CV
This is a description of the page. You can modify it in '_pages/cv.md'. You can also change or remove the top pdf download button.
Contact Information
| Name | John K. Jung |
| Professional Title | Ph.D. Candidate |
| kyungmin.jung@mail.mcgill.ca | |
| Location | 1160 Rue Mackay, Montreal, QC H3G 0G8 |
Professional Summary
I am a Ph.D. candidate in Robotics at DECAR research group, McGill University, Canada. My research interests include robot autonomy, specifically in the areas of robot perception, navigation, and mapping. I am passionate about developing algorithms and systems that enable robots to operate effectively in complex and dynamic environments.
Experience
-
2021 - 2026 Waterloo, ON
Graduate Student Researcher
Voyis Imaging Inc.
- Developed a real-time SLAM system fusing camera, DVL, IMU, and depth sensors within a continuous-time estimation framework for robust underwater navigation.
- Deployed a deep-learned visual front-end accelerated via the ONNX runtime, significantly increasing local feature tracking reliability under severe visual degradation.
- Developed robust non-convex optimization strategies and 3D feature descriptors to improve ICP-based point cloud registration for subsea laser SLAM.
-
2019 - 2021 Montreal, QC
Graduate Student Researcher
ARA Robotique
- Designed and implemented a tightly-coupled LiDAR-inertial-visual SLAM state estimator for UAVs utilizing factor graph optimization.
- Formulated IMU preintegration on Lie groups (manifolds) and implemented consistent visual feature marginalization techniques to preserve map consistency and bounded runtime.
- Executed multi-sensor spatial/temporal intrinsic and extrinsic calibration routines via Kalibr, along with Allan variance stochastic modeling for IMU noise calibration.
-
2018 - 2018 Mirabel, QC
Airframe Fatigue and Stress Analysis Intern
Bell Flight
- Evaluated structural fatigue life and multi-axial stress concentrations on composite bolted joint assemblies under flight loads.
- Analyzed bypass and bearing stress distribution profiles across diverse composite laminate configurations.
- Developed an automated structural analysis tool to accelerate joint fatigue verification workflows for airframe design engineers.
Education
-
2021 - 2026 Montreal, Canada
Publications
-
2026 DIVO: Continuous-time DVL-Inertial-Visual Odometry for Unmanned Underwater Vehicles
ArXiv
This paper presents a novel acoustic-visual-inertial odometry solution leveraging a continuous-time trajectory estimation framework for unmanned underwater vehicles. Underwater environments present unique challenges for visual localization and mapping, such as light attenuation, illumination variance, and the presence of particulate matter.
-
2024 An Adaptive Graduated Nonconvexity Loss Function for Robust Nonlinear Least-Squares Solutions
IEEE Transactions on Robotics
The main contribution of this article is to combine these two approaches by using an adaptive kernel within a GNC optimization scheme. This brings a solution to least-squares problems that is robust to both outliers and initialization errors, without the need for model selection and tuning.
-
2023 Performance Evaluation of 3D Keypoint Detectors and Descriptors on Coloured Point Clouds in Subsea Environments
IEEE International Conference on Robotics and Automation
This paper aims to identify the best detector/descriptor pair using a challenging field dataset collected using a commercial underwater laser scanner.