Tetsuya Ogata
Waseda University, Ritsumeikan University, Kyoto University, Kyoto College of Graduate Studies for Informatics, National Institute of Advanced Industrial Science and Technology, Suzuki (Japan), Kyushu Institute of Technology, RIKEN Center for Brain Science, Kyoto University of Education, Fujitsu (Japan), Institut national de recherche en sciences et technologies du numérique
Papers
240
Total Citations
3,876
H-Index
31
About
Tetsuya Ogata is a pioneering researcher at the intersection of deep learning, robotics, and cognitive science, whose work has fundamentally advanced how robots perceive, learn, and interact with the world. His research spans humanoid robot control, multimodal sensory integration, robot audition, and the computational grounding of language in physical experience. Ogata's most influential contributions include developing deep neural network frameworks that enable robots to perform complex manipulation tasks — most notably a humanoid capable of repeatedly folding garments on production lines (235 citations) — and multimodal integration systems that fuse vision, sound, and touch to improve robotic perception (196 citations). His survey on symbol emergence in robotics (153 citations) has become a landmark reference for researchers exploring how machines can autonomously acquire language-like representations through embodied interaction. Beyond manipulation, Ogata has made significant strides in robot audition, including deep learning-based sound source localization (129 citations) and microphone array-based speech recognition (69 citations). His work on bidirectional translation between robot actions and linguistic descriptions reflects a sustained commitment to bridging motor behavior and language. With contributions spanning wearable robotics hardware to reinforcement learning for whole-body control, Ogata's career represents a remarkably broad and enduring influence on embodied artificial intelligence.
Research Focus
Key Achievements
Top Papers
- 1Repeatable Folding Task by Humanoid Robot Worker Using Deep Learning235 citations · 2016
- 2Multimodal integration learning of robot behavior using deep neural networks196 citations · 2014
- 3Symbol emergence in robotics: a survey153 citations · 2016
- 4Sound Source Localization Using Deep Learning Models129 citations · 2017
- 5Tactile object recognition using deep learning and dropout111 citations · 2014
- 6
- 7
- 8
- 9
- 10