 5th anniversary and is launching an inaugural seminar series which will host distinguished academics from around the world each month to speak about leading research shaping the future of robotics and Artificial Intelligence.

Seminar 7

Patrick van der Smagt, Director of AI research at Volkswagen Group, hosted by ORI Professor Ingmar Posner

Title
Latent-space modelling and optimal control

Abstract
Control of multidimensional systems typically relies on accurately engineered models.  Breaking this requirement is problematic with neural networks, as their Gaussian data assumptions typically do not hold.  We address this problem with sequential latent-variable models.  Trick: regularisation of the latent space using model or control knowledge par Lagrangian optimisation.  Take-away: it works, as we demonstrate on various interactions through drones, robots, or drummers.

Patrick van der Smagt is director of AI research at Volkswagen Group, and leads its Machine Learning Research Lab in Munich (https://argmax.ai), which focuses on fundamental research on machine learning for time series modelling and optimal control.  He is faculty member of the LMU Graduate School of Systemic Neurosciences and research professor at Eötvös Loránd University Budapest. He is the founding head of a European industry initiative on certification of ethics in AI applications (https://etami.eu) and member of the AI Council of the State of Bavaria. Besides publishing some CC papers on machine learning, robotics, and motor control, he has won a number of awards, including the 2013 Helmholtz-Association Erwin Schrödinger Award, the 2014 King-Sun Fu Memorial Award, the 2013 Harvard Medical School/MGH Martin Research Prize, and best-paper awards at machine learning and robotics conferences and journals. Patrick is area chair for the large ML conferences and reviews for funding agencies around the globe.