Perception sensor data analysis for real-time target identification and sensor localization

University of Turku

Modern mapping systems such as unmanned aerial vehicles (UAV) and autonomous surface vessels (ASV) have witnessed significant advancements, but achieving effective decision-making in dynamically changing environments remains a huge challenge. Conventional mapping methodologies often rely on post-processing of the collected data, which can lead to unacceptable delays in getting the required information in quickly changing conditions, such as flood events. Increasing the real- or near-real-time capabilities in data processing will be an asset even in more conventional mapping tasks, reducing the timespan between data acquisition and pursued final product.

We seek a talented PhD researcher with expertise in machine learning and spatial environmental data analysis. The PhD project focuses on developing novel machine learning algorithms especially based on deep learning methodologies for real- and near-real-time target identification and sensor localization using the data collected with perception sensors, especially laser scanners, onboard UAVs and ASVs. From collected data, the goal is to create a comprehensive map needed for building accurate digital representations of the environment. The successful candidate will develop, test, and refine these machine learning algorithms.

The position requires an active approach, diligence and cooperation skills, willingness to work as a part of a team and a passion to learn new things. We expect an excellent master’s degree in robotics and autonomous systems, machine learning, data science, artificial intelligence or relevant field. We also welcome applications from master’s students who will complete their master’s degree in 2024 by the date set by the involved doctoral programme at UTU. The candidate should possess a strong understanding of machine learning algorithms and techniques, particularly those relevant to feature extraction and localization. Experience with environmental and geospatial data analysis is an asset.

FGI

Department of Computing/ Faculty of Technology

Prof. Tomi Westerlund, UTU

Prof. Jukka Heikkonen, UTU

Prof. Harri Kaartinen, FGI

Prof. Harri Kaartinen, FGI