Daiki Masumoto

Papers

Total Citations

H-Index

About

Daiki Masumoto’s research focuses on advancing robotic perception through intelligent sensor fusion and neural network architectures. His work addresses a fundamental challenge in robotics: how to transform ambiguous sensory data into reliable internal representations for goal-directed action. Masumoto proposed a sensory information processing system using neural networks (2002, 8 citations), offering an architecture that resolves uncertainty when sensed data cannot uniquely determine a robot’s internal state. He further developed a sensor selection method based on fuzzy inference for sensor fusion (2005, 7 citations), enabling robots to dynamically choose the most reliable sensors from multiple inputs to obtain more accurate and immeasurable environmental information. Though his citation counts are modest, Masumoto’s contributions are notable for pioneering early approaches to adaptive sensor fusion—a foundation for modern autonomous systems. His work demonstrates how fuzzy logic can enhance decision-making in multi-sensor environments, influencing subsequent research in robust robotic perception. For students exploring sensor integration and neural processing, Masumoto’s papers offer foundational insights into building resilient, context-aware robotic systems.