Masayuki Okamoto
Papers
2
Total Citations
162
H-Index
1
About
Masayuki Okamoto is a leading researcher in human–robot interaction and mechatronics education, with a focus on developing intuitive, robust interfaces between humans and machines. His most influential work, “A Hybrid Motion Classification Approach for EMG-Based Human–Robot Interfaces Using Bayesian and Neural Networks” (2009, 161 citations), introduces a task model that leverages Bayesian inference to predict user motion from electromyographic signals. By fusing context-aware Bayesian reasoning with neural network classification, Okamoto’s approach significantly improves the reliability of motion prediction—a critical advancement for controlling prosthetic devices and human-assisting manipulators in real-world settings. This work has become a foundational reference for researchers developing adaptive, bio-signal-driven robotic control systems. Beyond his technical contributions, Okamoto is deeply committed to engineering education. His project on constructing a large-scale humanoid robot as a hands-on learning platform (2014) demonstrates his belief that interdisciplinary collaboration—spanning mechanics, electronics, and information technology—is essential for inspiring the next generation of roboticists. Through this initiative, he has helped students gain practical, integrated skills in robot design and manufacturing. With over 160 citations on his core interface work, Okamoto’s research continues to shape the fields of assistive robotics and human–machine collaboration.
Research Focus
Key Achievements
Top Papers
- 1
- 2