Yutaka Nakamura

Yutaka Nakamura

Auto-generated profile, based on publicly available information

Yutaka Nakamura

RIKEN

Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 May 2012
Verified
Conference Paper
Closed access
YNYoshihiro Nakata
Yoshihiro Nakata
AIAtsuhiro Ide
Atsuhiro Ide
YNYutaka Nakamura
Yutaka Nakamura
KHKatsuhiro Hirata
Katsuhiro Hirata
Hiroshi IshiguroHiroshi Ishiguro
Hiroshi Ishiguro
The compliance of muscles with external forces and the structural stability given by biarticular muscles are important features of animals to realize dynamic whole body motions such as running and hopping in various environments. For this reason, we have been studying an electromagnetic linear actuator. This actuator can emulate the behavior of a human muscle such as the spring-damper characteristics by quick control of the output force (i.e. impedance control) and it is expected to be used as an artificial muscle. In this paper, we develop a monopedal robot possessing bi- and mono-articular muscles implemented by linear actuators. Thanks to the biarticular muscle, the bouncing direction of the robot can be controlled by changing the stiffness ellipse at the endpoint (i.e. foot) of the robot. We confirm that the bouncing direction of the robot can be controlled and hopping can be achieved by changing the stiffness ellipse.

14 April 2023 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
ZCZhichao Chen
Zhichao Chen
YNYutaka Nakamura
Yutaka Nakamura
Hiroshi IshiguroHiroshi Ishiguro
Hiroshi Ishiguro
Robots can tackle human–robot interaction (HRI) tasks through inverse reinforcement learning (IRL). However, offline IRL agents' performance is upper-bounded by experts. Limited demonstration fails to provide an overall picture of the environment, especially in real-world applications. To further enhance IRL's performance, we implement a cross-modal inverse reinforcement learning to reinforcement learning (IRL-to-RL) transition framework for a real-world HRI interaction task, in which a mall receptionist android promotes sanitizer usage. During the 10-day experiment, the android develops a more proactive and effective strategy than the human expert. Furthermore, we explore four decay modes of prior knowledge supervision and suggest a preferable pattern for practical use. Our results demonstrate the feasibility of the framework to assist robots in switching to diverse modalities, learning incrementally with a sparse reward function, and eventually outperforming the human expert. We anticipate our framework to inspire more IRL-to-better learning paradigms, facilitating robots to outcompete teachers in more real-world HRI applications.

3 June 2022 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
ZCZhichao Chen
Zhichao Chen
YNYutaka Nakamura
Yutaka Nakamura
HIHiroshi Ishiguro
Hiroshi Ishiguro
For human-robot interaction (HRI), it is difficult to hand-craft all the rules for robots owing to diverse situations. Therefore, inverse reinforcement learning (IRL) is a potential solution that helps transfer human knowledge about interactions to robots. However, the feasibility of practically using IRL for HRI remains unknown. Here, we demonstrate a practical HRI application of IRL. An android was trained using IRL and acted as a receptionist to encourage visitors to practice hand hygiene in a shopping mall. We found that android learning through IRL has a competitive ability to a well-trained human operator on the reception task. Furthermore, we found that the android maintained high performance regardless of customer traffic. Our results demonstrate the potential of IRL in advancing the social HRI field. We anticipate that our work will be a starting point for using IRL in future HRI applications.

12 August 2008
Verified
Book Chapter
Closed access
PDF file
IFIppei Fukuyori
Ippei Fukuyori
YNYutaka Nakamura
Yutaka Nakamura
YMYoshio Matsumoto
Yoshio Matsumoto
Hiroshi IshiguroHiroshi Ishiguro
Hiroshi Ishiguro

17 July 2024 in IEEE Access
Verified
Journal Article
Open access
YOYuya Okadome
Yuya Okadome
YNYutaka Nakamura
Yutaka Nakamura
Systems in the real world often consist of multiple subsystems interacting with each other, for example, the musculoskeletal system or human-human interaction. The measurement of temporal changes in these systems involves a multidimensional time series. This study introduces a novel framework for extracting features from multidimensional time series data with a group structure using self-supervised learning techniques. Specifically, we use a “lag operation,” which is a temporal shifting operation applied to the features of a certain group. We propose a self-supervised learning method for a neural network model that uses the data automatically generated by the lag operation and its corresponding operation labels to capture and quantify the interaction between groups. Upon completion of the training process, the representation space is obtained with the expectation that it will capture timing-dependent features within its boundaries. We define and calculate the interaction score, R-score, on the obtained space. To validate our approach, we apply the proposed methodology to an artificial oscillator and approximately 4 hours of conversational data to evaluate the R-score properties. From the results of the artificial data, the R-score increases when the connection between the groups is large. From the high R-score region of the representation space of the conversation data, we extract the data that contain social behaviors such as “eye contact,” “turn-taking,” and “smiling,” which are related to the interaction between the participants. The experimental results suggest that the proposed method can obtain a representation space for time series data with a group structure.

15 November 2024
Verified
Book Chapter
Open access
PDF file
Hiroshi IshiguroHiroshi Ishiguro
Hiroshi Ishiguro
KOKohei Ogawa
Kohei Ogawa
YNYoshihiro Nakata
Yoshihiro Nakata
MNMizuki Nakajima
Mizuki Nakajima
MSMasahiro Shiomi
Masahiro Shiomi
YNYutaka Nakamura
Yutaka Nakamura
Cybernetic Avatars (CAs) are controlled by an operator through an interface that communicates movements, voice, or the intent of action. The operator can use the CA to perform activities remotely. In other words, the CA is the operator’s alter ego. Therefore, the CA should have humanlike presence and lifelikeness. This chapter introduces related research, focusing on the development of a humanlike and life-like CA along with its interface technology.