Tag Archives: robotic

Postdoc to give a talk at a world-leading AI lab in America

A School of Computer Science STRANDS postdoc has been invited to give a presentation at a world-leading Computer Science and Artificial Intelligence Lab in the USA.

Dr Tomas Krajnik, in L-CAS will give a talk next week at MIT: Computer Science and Artificial Intelligence Laboratory in Cambridge, USA on ‘FreMEn: Frequency Map Enhancement for Long-Term Autonomy of Mobile Robots’.

Tom is a research fellow at the Lincoln Center of Autonomous Systems. He has a PhD degree in Artificial Intelligence and Biocybernetics from the Czech Technical University, Prague, Czech Republic, in 2012. His research interests include long-term autonomy, robot vision and aerial robotics.

This is an amazing opportunity for him to present the work of the STRANDS project to an American audience and we will keep you informed on how the talk goes.

Abstract:

While robotic mapping of static environments has been widely studied,life-long mapping in non-stationary environments is still an open problem. We present an approach for long-term representation of natural environments, where many of the observed changes are caused by pseudo-periodic factors, such as seasonal variations, or humans performing their daily chores.

Rather than using a fixed probability value, our method models the uncertainty of the elementary environment states by their frequency spectra. This allows to integrate sparse and irregular observations obtained during long-term deployments of mobile robots into memory-efficient models that reflect the recurring patterns of activity in the environment.

The frequency-enhanced spatio-temporal models allow to predict the future environment states, which improves the efficiency of mobile robot operation in changing environments. In a series of
experiments performed over periods of weeks to years, we demonstrate that the proposed approach improves mobile robot localization, path and task planning, activity recognition and allows for life-long spatio-temporal exploration.

STRANDS