Tatsuro Yamada
Papers
10
Total Citations
141
H-Index
5
About
Tatsuro Yamada is a leading researcher at the intersection of cognitive robotics, human-robot interaction, and deep learning, with a focus on bridging the gap between language and robot behavior. His major contributions center on developing neural network architectures that enable robots to dynamically integrate linguistic instructions with physical actions, allowing for bidirectional translation between natural language and motor sequences. Yamada’s most influential work, “Paired Recurrent Autoencoders for Bidirectional Translation Between Robot Actions and Linguistic Descriptions” (2018, 64 citations), introduced a novel framework that maps action sequences to language and vice versa, a key step toward more intuitive human-robot collaboration. His 2016 paper on dynamical integration of language and behavior (40 citations) further advanced this field by enabling robots to autonomously apply learned mappings in real-time interactive tasks. Yamada has also explored predictive learning inspired by cognitive development, as seen in his 2023 work on deep predictive learning for motion generation (6 citations), and has investigated how recurrent neural networks can represent compositional logic in language (2017, 11 citations). His research, which spans from foundational machine learning to neurorobotics experiments modeling infant-caregiver interactions, has garnered over 140 citations, establishing him as a key figure in cognitive robotics and language-guided behavior learning.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7Machine Learning for Cognitive Robotics3 citations · 2022
- 8
- 9
- 10Parrot-like speaking using optimal vector quantization2 citations · 2002