Robotics Colloquium: Guest Speaker Gregory Dudek

In this talk, I will discuss a series of projects focused on developing autonomous robots to collect photographic data in various settings, from scientific surveys to social gatherings. Our initial efforts involved hand-crafted algorithms supported by basic computational complexity analysis. We then progressed to using topic models to guide an autonomous swimming robot with six degrees of freedom (6DOF). We have also explored predicting human trajectories to better capture subjects photographically.  In all these case, we deployed robots in the field to aid our methods, typically using navigation policies based on a combination of model-based and model-free reinforcement learning. In recent years, our research has advanced to employing large language models to determine appropriate scenarios for indoor photography. I will provide a brief overview of these methods and some of the trade-offs associated with deploying field robots that must anticipate human needs.

Bio:
 

Gregory Dudek is a Professor with the School of Computer Science and a member of the McGill Research Centre for Intelligent Machines (CIM) and an Associate member of the Dept. of Electrical Engineering at McGill University. In 9/2008 he became the Director of the McGill School of Computer Science. Since 2012 he has been the Scientific Director of the NSERC Canadian Field Robotics Network (NCFRN): http://ncfrn.mcgill.ca He is the former Director of McGill's Research Center for Intelligent Machines, a nearly 40 year-old inter-faculty research facility. In 2002 he was named a William Dawson Scholar. In 2008 he was made James McGill Chair, and subsequently Distinguished James McGill Professor.  In 2017 he was awarded an IEEE Gold Medal. He directs the McGill Mobile Robotics Laboratory. He has been on the organizing and/or program committees of Robotics: Systems and Science, the IEEE International Conference on Robotics and Automation (ICRA), the IEEE/RSJ International Conference on Intelligent Robotics and Systems (IROS), the International Joint Conference on Artificial Intelligence (IJCAI), Computer and Robot Vision, IEEE International Conference on Mechatronics and International Conference on Hands-on Intelligent Mechatronics and Automation among other bodies. He is president of CIPPRS, the Canadian Information Processing and Pattern Recognition Society, an ICPR national affiliate. He has authored and co-authored over 350 research publications on subjects including visual object description, recognition, RF localization, robotic navigation and mapping, distributed system design, 5G telecommunications, and biological perception. This includes a book entitled "Computational Principles of Mobile Robotics" co-authored with Michael Jenkin and published by Cambridge University Press. He has chaired and been otherwise involved in numerous national and international conferences and professional activities concerned with Robotics, Machine Sensing and Computer Vision. His research interests include perception for mobile robotics, navigation and position estimation, environment and shape modelling, computational vision and collaborative filtering.