Acquisition of reactive motion for communication robots using interactive EC

    研究成果: Conference contribution

    3 引用 (Scopus)

    抄録

    We've developed an emotional communication robot, WAMOEBA, using behavior-based techniques. We also proposed motor-agent (MA) model, which is an autonomous distributed-control algorithm constructed of simple sensor-motor coordination. Though it enables WAMOEBA to behave in various ways, the weight of the combinations between different motor agents is influenced by the preferences of the developer. We usually use machine-learning algorithms to automatically configure these parameters for communication robots. However, this makes it difficult to define the quantitative evaluation required for communication. We therefore used the method of interactive evolutionary computation (IEC), which can be applied to problems involving quantitative evaluation. IEC does not require to define a fitness function; this task is performed by users. But the biggest problem with using IEC is human fatigue, which causes insufficiency of individuals and generations for convergence of EC. To fix this problem, we use the prediction function that automatically calculates the fitness values of genes from some samples that have received the human subjective evaluation. Then we carried out the behavior acquisition experiment using the IEC simulation system with the prediction function. As the results of experiments, it is confirmed that diversifying the genetic pool is an efficient way for generating a variety of behavior.

    元の言語English
    ホスト出版物のタイトル2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
    ページ1198-1203
    ページ数6
    2
    出版物ステータスPublished - 2004
    イベント2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) - Sendai
    継続期間: 2004 9 282004 10 2

    Other

    Other2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
    Sendai
    期間04/9/2804/10/2

    Fingerprint

    Evolutionary algorithms
    Robots
    Communication
    Learning algorithms
    Learning systems
    Genes
    Experiments
    Fatigue of materials
    Sensors

    ASJC Scopus subject areas

    • Engineering(all)

    これを引用

    Suga, Y., Ogata, T., & Sugano, S. (2004). Acquisition of reactive motion for communication robots using interactive EC. : 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (巻 2, pp. 1198-1203)

    Acquisition of reactive motion for communication robots using interactive EC. / Suga, Yuki; Ogata, Tetsuya; Sugano, Shigeki.

    2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 巻 2 2004. p. 1198-1203.

    研究成果: Conference contribution

    Suga, Y, Ogata, T & Sugano, S 2004, Acquisition of reactive motion for communication robots using interactive EC. : 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 巻. 2, pp. 1198-1203, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Sendai, 04/9/28.
    Suga Y, Ogata T, Sugano S. Acquisition of reactive motion for communication robots using interactive EC. : 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 巻 2. 2004. p. 1198-1203
    Suga, Yuki ; Ogata, Tetsuya ; Sugano, Shigeki. / Acquisition of reactive motion for communication robots using interactive EC. 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 巻 2 2004. pp. 1198-1203
    @inproceedings{efb85ac4e88847ceb507e97961c831ea,
    title = "Acquisition of reactive motion for communication robots using interactive EC",
    abstract = "We've developed an emotional communication robot, WAMOEBA, using behavior-based techniques. We also proposed motor-agent (MA) model, which is an autonomous distributed-control algorithm constructed of simple sensor-motor coordination. Though it enables WAMOEBA to behave in various ways, the weight of the combinations between different motor agents is influenced by the preferences of the developer. We usually use machine-learning algorithms to automatically configure these parameters for communication robots. However, this makes it difficult to define the quantitative evaluation required for communication. We therefore used the method of interactive evolutionary computation (IEC), which can be applied to problems involving quantitative evaluation. IEC does not require to define a fitness function; this task is performed by users. But the biggest problem with using IEC is human fatigue, which causes insufficiency of individuals and generations for convergence of EC. To fix this problem, we use the prediction function that automatically calculates the fitness values of genes from some samples that have received the human subjective evaluation. Then we carried out the behavior acquisition experiment using the IEC simulation system with the prediction function. As the results of experiments, it is confirmed that diversifying the genetic pool is an efficient way for generating a variety of behavior.",
    author = "Yuki Suga and Tetsuya Ogata and Shigeki Sugano",
    year = "2004",
    language = "English",
    isbn = "0780384636",
    volume = "2",
    pages = "1198--1203",
    booktitle = "2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",

    }

    TY - GEN

    T1 - Acquisition of reactive motion for communication robots using interactive EC

    AU - Suga, Yuki

    AU - Ogata, Tetsuya

    AU - Sugano, Shigeki

    PY - 2004

    Y1 - 2004

    N2 - We've developed an emotional communication robot, WAMOEBA, using behavior-based techniques. We also proposed motor-agent (MA) model, which is an autonomous distributed-control algorithm constructed of simple sensor-motor coordination. Though it enables WAMOEBA to behave in various ways, the weight of the combinations between different motor agents is influenced by the preferences of the developer. We usually use machine-learning algorithms to automatically configure these parameters for communication robots. However, this makes it difficult to define the quantitative evaluation required for communication. We therefore used the method of interactive evolutionary computation (IEC), which can be applied to problems involving quantitative evaluation. IEC does not require to define a fitness function; this task is performed by users. But the biggest problem with using IEC is human fatigue, which causes insufficiency of individuals and generations for convergence of EC. To fix this problem, we use the prediction function that automatically calculates the fitness values of genes from some samples that have received the human subjective evaluation. Then we carried out the behavior acquisition experiment using the IEC simulation system with the prediction function. As the results of experiments, it is confirmed that diversifying the genetic pool is an efficient way for generating a variety of behavior.

    AB - We've developed an emotional communication robot, WAMOEBA, using behavior-based techniques. We also proposed motor-agent (MA) model, which is an autonomous distributed-control algorithm constructed of simple sensor-motor coordination. Though it enables WAMOEBA to behave in various ways, the weight of the combinations between different motor agents is influenced by the preferences of the developer. We usually use machine-learning algorithms to automatically configure these parameters for communication robots. However, this makes it difficult to define the quantitative evaluation required for communication. We therefore used the method of interactive evolutionary computation (IEC), which can be applied to problems involving quantitative evaluation. IEC does not require to define a fitness function; this task is performed by users. But the biggest problem with using IEC is human fatigue, which causes insufficiency of individuals and generations for convergence of EC. To fix this problem, we use the prediction function that automatically calculates the fitness values of genes from some samples that have received the human subjective evaluation. Then we carried out the behavior acquisition experiment using the IEC simulation system with the prediction function. As the results of experiments, it is confirmed that diversifying the genetic pool is an efficient way for generating a variety of behavior.

    UR - http://www.scopus.com/inward/record.url?scp=14044263599&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=14044263599&partnerID=8YFLogxK

    M3 - Conference contribution

    AN - SCOPUS:14044263599

    SN - 0780384636

    VL - 2

    SP - 1198

    EP - 1203

    BT - 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

    ER -