In this interview of Robots in Depth, the host Per Sjöborg speaks to professor of computer science at McGill University, Gregory Dudek about the field of robotics.
They discuss air, surface and underwater vehicles, reviewing challenges as well as how to best use these vehicles, both individually and as a collaborative team of robots.
Professor Dudek is Research Director of the McGill Mobile Robotics Lab. His research area's are autonomous navigation, robots that learn, mobile robotics, machine learning, robot localization, information summarization, human-robot interaction, sensor-based robotics, multi-robot systems, computer vision, marine robotics, self-driving vehicles, and recognition.
His research deals with sensing for robots and has included theoretical work on the complexity of robot localization and the development of underwater and amphibious robots. He has worked on the use of topological maps and the complexity of topological mapping, an abstract idealized form of robotics problem. He has also looked at robot position estimation using photographic data, and the automated detection of interesting images.
With his colleagues he produced the first formal proof of the complexity of global robot localization in a metric environment (i.e. how hard it is, in the worst possible case, for a robot to determine its position if it totally lost).
Gregory has a wide range of research interests that all have the common theme of robotics. He works with students in the Mobile Robotics Lab (MRL) at McGill on many problems involving aspects of artificial perception, robot navigation, sample theory (e.g. applications of the secretary problem to robotics and recommender systems.