Behavior Learning
Research Team

Research Summary

Recent dialogue systems using AI systems, such as smart speakers, are able to provide various functions such as information retrieval based on voice commands. In this context, interactive robots are expected to be a system that can coexist with humans, but the communication mechanism that utilizes various modalities such as gestures and eye gaze as humans do has not yet been realized. Our team aims to develop a robot that can interact with humans as humans do in daily life by measuring human behaviors during the dialogue and constructing a deep generative model of the interaction behaviors.

Main Research Fields
  • Human robot interaction
  • Machine learning
Keywords
  • Reinforcement learning
  • Human robot interaction
  • Communicative robot
  • Motion generation
  • Intrinsic motivation
Research theme
  • Reinforcement learning of robots interacting with humans.
  • Automatic generation of human-like and natural motion of communicative robot based on human cognition.
  • Interactive robot operation mechanism through communication.
  • Autonomous robots operating in everyday environments.

Yutaka Nakamura

Yutaka Nakamura

History

2004
Nara institute of science and technology
2006
Osaka University
2020
RIKEN

Members

Yuya Okadome
Research Scientist
Huthaifa Ahmad
Research Scientist
Yusuke Nishimura
Research Part-time Worker I

Former member

Shota Takashiro
Administrative Part-time Worker II (2021/12-2022/03)

Selected Publications

  1. Yusuke Nishimura, Yutaka Nakamura, and HiroshiIshiguro.:
    "Human interaction behavior modeling using Generative Adversarial Networks"
    Neural Networks, 132, pp.521—531 (2020)
  2. Mofei Li, Yutaka Nakamura, and Hiroshi Ishiguro.:
    "Choice modeling using dot-product attention mechanism"
    Artificial Life and Robotics (2020)
  3. Huthaifa Ahmad, Yoshihiro Nakata, Yutaka Nakamura, Hiroshi Ishiguro.:
    "PedestriANS: a bipedal robot with adaptive morphology"
    Adaptive behavior (2020)
  4. 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)
  5. Kenta Maeda, Yoshihiro Nakata, Yutaka Nakamura, Hiroshi Ishiguro.:
    "Effect of the cervical structure on the operability of teleoperated humanoid head"
    Artificial Life and Robotics, 22(4), pp 497-–502 (2017)
  6. Yuya Okadome, Yutaka Nakamura, and Hiroshi Ishiguro.:
    "A confidence-based roadmap using Gaussian process regression"
    Autonomous Robots, 41(4) (2017)
  7. Ahmed Qureshi, Yutaka Nakamura, Yuichiro Yoshikawa, Hiroshi Ishiguro.:
    "Show, Attend and Interact: Perceivable Human-Robot Social Interaction through Neural Attention Q-Network"
    2017 IEEE International Conference on Robotics and Automation (ICRA), pp.1639--1645 (2017)
  8. Hideyuki RYU, Yoshihiro Nakata, Yutaka Nakamura, and Hiroshi Ishiguro.:
    "Adaptive Whole-body Dynamics: An Actuator Network System for Orchestrating Multi-joint Movements"
    IEEE Robotics & Automation Magazine, 23(3), pp.85—92 (2016)
  9. Eri Takano, Takenobu Chikaraishi, Yoshio Matsumoto, Yutaka Nakamura, Hiroshi Ishiguro, and Kazuomi Sugamoto.:
    "Psychological effects on interpersonal communication by bystander android using motions based on human-like needs"
    IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp.3721—3726 (2009)
  10. 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)

Links

Contact Information

yutaka.nakamura [at] riken.jp