Papers
14
Total Citations
290
H-Index
6
About
Kyoobin Lee is a robotics and computer vision researcher whose work spans two distinct but complementary domains: assistive robotics for people with disabilities and intelligent robotic perception for manipulation tasks. Beginning in the early 2000s, Lee made foundational contributions to human-friendly interfaces for wheelchair and robotic manipulator control systems, developing wearable devices using optical fiber curvature sensors and intuitive motion-based controls to empower individuals with spinal cord injuries. His landmark KARES II rehabilitation robotic system (2004, 89 citations) remains among his most influential achievements, demonstrating seamless human-machine interaction for handicapped users. In more recent years, Lee has pivoted toward cutting-edge deep learning for robotic perception, tackling challenges such as amodal instance segmentation of unseen objects in cluttered environments (2022, 66 citations), food instance segmentation using synthetic data (2021, 34 citations), and novel object placement via large-scale simulation. His 2025 work, GraspSAM, innovatively extends Meta's Segment Anything Model for grasp detection, reflecting his commitment to advancing prompt-driven robotic manipulation. Collectively, Lee's research bridges compassionate assistive technology with sophisticated robot intelligence, making him a versatile and impactful figure across both humanitarian and industrial robotics communities.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4Deep Learning based Food Instance Segmentation using Synthetic Data34 citations · 2021
- 5
- 6
- 7GraspSAM: When Segment Anything Model Meets Grasp Detection6 citations · 2025
- 8
- 9Learning to Place Unseen Objects Stably Using a Large-Scale Simulation4 citations · 2024
- 10