Keiji YAMAKAWA
Papers
1
Total Citations
3
H-Index
1
About
Keiji Yamakawa is a pioneering figure in the application of neural networks to robotics, with a focused career dedicated to enhancing the precision and reliability of robotic manipulators. His key research areas span intelligent control systems, error compensation, and the integration of machine learning into mechanical automation. Yamakawa’s most notable contribution is his seminal 1993 work on using neural networks to correct position and orientation errors in robot manipulators. This approach addressed a critical challenge in robotics: the inaccuracies arising from modeling errors or improper setup. By enabling a neural network to learn and compensate for these deviations, he provided a practical method to refine robot controller inputs, significantly improving operational accuracy. While his direct citation count for this foundational paper stands at 3, its conceptual influence is felt in subsequent research on adaptive control and sensorless calibration. Yamakawa’s work represents an early, insightful bridge between neural computation and precision engineering, offering a lasting framework for researchers exploring intelligent error mitigation in automated systems.
Research Focus
Key Achievements
Top Papers
- 1