Max Robotics — Global Service Robot Directory + US Certification

About

Hyogo Hiruma is an emerging robotics researcher whose work sits at the intersection of deep learning, visual attention, and intelligent robot motion generation. His research primarily focuses on developing biologically inspired visual attention mechanisms that enable robots to adaptively perceive and interact with complex environments — capabilities that closely mirror human cognitive processes. His most cited work, "Deep Active Visual Attention for Real-Time Robot Motion Generation" (2022, 12 citations), introduced a framework through which robots can dynamically modify their perceptual focus, giving rise to emergent behaviors such as tool-body assimilation and adaptive tool use. Hiruma has further advanced robot perception by tackling challenging scenarios including transparent object grasping through stereo disparity learning and attention mechanisms, addressing a persistent limitation of conventional depth sensors. His investigations into the interplay between top-down and bottom-up visual attention processes reflect a commitment to understanding how structured, human-like attention develops in robotic systems over time. More recently, his work on uncertainty-driven foresight prediction pushes imitation learning beyond idealized success demonstrations, equipping robots to handle ambiguous real-world conditions. Collectively, Hiruma's contributions represent a meaningful effort to bridge neuroscience-inspired perception with practical, real-time robotic intelligence.