Papers
/
/

CV

Taekyung Kim is a third-year PhD student in Robotics at the University of Michigan, Ann Arbor. He has research experiences in safety-critical navigation, learning for robot dynamics and control, and model-based reinforcement learning.
A PDF version of my CV is also available in this link. For the most current version of my CV, please refer to this web page.

Education

•
University of Michigan, Ann Arbor
PhD, Robotics (Advisor: Dimitra Panagou)
2023.08 - (Expected) 2027.04
•
Daegu Gyeongbuk Institute of Science and Technolog (DGIST)
Bachelor's degree, College of Transdisciplinary Studies, 3.92/4.0
Summa Cum Laude
2016.02 - 2020.02
•
UC Berkeley
Visiting Student
2017.06 - 2017.08

Publication

Journal Publications

Visibility-Aware RRT* for Safety-Critical Navigation of Perception-Limited Robots in Unknown Environments [RA-L/IROS 2025]
Authors: Taekyung Kim, Dimitra Panagou
Learning Terrain-Aware Kinodynamic Model for Autonomous Off-Road Rally Driving With Model Predictive Path Integral Control [RA-L 2023/ICRA 2024]
Authors: Hojin Lee*, Taekyung Kim*, Jungwi Mun, Wonsuk Lee
Self-Supervised 3D Traversability Estimation with Proxy Bank Guidance [IEEE Access 2023]
Authors: Jihwan Bae*, Junwon Seo*, Taekyung Kim, Hae-gon Jeon, Kiho Kwak, Inwook Shim
ScaTE: A Scalable Framework for Self-Supervised Traversability Estimation in Unstructured Environments [RA-L/IROS 2023]
Authors: Junwon Seo*, Taekyung Kim*, Kiho Kwak, Jihong Min, Inwook Shim
Smooth Model Predictive Path Integral Control without Smoothing [RA-L/IROS 2022]
Authors: Taekyung Kim, Gyuhyun Park, Kiho Kwak, Jihwan Bae, Wonsuk Lee
TOAST: Trajectory Optimization and Simultaneous Tracking Using Shared Neural Network Dynamics [RA-L/IROS 2022]
Authors: Taekyung Kim*, Hojin Lee*, Seongil Hong, Wonsuk Lee
An Open-Source Low-Cost Mobile Robot System with an RGB-D Camera and Efficient Real-Time Navigation Algorithm [IEEE Access 2022]
Authors: Taekyung Kim*, Seunghyun Lim*, Gwanjun Shin, Geonhee Sim, Dongwon Yun
Curriculum Learning for Vehicle Lateral Stability Estimations [IEEE Access 2021]
Authors: Jihwan Bae*, Taekyung Kim*, Wonsuk Lee, Inwook Shim
Improved Environment Recognition Algorithms for Autonomous Vehicle Control [Journal of Auto-vehicle Safety Association 2019]
Authors: Inhwan Bae*, Yeonghoo Kim*, Taekyung Kim*, et al.

