Hyeok-Joo Chae
Papers
2
Total Citations
4
H-Index
2
About
Hyeok-Joo Chae is a researcher advancing the frontier of autonomous robotics through innovative work in motion planning, control, and environmental perception. His research focuses on two interconnected challenges: enabling robots to learn optimal behaviors from demonstrations and building robust, dynamic 3-D representations of complex surroundings. In his highly cited 2021 paper, Chae introduced a diffusion wavelets-based multiscale framework for inverse optimal control, a novel approach that allows robots to infer cost functions from observed motion in stochastic environments—a critical step toward more intuitive human-robot interaction. This work, which has garnered 2 citations, addresses the computational complexity of planning in large decision spaces with intricate geometry. More recently, in 2023, Chae developed DS-K3DOM, a 3-D dynamic occupancy mapping framework that fuses kernel inference with Dempster-Shafer evidential theory. This method tackles the underexplored problem of representing moving obstacles in three dimensions, providing a principled way to handle uncertainty in sensor data. With 2 citations, this contribution is foundational for safe navigation and manipulation in dynamic, real-world settings. Chae’s work bridges theoretical rigor and practical deployment, making him a rising voice in robotics and autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2