2P1-D18 Adaptation to Variation of Human Subjective Preference using Communication Robot with IEC

• ENDO Chihiro

  Waseda Univ.

• KOBAYASHI Daizo

  Waseda Univ.

• MATSUMOTO Takeshi

  Waseda Univ.

• SUGA Yuki

  Waseda Univ.

• OGATA Tetsuya

  Kyoto Univ.

• SUGANO Shigeki

  Waseda Univ.

Bibliographic Information

Other Title

• 2P1-D18 IECを用いたコミュニケーションロボットにおける人間の主観変化への適応

Abstract

As the learning function of a communication robot, we are using Interactive Evolutionary Computation (IEC). The IEC is an evolutionary computation where the fitness function is performed by a user, so it is available for the learning of the user's subjective preference. In this paper, we show the adaptability of the IEC to the interaction between various users and a robot. We installed the IEC function into a real robot named WAMOEBA-3. In the experiment, various interactions were shown because we did not tell subjects anything about the robot. However, the robot's motion changed to the behavior the users liked and the fitness values are gradually increased. Therefore, the adaptability of the IEC is confirmed.

Journal

• The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec)

  The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec) 2006 (0), _2P1-D18_1-_2P1-D18_2, 2006

  The Japan Society of Mechanical Engineers

Keywords

• Interactive Evolutionary Computation
• human-robot interaction

Details

• CRID: 1390282680912509184
• NII Article ID: 110008694216
• DOI: 10.1299/jsmermd.2006._2p1-d18_1
• ISSN: 24243124
• Web Site: https://www.jstage.jst.go.jp/article/jsmermd/2006/0/2006__2P1-D18_1/_pdf
• Text Lang: ja
• Data Source:
  • JaLC
  • Crossref
  • CiNii Articles
• Abstract License Flag: Disallowed