Peer Reviewed Conference Publications

Safe Model Predictive Diffusion with Shielding [ICRA 2026]
Authors: Taekyung Kim, Keyvan Majd, Hideki Okamoto, Bardh Hoxha, Dimitra Panagou, Georgios Fainekos
Beyond Collision Cones: Dynamic Obstacle Avoidance for Nonholonomic Robots via Dynamic Parabolic Control Barrier Functions [ICRA 2026] Oral (Top 8.27 %)
Authors: Hun Kuk Park*, Taekyung Kim*, Dimitra Panagou
How to Adapt Control Barrier Functions? A Learning-Based Approach with Applications to a VTOL Quadplane [CDC 2025]
Authors: Taekyung Kim, Randal W. Beard, Dimitra Panagou
Safe Navigation in Uncertain Crowded Environments Using Risk Adaptive CVaR Barrier Functions [IROS 2025]
Authors: Xinyi Wang, Taekyung Kim, Bardh Hoxha, Georgios Fainekos, Dimitra Panagou
Certifiably-Correct Mapping for Safe Navigation Despite Odometry Drift [RSS 2025]
Authors: Devansh R. Agrawal, Taekyung Kim, Rajiv Govindjee, Trushant Adeshara, Jiangbo Yu, Anurekha Ravikumar, Dimitra Panagou
Safe Navigation in Uncertain Crowded Environments Using Risk Adaptive CVaR Barrier Functions [ICRA 2025 Workshop on Robot Safety Under Uncertainty from Intangible Specifications]
Authors: Xinyi Wang, Taekyung Kim, Bardh Hoxha, Georgios Fainekos, Dimitra Panagou
Learning to Refine Input Constrained Control Barrier Functions via Uncertainty-Aware Online Parameter Adaptation [ICRA 2025]
Authors: Taekyung Kim, Robin Inho Kee, Dimitra Panagou
METAVerse: Meta-Learning Traversability Cost Map for Off-Road Navigation [IROS 2024]
Authors: Junwon Seo, Taekyung Kim, Seongyong Ahn, Kiho Kwak
Bridging Active Exploration and Uncertainty-Aware Deployment Using Probabilistic Ensemble Neural Network Dynamics [RSS 2023]
Authors: Taekyung Kim*, Jungwi Mun*, Junwon Seo, Beomsu Kim, Seongil Hong
Safe Navigation in Unstructured Environments by Minimizing Uncertainty in Control and Perception [RSS 2023 Workshop on Inference and Decision Making for Autonomous Vehicles (IDMAV)]
Authors: Junwon Seo, Jungwi Mun, Taekyung Kim
Physics Embedded Neural Network Vehicle Model and Applications in Risk-Aware Autonomous Driving Using Latent Features [IROS 2022]
Authors: Taekyung Kim*, Hojin Lee*, Wonsuk Lee

Selected Conference Posters and Presentations

Convex Optimization based Robust Optimal Control for Autonomous Vehicle [Institute of Control, Robotics and Systems (ICROS) 2022] Best Paper Award (Top 2.17 %)
Authors: Seongil Hong, Gyuhyun Park, Taekyung Kim, Jungwi Mun
Trajectory Planning for Autonomous Driving with Path Integral Control Using Pre-optimized Prior [Asian Control Conference (ASCC) 2022]
Authors: Yongjae Kim, Wonsuk Lee, Taekyung Kim, Jungwi Mun

Works Under Review

BR-MPPI: Barrier Rate guided MPPI for Enforcing Multiple Inequality Constraints with Learned Signed Distance Field [2025]
Authors: Hardik Parwana, Taekyung Kim, Kehan Long, Bardh Hoxha, Hideki Okamoto, Georgios Fainekos, Dimitra Panagou
Safe Model Predictive Path Integral with Signal Temporal Logic [2026]
Authors: Yiqi Zhao, Taekyung Kim, Hideki Okamoto, Bardh Hoxha, Jyotirmoy V. Deshmukh, Lars Lindemann, Georgios Fainekos
Policy Library CBF: Finite-Horizon Safety at Runtime via Parallel Rollouts [2026]
Authors: Taekyung Kim, Hideki Okamoto, Bardh Hoxha, Georgios Fainekos, Dimitra Panagou
Is Your Safe Controller Actually Safe? A Critical Review of CBF Tautologies and Hidden Assumptions [2026]
Authors: Taekyung Kim
Backup-Based Safety Filters: A Comparative Review of Backup CBF, Model Predictive Shielding, and gatekeeper [2026]
Authors: Taekyung Kim, Aswin D. Menon, Akshunn Trivedi, Dimitra Panagou
Reinforcement Learning for Risk Adaptation via Differentiable CVaR Barrier Functions [2026]
Authors: Xinyi Wang, Taekyung Kim, Bardh Hoxha, Georgios Fainekos, Dimitra Panagou
Distributionally Robust Safety Under Arbitrary Uncertainties: A Safety Filtering Approach [2026]
Authors: Daniel M. Cherenson*, Haejoon Lee*, Taekyung Kim, Dimitra Panagou
Learning to Adapt Control Barrier Functions Under Epistemic and Aleatoric Uncertainty [2026]
Authors: Taekyung Kim, Robin Inho Kee, Dimitra Panagou

