Takashi Sumiyoshi

Papers

Total Citations

H-Index

About

Takashi Sumiyoshi is a leading researcher in human-robot interaction, with a focus on enabling service robots to operate intuitively and proactively in real-world environments. His key research areas include acoustic signal processing for robot audition and anticipatory human-robot interaction. Sumiyoshi’s major contributions center on robust direction-of-arrival (DOA) estimation for human speech, critical for robots operating in noisy, dynamic settings. In his highly cited 2009 paper (11 citations), he introduced two innovative DOA methods—the modified delay-and-sum beamformer based on sparseness (MDSBF) and stepwise phase difference restoration (SPIRE)—which leverage the sparseness of human speech to accurately estimate both azimuth and elevation, enabling human symbiotic robots to locate speakers more reliably. Building on this, his 2020 work (6 citations) advanced proactive service robotics by developing methods for anticipating the start of user interaction “in the wild,” allowing robots to initiate service before being addressed, rather than reacting passively. This shift from reactive to anticipatory behavior is a notable achievement, enhancing the naturalness and efficiency of human-robot collaboration. Sumiyoshi’s research continues to shape the design of socially aware robots that can seamlessly integrate into everyday human spaces.