Tae‐Koo Kang
Papers
9
Total Citations
87
H-Index
6
About
Tae‐Koo Kang is a robotics and autonomous systems researcher whose work spans autonomous driving, humanoid robotics, computer vision, and robotic construction automation. With a career stretching from the mid-2000s to the present, Kang has made sustained contributions to intelligent motion planning and perception systems for robots operating in complex, real-world environments. His most cited work (23 citations) introduces an Obstacle-Dependent Gaussian Model Predictive Control framework for autonomous vehicle path planning, elegantly balancing safety and passenger comfort through optimal control integration. This research reflects his broader interest in Gaussian-based potential field methods, also evident in his robot soccer obstacle avoidance work. In computer vision, Kang developed robust visual tracking systems capable of handling motion blur by fusing appearance- and feature-based detection, and pioneered 3D panoramic environment mapping using SURF and SIFT descriptors to enable effective obstacle avoidance in humanoid robots. Earlier in his career, Kang tackled the ambitious challenge of automating steel-frame construction in high-rise buildings through robotic crane systems — work that earned 10 citations and demonstrated his talent for applying robotics to large-scale engineering problems. Across more than 80 cumulative citations, Kang's research consistently bridges theoretical control methods with practical robotic applications.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 53D vision based local obstacle avoidance method for humanoid robot9 citations · 2012
- 6
- 7
- 8
- 9