Kazushi Yoshida

Papers

Total Citations

H-Index

About

Kazushi Yoshida is a robotics and machine learning researcher whose work bridges visual feedback control and deep learning for industrial automation. His primary research areas include convolutional neural networks (CNNs), transfer learning, and robotic manipulation systems. Yoshida’s most cited work, “Pick and Place Robot Using Visual Feedback Control and Transfer Learning-Based CNN” (2020, 13 citations), introduces a novel approach that integrates CNN-based image recognition with transfer learning to enhance the precision and adaptability of pick-and-place robots. This contribution is significant for enabling robots to recognize and manipulate objects in unstructured environments without extensive retraining, reducing setup time and improving efficiency in manufacturing. By leveraging deep neural networks (DNNs) with four or more layers, Yoshida demonstrates how advanced machine learning can be practically applied to defect inspection and real-time visual servoing. His work has been cited by researchers exploring automated quality control and adaptive robotics, highlighting its relevance to Industry 4.0. Yoshida’s research stands out for its focus on making deep learning accessible for real-world robotic tasks, offering a scalable solution for industries seeking to integrate intelligent automation.