Jaehyung Jung

Hi! I’m a research scientist at the Institute of Robotics and Mechatronics, German Aerospace Center (DLR). My research background is in state estimation and machine learning for robotics.

I’ve been working on robot perception since my PhD, where I focused mainly on visual-inertial simultaneous localization and mapping with proper state uncertainty estimation. Now, I’m especially interested in real-world robots functioning outside the lab, powered by robust and theoretically grounded software stacks. My vision is to build safer and smarter robots for real-world applications (including space exploration robots!) based on theoretical foundations.

news

Jul 1, 2026	🚀 My new position at DRL-RM started!
Jun 1, 2026	FindAnything has won the ICRA 2026 Best Paper Award on Robot Perception!
Dec 16, 2025	🚀 OKVIS2-X has been open-sourced!
Oct 23, 2025	🎉 Our paper, OKVIS2-X, has been accepted in a SLAM special edition in T-RO!
May 22, 2025	My paper will be presented in ICRA 2025. Feel free to visit my session!
Jul 19, 2024	I will organize a RSS 2024 workshop. Thank you for speakers and participants!
Sep 4, 2023	🚀 My postdoc begins at Smart Robotics Lab @ TUM led by Prof. Stefan Leutenegger.
Aug 29, 2023	The end of long journey – I’ve got Ph.D. 😁
May 30, 2023	Oral presentation in a SLAM session at ICRA 2023, the video can be found here!

selected publications

2025

Uncertainty-Aware Visual-Inertial SLAM with Volumetric Occupancy Mapping

Jae Hyung Jung, Simon Boche, Sebastián Barbas Laina, and 1 more author

In 2025 IEEE International Conference on Robotics and Automation (ICRA), 2025

Bib HTML Supp

@inproceedings{jung2025uncertainty,
  title = {Uncertainty-Aware Visual-Inertial SLAM with Volumetric Occupancy Mapping},
  author = {Jung, Jae Hyung and Boche, Simon and Barbas Laina, Sebastián and Leutenegger, Stefan},
  booktitle = {2025 IEEE International Conference on Robotics and Automation (ICRA)},
  pages = {},
  year = {2025},
  organization = {IEEE},
}

OKVIS2-X: Open Keyframe-based Visual-Inertial SLAM Configurable with Dense Depth or LiDAR, and GNSS

Simon Boche, Jaehyung Jung, Sebastián Barbas Laina, and 1 more author

In IEEE Transactions on Robotics, 2025

Bib HTML Supp

@inproceedings{boeche2025okvis2x,
  title = {OKVIS2-X: Open Keyframe-based Visual-Inertial SLAM Configurable with Dense Depth or LiDAR, and GNSS},
  author = {Boche, Simon and Jung, Jaehyung and Barbas Laina, Sebastián and Leutenegger, Stefan},
  booktitle = {IEEE Transactions on Robotics},
  pages = {},
  year = {2025},
  organization = {IEEE},
}

2022

Gaussian Mixture Midway-Merge for Object SLAM With Pose Ambiguity

Jae Hyung Jung, and Chan Gook Park

IEEE Robotics and Automation Letters, 2022

Bib HTML Supp Code

@article{jung2022gaussian,
  title = {Gaussian Mixture Midway-Merge for Object SLAM With Pose Ambiguity},
  author = {Jung, Jae Hyung and Park, Chan Gook},
  journal = {IEEE Robotics and Automation Letters},
  volume = {8},
  number = {1},
  pages = {400--407},
  year = {2022},
  publisher = {IEEE},
}

Photometric visual-inertial navigation with uncertainty-aware ensembles

Jae Hyung Jung, Yeongkwon Choe, and Chan Gook Park

IEEE Transactions on Robotics, 2022

Bib HTML Supp Code

@article{jung2022photometric,
  title = {Photometric visual-inertial navigation with uncertainty-aware ensembles},
  author = {Jung, Jae Hyung and Choe, Yeongkwon and Park, Chan Gook},
  journal = {IEEE Transactions on Robotics},
  volume = {38},
  number = {4},
  pages = {2039--2052},
  year = {2022},
  publisher = {IEEE},
}

Object-based visual-inertial navigation system on matrix lie group

Jae Hyung Jung, and Chan Gook Park

In 2022 International Conference on Robotics and Automation (ICRA), 2022

Bib HTML Supp

@inproceedings{jung2022object,
  title = {Object-based visual-inertial navigation system on matrix lie group},
  author = {Jung, Jae Hyung and Park, Chan Gook},
  booktitle = {2022 International Conference on Robotics and Automation (ICRA)},
  pages = {9499--9505},
  year = {2022},
  organization = {IEEE},
}

2020

Constrained filtering-based fusion of images, events, and inertial measurements for pose estimation

Jae Hyung Jung, and Chan Gook Park

In 2020 IEEE International Conference on Robotics and Automation (ICRA), 2020

Bib HTML Supp

@inproceedings{jung2020constrained,
  title = {Constrained filtering-based fusion of images, events, and inertial measurements for pose estimation},
  author = {Jung, Jae Hyung and Park, Chan Gook},
  booktitle = {2020 IEEE International Conference on Robotics and Automation (ICRA)},
  pages = {644--650},
  year = {2020},
  organization = {IEEE},
}