08/09/2018

What´s next?

Our Meetup series for interested parties presents and discusses current, practice-relevant research topics in the field of automated driving.

Spatio-Temporal Predictions with Deep Learning

Neural networks are already widely used in image processing for environmental perception. Mark Schutera will describe how the methods can be applied to pre-processed data in the form of objects. He will discuss the application of recurrent networks for the temporal tracking of objects as a basis for automated driving functions. He will explain how to generate sufficient data sets for the training of the networks and how to parameterize the structure of the network in a suitable way.

Mark Schutera

• is a PhD student in the field of Machine Learning in cooperation between ZF Friedrichshafen AG and the Institute for Automation and Applied Computer Science at the Karlsruhe Institute of Technology
• deals with the design of neural networks with a focus on recurrent neural networks and prediction of time series data