Max Robotics — Global Service Robot Directory + US Certification

About

Ryo Hachiuma is a researcher at the forefront of multimodal perception and robotic intelligence, whose work bridges audio-visual learning, human-robot interaction, and surgical data science. His core contributions lie in developing self-supervised and hybrid approaches that enable machines to understand complex physical environments through complementary sensory inputs. Hachiuma’s highly cited work on audio-visual hybrid methods for filling mass estimation (10 citations) and the CORSMAL benchmark (9 citations) addresses a critical challenge in safe human-to-robot handovers: contactlessly estimating container weight and content properties despite variations in opacity, material, and shape. He has also pioneered self-supervised audio-visual feature learning for incremental terrain type clustering (8 citations), demonstrating how multi-modal data from RGB cameras, depth sensors, and microphones can be leveraged for robust environmental understanding. Notably, Hachiuma contributed to the Intuitive Surgical SurgToolLoc and SurgVU challenges (6 citations), advancing machine learning models for robotic-assisted surgery. His recent work on verbalized layers-to-interactions (VLsI) for vision-language models (3 citations) explores efficient scaling of open-source VLMs, while his earlier research on 6-DoF pose estimation of stacked objects (2 citations) supports warehouse automation. With a growing citation impact and a focus on real-world applications, Hachiuma’s research continues to shape the future of autonomous systems and surgical robotics.