Yuki Nakai

Kyoto Institute of Technology, Nagoya University

Papers

Total Citations

H-Index

About

Yuki Nakai is a robotics researcher whose work spans intelligent control systems, neural network-based learning, and autonomous robot motion planning. Nakai's most significant contributions lie in developing novel approaches to one of robotics' fundamental challenges: the inverse kinematics problem. His 2002 papers introduced an innovative neural network learning method capable of simultaneously representing both positional and velocity relationships between task space and joint space coordinates in robot manipulators — a meaningful advancement over conventional analytical approaches. The more influential of these works has accumulated 23 citations, reflecting its lasting relevance to the robotics and machine learning communities. More recently, Nakai extended his research into dynamic, real-time robot applications, as demonstrated by his 2016 work on ball trajectory planning for table tennis robots. This study applied physical modeling to plan precise ball trajectories through the serving task, highlighting his ability to bridge theoretical frameworks with practical robotic challenges. Though his citation counts are modest, his research addresses enduring problems in robotic manipulation and autonomous motion planning that remain active areas of inquiry. His career reflects a consistent focus on making robots smarter, more adaptable, and capable of performing complex, dynamic tasks through principled learning and planning strategies.