Naoyuki Ishibashi

Papers

Total Citations

H-Index

About

Naoyuki Ishibashi has made focused and impactful contributions to the field of robotics, particularly in the domain of intelligent control systems for industrial manipulators. His key research areas center on the application of recurrent neural networks (RNNs) and advanced optimization techniques for robot dynamics and positioning control. Ishibashi’s most notable work, “Learning of inverse-dynamics for SCARA robot” (2011), with 6 citations, introduces a novel approach where a recurrent neural network learns the inverse dynamics of a SCARA robot using the simultaneous perturbation stochastic approximation (SPSA) method. This contribution is significant for enabling more adaptive and computationally efficient control without requiring an explicit analytical model of the robot’s complex dynamics. By demonstrating that neural networks can effectively approximate and control nonlinear robotic systems through online learning, Ishibashi’s research bridges the gap between theoretical machine learning and practical automation. His work is particularly relevant for students and researchers interested in neural control, adaptive robotics, and the application of optimization algorithms to real-world mechatronic systems, offering a foundational approach to developing smarter, more autonomous industrial robots.