Jungseock Joo
Papers
8
Total Citations
112
H-Index
6
About
Jungseock Joo is a researcher whose work sits at the dynamic intersection of robotics, computer vision, and human-robot collaboration, with a particular focus on the manipulation and understanding of deformable objects. His most significant contributions address one of robotics' most persistent challenges: enabling machines to reliably handle flexible, nonlinear materials such as cables, rods, and paper in real-world environments. Joo's highly cited work includes the development of fully implicit methods for robust frictional contact handling in elastic rods (25 citations) and the mBEST algorithm, a realtime detection framework for deformable linear objects that leverages minimal bending energy skeleton traversals (25 citations). His Sim2Real research demonstrates a compelling pipeline for transferring physics-based neural controllers from simulation to physical robotic deployment, advancing the practicality of deformable object manipulation at scale. His investigations into human-robot collaboration are equally notable, encompassing natural gesture-based communication for embodied navigation agents and preemptive motion planning for seamless human-to-robot handovers. Collectively accumulating over 110 citations, Joo's body of work reflects a sophisticated synthesis of computational mechanics, machine learning, and interactive robotics — making his research essential reading for scholars pursuing intelligent, physically aware robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6Preemptive Motion Planning for Human-to-Robot Indirect Placement Handovers10 citations · 2022
- 7
- 8