|
Changwoo Yoo Hi there! I'm an M.S. student at KAIST AI, advised by Prof. Kee-Eung Kim. My goal is to develop mathematically grounded algorithms that enable robots to improve themselves. Toward this goal, I am currently focusing on scaling reinforcement learning algorithms. |
|
Publications(* Equal contribution) |
|
EgoDelta: From Egocentric Scene Change to 3D Attachment Targets for Agricultural Manipulation
Namho Koh*, Junyoung Jang*, Chaeyoung Oh, Changwoo Yoo, Jongho Lee, Kee-Eung Kim WACV, 2027 project page Recovering 3D attachment targets from scene changes in egocentric human demonstrations to generate robot trajectories for harvesting and deleafing. |
|
Learning Social Navigation from Positive and Negative Demonstrations and Rule-Based Specifications
Chanwoo Kim, Jihwan Yoon, Hyeonseong Kim, Taemoon Jeong, Changwoo Yoo, Seungbeen Lee, Soohwan Byeon, Hoon Chung, Matthew Pan, Jean Oh, Kyungjae Lee, Sungjoon Choi ICRA, 2026 project page / arXiv Learning a density-based reward from positive and negative demonstrations augmented with rule-based safety constraints to balance adaptability and reliability. |
|
|