Scholar
Ukcheol Shin
Google Scholar ID: ZvxI80EAAAAJ
Korea Institute of Energy Technology (KENTECH)
Citations & Impact
Citations
463
H-index
11
i10-index
13
Publications
20
Co-authors
25
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Best Student Paper Award, WACV 2023
- 29th Samsung Humantech Paper Award
- 1st Place Award, CVPR WAD Workshop 2024
- Best Poster Award, ICRA TIRO Workshop 2025
- Co-organized 'Thermal Infrared in Robotics' workshop at ICRA 2025
- Co-organized 'Multi-spectral Imaging for Robotics and Automation' workshop at ICCV 2025
- Multiple under-review publications including 'All-day Depth Completion via Thermal-LiDAR Fusion', 'Deep Depth Estimation from Thermal Image', and 'SF-VO: Self-Supervised Few-Shot Adaptation for Visual Odometry'
Research Experience
- Aug. 2025–Present: Assistant Professor, School of Energy Engineering / Institute for Energy AI, KENTECH; Principal Investigator of Robust Physical AI & Robotics (RoBust) Lab
- Aug. 2023–Aug. 2025: Postdoctoral Fellow, Bot Intelligence Group, Robotics Institute, Carnegie Mellon University (Advisor: Prof. Jean Oh)
- Sep. 2019–Aug. 2023: Research Assistant (Ph.D.), Robotics and Computer Vision Lab, KAIST (Advisor: Prof. In So Kweon); Research topics: Self-supervised learning, 3D geometry, thermal imaging, reinforcement learning
- Sep. 2017–Aug. 2019: Research Assistant (M.S.), Robotics and Computer Vision Lab, KAIST (Advisor: Prof. In So Kweon); Research topics: Camera exposure control, low-level vision, 3D geometry
- Mar. 2015–Jun. 2017: Research Intern, Embedded System Lab, SNUST (Advisor: Prof. Byoung Wook Choi); Research topics: Embedded Linux, real-time operating systems, real-time Ethernet protocols
Background
- Assistant Professor at the School of Energy Engineering and Institute for Energy AI, KENTECH.
- Research focuses on developing robust physical AI capable of perceiving, understanding, and navigating dynamic environments under challenging conditions.
- Specific interests include spatial/semantic perception in extreme conditions, self-supervised learning, deep reinforcement learning, multi-sensor fusion, and vision-language navigation/manipulation.
- Interested in physical AI and deep reinforcement learning for embodied agents (e.g., legged robots, humanoids, camera systems).
- Works on 3D geometry under adverse conditions such as rain, snow, over-exposure, and low-light.
- Explores representation learning from multi-modal sensors via self-supervision.
