Nobukatsu Sugiyama
Papers
2
Total Citations
48
H-Index
2
About
Nobukatsu Sugiyama is a leading researcher in intelligent robotics and automated visual inspection, with a focus on solving critical industrial challenges. His work centers on two key areas: vision-guided robotic manipulation and advanced defect detection. In his seminal 2020 paper on depth image–based deep learning for grasp planning, Sugiyama addressed the difficult problem of bin-picking textureless, planar-faced objects—a common task in warehouse automation. This work, which has garnered 45 citations, introduced a general system that eliminates the need for complex feature extraction and goal image preparation, significantly streamlining robotic picking operations. More recently, Sugiyama has pioneered innovative inspection techniques to combat labor shortages in Japan’s manufacturing sector. His 2023 development of the One-shot BRDF (Bidirectional Reflectance Distribution Function) imaging system, deployed using a 6-DOF robot arm, enables rapid, high-sensitivity detection of micro-defects on curved surfaces—a task previously requiring multiple imaging passes. This breakthrough promises to revolutionize quality control in industries where even microscopic flaws can lead to product failure. Sugiyama’s research directly addresses real-world industrial needs, combining deep learning, robotics, and optical engineering to create practical, deployable solutions.
Research Focus
Key Achievements
Top Papers
- 1
- 2