RIKEN Information R&D and Strategy Headquarters Behavior Learning Research Team
Team Leader: Yutaka Nakamura (D.Eng.)
While humans engage in dialogue, they use not only language but also various modalities such as gestures. This team is measuring the participants' behaviors interacting with each other and modeling them using deep learning. We are also developing a framework for motion control of communication robots using the models obtained through learning. We are working on the following specific research topics:
- Reinforcement learning for human robot interaction
- Deep generative model for the behaviors during dialogue
- Development of a control framework for communication robot
Main Research Fields
- Complex Systems
Related Research Fields
- Interdisciplinary Science & Engineering
- Intelligent robotics
- Intelligent informatics
- Soft computing
- Human robot interaction
- Generative model
- Reinforcement learning
- Motion generation
- Communication robot
Papers with an asterisk(*) are based on research conducted outside of RIKEN.
Yuya Okadome, Kenshiro Ata, Hiroshi Ishiguro, Yutaka Nakamura.:
"Self-supervised Learning Method for Behavior Prediction during Dialogue Based on Temporal Consistency,"
Transactions of the Japanese Society for Artificial Intelligence (2022) Volume 37 Issue 6 Pages B-M43_1-13
Zhichao Chen, Nakamura Yutaka, Hiroshi Ishiguro.:
"Android As a Receptionist in a Shopping Mall Using Inverse Reinforcement Learning"
IEEE/RSJ International Conference on Intelligent Robots and Systems (2022)
Naoki Ise, Yoshihiro Nakata, Yutaka Nakamura, Hiroshi Ishiguro.:
"Gaze motion and subjective workload assessment while performing a task walking hand in hand with a mobile robot"
International Journal of Social Robotics (2022)
Huthaifa Ahmad, Yutaka Nakamura.:
"A robot that is always ready for safe physical interactions"
Interdisciplinary Conference on Mechanics, Computers and Electrics (ICMECE 2022)
Satoshi Yagi, Yoshihiro Nakata, Yutaka Nakamura, Hiroshi Ishiguro.:
"Can an android’s posture and movement discriminate against the ambiguous emotion perceived from its facial expressions?"
Plos ONE (2021)
Yusuke Nishimura, Yutaka Nakamura, and Hiroshi Ishiguro.:
"Human interaction behavior modeling using Generative Adversarial Networks"
Neural Networks, 132, pp.521—531 (2020)
*Mofei Li, Yutaka Nakamura, and Hiroshi Ishiguro.:
"Choice modeling using dot-product attention mechanism"
Artificial Life and Robotics (2020)
*Ahmed Hussain Qureshi, Yutaka Nakamura, Yuichiro Yoshikawa, and Hiroshi Ishiguro.:
"Intrinsically motivated reinforcement learning for human–robot interaction in the real-world"
Neural Networks, 107, pp. 23—33 (2018)
*Yuya Okadome, Yutaka Nakamura, and Hiroshi Ishiguro.:
"A confidence-based roadmap using Gaussian process regressio"
Autonomous Robots, 41(4) (2017)
*Yutaka Nakamura, Takeshi Mori, Masa-aki Sato, and Shin Ishii.:
"Reinforcement learning for a biped robot based on a CPG-actor-critic method"
Neural Networks, 20(6), pp.723-735 (2007)
- Yutaka Nakamura
- Team Leader
- Huthaifa Abedallah Mohammad Ahmad
- Research Scientist
- Yuya Okadome
- Research Scientist
- Zhichao Chen
- Technical Staff I
|Seeking a Research Scientist or Postdoctoral Researcher (W23019)||Open until filled|
3rd Floor, Advanced Telecommunications Research Institute International
2-2-2 Hikaridai Seika-cho, Sorakugun, Kyoto
619-0288 Japan (Kansai Science City)
Email: yutaka.nakamura [at] riken.jp