Dongryung Lee — accepted AI-conference papers

2025

A low-cost and lightweight 6 DoF bimanual arm for dynamic and contact-rich manipulation

Jaehyung Kim, Jiho Kim, Dongryung Lee, Yujin Jang, Beomjoon Kim

RSS 2025poster

Dynamic and contact-rich object manipulation, such as striking, snatching, or hammering, remains challenging for robotic systems due to hardware limitations. Most existing robots are constrained by high-inertia design, limited compliance, and reliance on expensive torque sensors. To address this, we…

Cited by 0 PDF ↗Scholar ↗

2023

Preference learning for guiding the tree search in continuous POMDPs

Jiyong Ahn, Sanghyeon Son, Dongryung Lee, Jisu Han, Dongwon Son, Beomjoon Kim

CoRL 2023poster

A robot operating in a partially observable environment must perform sensing actions to achieve a goal, such as clearing the objects in front of a shelf to better localize a target object at the back, and estimate its shape for grasping. A POMDP is a principled framework for enabling robots to perfo…

Cited by 0 Source ↗Scholar ↗