Thomas Schön

Thomas Schön, Professor of Automatic Control at Uppsala University. Photo: Mikael Wallerstedt

My main research interest is nonlinear inference, especially within the context of dynamical systems, solved using probabilistic models and algorithms. In terms of scientific fields, my research is situated somewhere on the intersection between the fields of machine learning, signal processing and automatic control. My aim is to pursue both basic and applied research, where the latter is typically carried out in close collaboration with industry. A brief overview of my research is available here and my publications are available here.


Recent research results/news

August 28, 2014: Our new results on Bayesian parameter inference in nonlinear dynamical systems have just been accepted for publication in Statistics and Computing. We introduce two alternative versions of the Particle Metropolis Hastings (PMH) algorithm that incorporate gradient and Hessian information about the posterior into the proposal. In the paper we show how to estimate the required information using a fixed-lag particle smoother.

Johan Dahlin, Fredrik Lindsten and Thomas B. Schön. Particle Metropolis Hastings using gradient and Hessian information. Statistics and Computing, 2014. (accepted for publication) [arXiv] [code]

August 22, 2014: Christian Andersson Naesseth won the best poster award at the Summer school on deep learning for image analysis (held in Copenhagen, Denmark). The poster is available here and the papers describing the work in detail are available here and here.

cars

August 18, 2014: During the summer a team of students have been working on realizing the CARS project, which is an acronym for Camera-based Autonomous Racing System. You can have a look at their result in this video. It includes a camera based target tracking system, controllers and of course the practical implemention of it all. The project web-site will be available shortly.

July 30, 2014: Recently we had two papers accepted. The first paper presents a maximum likelihood estimator for jump Markov linear models based on a combination of the particle filter and Markov chain Monte Carlo methods. In the second paper we derive a new Sequential Monte Carlo-based algorithm to estimate the capacity of two-dimensional channel models, yielding more than an order of magnitude improvement in estimation accuracy compared to existing methods. The underlying method is explained in  a more general context in this video and in this arXiv paper.

Andreas Svensson, Thomas B. Schön and Fredrik Lindsten. Identification of jump Markov linear models using particle filters. In Proceedings of the 53rd IEEE Conference on Decision and Control (CDC), Los Angeles, CA, USA, December, 2014. (accepted for publication)
Christian A. Naesseth, Fredrik Lindsten and Thomas B. Schön. Capacity estimation of two-dimensional channels using Sequential Monte CarloIn Proceedings of the IEEE Information Theory Workshop (ITW), Hobart, Tasmania, Australia, November, 2014. (accepted for publication) [pdf] [arXiv]

May 28, 2014: Our recent explorations on the use of Monte Carlo methods (including sequential Monte Carlo) for real-time video based lightning has been accepted for publication at the 22nd European Signal Processing Conference (EUSIPCO) held in Lisabon, Portugal in September. This is very much introductory work for us and more will follow.

Joel Kronander, Johan Dahlin, Daniel Jönsson, Manon Kok, Thomas B. Schön and Jonas Unger. Real-time video based lighting using GPU raytracing, in Proceedings of the 22nd European Signal Processing Conference (EUSIPCO), Lisabon, Portugal, September 2014. (accepted for publication)

May 21, 2014: We (Nicolas Chopin, Adam Johansen and myself) are organizing a workshop on sequential Monte Carlo methods at ENSAE in Paris during August 26-28 2015. More information is available here. Hope to see you there!

May 9, 2014: On June 5, Manon Kok will defend her licentiate thesis entitled Probabilistic modeling for positioning applications using inertial sensors [pdf]. The discussion leader will be Dr. Gabriele Bleser from the Augmented Vision group at the German Research Center for Artificial Intelligence. The thesis contains (among other things); A new optimization-based formulation of human motion capture (finding the position and orientation of human bodies) using inertial sensors and a new algorithm to calibrate magnetometers in the presence of metallic objects. The thesis is available here.


Click here for older news.

 © Thomas Schön 2014