Georgios Georgakis

I am a Robotics Technologist at the NASA-Jet Propulsion Laboratory working in the Aerial and Orbital Image Analysis group. My research interests lie at the intersection of computer vision and machine learning that have applications in robotics. At JPL, I have been developing perception algorithms in support of multiple autonomous systems including a future Mars Science Helicopter. Prior to joining JPL, I was a Postdoctoral Researcher in the GRASP Lab at the University of Pennsylvania advised by Kostas Daniilidis. During my PostDoc I worked on vision-based semantic navigation in novel environments for the tasks of exploration, object-goal navigation, and vision and language navigation (VLN).

I received my Ph.D from the Department of Computer Science at George Mason University. My advisor was Jana Kosecka. During my Ph.D I worked on multiple problems such as object detection and recognition in RGB-D data, keypoint and descriptor learning, and 3D object pose estimation. I spent two wonderful summers at Siemens CT as an intern in the computer vision research group. In the summer of 2019 I did an internship in the computer vision and robotics group at United Imaging Intelligence (UII) America where I worked on human 3D reconstruction. Our algorithm was integrated in a new generation of medical CT scanners that model the patient in 3D and automate the scanning process. The scanners have been deployed in more than 300 hospitals worldwide including in Cyprus!

Prior to joining George Mason University I completed my Diploma in Computer Engineering from the Technical University of Crete in Greece. I worked with Dr. Michail G. Lagoudakis on landmark recognition and localization for the RobotStadium online robotic soccer competition.

CV | Scholar | LinkedIn | Github

Contact Information

198-120, 4800 Oak Grove Dr, Pasadena, CA 91109
georgios DOT georgakis AT jpl DOT nasa DOT gov


Teaching

ESE 650 Learning in Robotics (Spring 2022)
Syllabus | Website | Notes: Spring 2021 from Pratik Chaudhari


Papers

Learning Illumination Invariant Features for Lunar South Pole with Deep Learning
Georgios Georgakis, Adnan Ansar
Space Imaging Workshop (SIW), 2024
[pdf]

 
     

Pixel to Elevation: Learning to Predict Elevation Maps at Long Range
using Images for Autonomous Offroad Navigation

Chanyoung Chung, Georgios Georgakis, Patrick Spieler, Curtis Padgett,
Ali Agha, Shehryar Khattak
IEEE Robotics and Automation Letters (RA-L), 2024
[pdf]

 
     

Icy Moon Surface Simulation and Stereo Depth Estimation for Sampling Autonomy
Ramchander Bhaskara, Georgios Georgakis, Jeremy Nash, Marissa Cameron,
Joseph Bowkett, Adnan Ansar, Manoranjan Majji, Paul Backes
IEEE Aerospace Conference (AeroConf), 2024
[pdf | code]

 
     

Unordered Navigation to Multiple Semantic Targets in Novel Environments
Bernadette Bucher*, Katrina Ashton*, Bo Wu, Karl Schmeckpeper, Siddharth Goel,
Nikolai Matni, Georgios Georgakis, Kostas Daniilidis
Embodied AI Workshop at CVPR 2023
[pdf]

 
     

Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets
Frederick Ebert*, Yanlai Yang*, Karl Schmeckpeper, Bernadette Bucher, Georgios Georgakis,
Kostas Daniilidis, Chelsea Finn, Sergey Levine
Robotics: Science and Systems (RSS), 2022
* equal contribution
[pdf]

 
     

Cross-modal Map Learning for Vision and Language Navigation
Georgios Georgakis, Karl Schmeckpeper, Karan Wanchoo, Soham Dan,
Eleni Miltsakaki, Dan Roth, Kostas Daniilidis
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
[pdf | project page | code]

 
     

Learning to Map for Active Semantic Goal Navigation
Georgios Georgakis*, Bernadette Bucher*, Karl Schmeckpeper,
Siddharth Singh, Kostas Daniilidis
International Conference on Learning Representations (ICLR), 2022
* equal contribution
[pdf | project page | code | video]

 
     

Uncertainty-driven Planner for Exploration and Navigation
Georgios Georgakis, Bernadette Bucher, Anton Arapin, Karl Schmeckpeper,
Nikolai Matni, Kostas Daniilidis
IEEE Conference on Robotics and Automation (ICRA), 2022
[pdf | project page | code | video | slides]

 
     

Object-centric Video Prediction without Annotation
Karl Schmeckpeper*, Georgios Georgakis*, Kostas Daniilidis
IEEE Conference on Robotics and Automation (ICRA), 2021
* equal contribution
[pdf | code | video]

 
     

Hierarchical Kinematic Human Mesh Recovery
Georgios Georgakis*, Ren Li*, Srikrishna Karanam,
Terrence Chen, Jana Kosecka, and Ziyan Wu
European Conference on Computer Vision (ECCV), 2020
* equal contribution
[pdf | supplementary | long slides | short slides | long video | short video]

 
     

Robust Multi-modal 3D Patient Body Modeling
Fan Yang, Ren Li, Georgios Georgakis, Srikrishna Karanam,
Terrence Chen, Haibin Ling, Ziyan Wu
Medical Image Computing and Computer Assisted Interventions (MICCAI), 2020
[pdf]

 
     

Simultaneous Mapping and Target Driven Navigation
Georgios Georgakis, Yimeng Li, and Jana Kosecka
arXiv:1911.07980
[pdf | code]

 
     

Towards Robust RGB-D Human Mesh Recovery
Ren Li, Changjiang Cai, Georgios Georgakis, Srikrishna Karanam,
Terrence Chen, Ziyan Wu
arXiv:1911.07383
[pdf]

 
     

Learning Local RGB-to-CAD Correspondences for Object Pose Estimation
Georgios Georgakis, Srikrishna Karanam, Ziyan Wu, and Jana Kosecka
IEEE International Conference on Computer Vision (ICCV), 2019
[pdf | slides | poster]

 
     

End-to-end Learning for Keypoint Detection and Descriptor for Pose Invariant 3D Matching
Georgios Georgakis, Srikrishna Karanam, Ziyan Wu, Jan Ernst, and Jana Kosecka
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018
[pdf | supplementary | poster]

 
     

Label Propagation in RGB-D Video
Md Alimoor Reza, Hui Zheng, Georgios Georgakis, and Jana Kosecka
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2017
[pdf]

 
     

Synthesizing Training Data for Object Detection in Indoor Scenes
Georgios Georgakis, Arsalan Mousavian, Alexander C. Berg, and Jana Kosecka
Robotics: Science and Systems (RSS), 2017
[pdf | poster | slides | video | project page]

 
     

A Contact Exploitative Approach to the Amazon Robotics Challenge
Eadom Dessalene, Georgios Georgakis, Md Alimoor Reza, Yimeng Li,
Yossi Ovcharik, Amir Shapiro, Jana Kosecka, and Daniel Lofaro
Warehouse Picking Automation Workshop (ICRA), 2017
[pdf]

 
     

Multiview RGB-D Dataset for Object Instance Detection
Georgios Georgakis, Md Alimoor Reza, Arsalan Mousavian, Le Phi-Hung, and Jana Kosecka
International Conference on 3D Vision (3DV), 2016
[pdf | poster | project page]

 
     

RGB-D Multiview Object Detection with Object Proposals and Shape Context
Georgios Georgakis, Md Alimoor Reza, and Jana Kosecka
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2016
[pdf | poster | short slides | code]

 
     

Patents Pending