Research Experience

University of Michigan Graduate Student Research Assistant
2023.08 - Present
Toyota Research Institute of North America Research Resident
2025.05 - 2025.08
Agency for Defense Development Full-time Researcher
2020.06 - 2023.05
Research Officers for National Defense - Republic of Korea Air Force First Lieutenant
2020.06 - 2023.05
Undergraduate Group Research Program Senior Student
2019.03 - 2020.02
Undergraduate Group Research Program Senior Student
2018.03 - 2019.02

Professional Experience

NVIDIA Deep Learning Institute (DLI) NVIDIA Jetson AI Ambassador
2022.10 - 2023.10
Safe Pass Inc. Co-Founder & CTO
2021.03 - Present
Sonnet.AI Associate Research Intern
2019.05 - 2019.10
Oasys Story Software Engineer
2018.09 - 2020.04

Selected Awards & Honors

Chief of Staff of the Republic of Korea Air Force Honors
2020.09
 National Scholarship Student (Science and Engineering)
2018.03 - 2020.02
1st Place - DGIST Best Research Awards
2020.01
 Talent Award of Korea
2019.12
1st Place - SOSCON (Samsung) 2019 Robot Open Source Lab
2019.10
4th Place - 2019 International Student Green Car Competition
2019.09
1st Place - DGIST Best Research Awards
2019.01
1st Place - SOSCON (Samsung) 2018 Robot Cleaner Autonomous Path Planning Algorithm Hackathon
2018.10
2018 International Student Green Car Competition
2018.05
4th Place - International World Robot Olympiad (WRO Final) in Jakarta, Indonesia
2013.05

Skills & Tools

Languages & Packages
•
Python
•
C++
•
PyTorch
•
Jax
•
ROS & ROS 2
•
Nvidia Isaac
•
OpenCV
Technical Skills
•
Certified Drone Pilot
•
IPG CarMaker
•
Nvidia Jetson
•
Docker
•
GIT
•
Linux
•
Premiere Pro & Final Cut

Patents

Systems and Methods for Articulated-Vehicle Global Trajectory Planning US Patent
2025.11.24
System and Method for Alleviating Uncertainty Handling in Dynamics Learning Model Using Neural Network KR Patent
2023.12.18
Physics Embedded Neural Network Dynamics Model Structure of Autonomous Vehicle, Awareness of Hazardous Driving Situation and Stable Driving Methodology Using Latent Variables in the Model Hidden Layer KR Patent
2023.12.13
Control Framework of Model Predictive Control and Adaptive Tracking Using Shared Neural Network Dynamics Model KR Patent
2022.09.15
System for Providing Real-Time Vision Recognition Based SAFE PASS Service KR Patent
2022.07.20

Academic Service

ICRA 2025 Workshop on Robot Safety Under Uncertainty from Intangible Specifications
Program Committee
2025.05

Review Service

CDC 2026 (x2), IROS 2026 (x3), T-RO 2026 (x2), ICCPS 2026, ECC 2026, ICRA 2026 (x2), T-RO 2025 (x4), CDC 2025, ICRA Workshop 2025 (x2), IROS 2025 (x3), RA-L 2025 (x2), ACC 2025, ICRA 2025, SII 2025, RA-L 2024, T-RO 2024 (x3), IROS 2024, ICRA 2023 (x2), IROS 2022

Contact

•
E-mail : {firstname}@umich.edu
Publications