Max Robotics — Global Service Robot Directory + US Certification

About

Toshio Ogiso is a pioneering researcher in robotics, with a focus on neural network architectures, robot calibration, and motion optimization. His most influential work, "Partitioned neural network architecture for inverse kinematic calculation of a 6 DOF robot manipulator" (1991, 18 citations), introduced a novel parallel neural network design that significantly improved learning accuracy for complex robotic tasks. This partitioned network, featuring a preprocessing layer and dedicated neuron modules, laid groundwork for efficient inverse kinematics solutions in high-precision applications. Ogiso also advanced robot calibration through his 2002 study on direct drive robots, developing a software-based method that used stiffness models to correct positioning errors from static deflection, enhancing SCARA robot accuracy. His 1994 work on optimizing driving patterns with indexed sinusoidal curves further contributed to reducing motion times in mechatronic systems. While his citation counts reflect a focused, technical audience, Ogiso's contributions to neural network-based robotics and calibration techniques have informed subsequent research in industrial automation and robot control, demonstrating a career dedicated to solving fundamental challenges in robotic precision and efficiency.