4800 Oak Grove Drive
Georgios Georgakis is a Robotics Technologist in the Aerial and Orbital Image Analysis group. He received his PhD at George Mason University advised by Jana Kosecka. Georgios also holds an MSc in Computer Science from George Mason University and a Diploma in Electronic and Computer Engineering from the Technical University of Crete in Greece. Prior to joining JPL he was a Postdoctoral Researcher at the GRASP Laboratory at University of Pennsylvania working with Kostas Daniilidis. He has also spent time at Siemens Corporate Technology and United Imaging Intelligence as a research intern.
His research interests lie at the intersection of computer vision and machine learning that have applications in robotics. In his recent work he has been designing deep learning-based algorithms for vision-based navigation in novel indoor environments for the tasks of exploration, object-goal navigation, and natural language instruction-following. He is also interested in methods for uncertainty quantification in machine learning that can explain knowledge gaps of models. Prior to this, during his PhD he has worked on object detection, keypoint detector and descriptor learning, 3D object pose estimation, and human mesh recovery.
At JPL, Georgios is currently working on map-based localization for the Mars Science Helicopter, and is also part of the Europa Lander and RACER projects.
Personal website with publications and code: https://ggeorgak11.github.io/