Generation of behavior automaton on neural network

Tetsuya Ogata, Kazuki Hayashi, Ikuo Kitagishi, Shigeki Sugano

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    6 Citations (Scopus)

    Abstract

    To plan behavior procedures, it is necessary for an agent to have a world model concerning the temporal sequences information. In this paper, a temporal information learning algorithm is proposed with a three layer neural network implemented the `effectiveness of simulation accumulation' algorithm. This algorithm can construct `behavior automaton' in the neural network. From the results of some learning experiments using a mobile robot simulation, the generated automaton express the complexity of the simulation environments. The robot agent acquires a behavior automaton for obstacle avoidance behavior which is influenced by the simulation environment.

    Original languageEnglish
    Title of host publicationIEEE International Conference on Intelligent Robots and Systems
    Editors Anon
    Place of PublicationPiscataway, NJ, United States
    PublisherIEEE
    Pages608-613
    Number of pages6
    Volume2
    Publication statusPublished - 1997
    EventProceedings of the 1997 IEEE/RSJ International Conference on Intelligent Robot and Systems. Part 2 (of 3) - Grenoble, Fr
    Duration: 1998 Sep 71998 Sep 11

    Other

    OtherProceedings of the 1997 IEEE/RSJ International Conference on Intelligent Robot and Systems. Part 2 (of 3)
    CityGrenoble, Fr
    Period98/9/798/9/11

    Fingerprint

    Neural networks
    Collision avoidance
    Mobile robots
    Learning algorithms
    Robots
    Experiments

    ASJC Scopus subject areas

    • Control and Systems Engineering

    Cite this

    Ogata, T., Hayashi, K., Kitagishi, I., & Sugano, S. (1997). Generation of behavior automaton on neural network. In Anon (Ed.), IEEE International Conference on Intelligent Robots and Systems (Vol. 2, pp. 608-613). Piscataway, NJ, United States: IEEE.

    Generation of behavior automaton on neural network. / Ogata, Tetsuya; Hayashi, Kazuki; Kitagishi, Ikuo; Sugano, Shigeki.

    IEEE International Conference on Intelligent Robots and Systems. ed. / Anon. Vol. 2 Piscataway, NJ, United States : IEEE, 1997. p. 608-613.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Ogata, T, Hayashi, K, Kitagishi, I & Sugano, S 1997, Generation of behavior automaton on neural network. in Anon (ed.), IEEE International Conference on Intelligent Robots and Systems. vol. 2, IEEE, Piscataway, NJ, United States, pp. 608-613, Proceedings of the 1997 IEEE/RSJ International Conference on Intelligent Robot and Systems. Part 2 (of 3), Grenoble, Fr, 98/9/7.
    Ogata T, Hayashi K, Kitagishi I, Sugano S. Generation of behavior automaton on neural network. In Anon, editor, IEEE International Conference on Intelligent Robots and Systems. Vol. 2. Piscataway, NJ, United States: IEEE. 1997. p. 608-613
    Ogata, Tetsuya ; Hayashi, Kazuki ; Kitagishi, Ikuo ; Sugano, Shigeki. / Generation of behavior automaton on neural network. IEEE International Conference on Intelligent Robots and Systems. editor / Anon. Vol. 2 Piscataway, NJ, United States : IEEE, 1997. pp. 608-613
    @inproceedings{b824911b57c941f8b42a87e5e780f149,
    title = "Generation of behavior automaton on neural network",
    abstract = "To plan behavior procedures, it is necessary for an agent to have a world model concerning the temporal sequences information. In this paper, a temporal information learning algorithm is proposed with a three layer neural network implemented the `effectiveness of simulation accumulation' algorithm. This algorithm can construct `behavior automaton' in the neural network. From the results of some learning experiments using a mobile robot simulation, the generated automaton express the complexity of the simulation environments. The robot agent acquires a behavior automaton for obstacle avoidance behavior which is influenced by the simulation environment.",
    author = "Tetsuya Ogata and Kazuki Hayashi and Ikuo Kitagishi and Shigeki Sugano",
    year = "1997",
    language = "English",
    volume = "2",
    pages = "608--613",
    editor = "Anon",
    booktitle = "IEEE International Conference on Intelligent Robots and Systems",
    publisher = "IEEE",

    }

    TY - GEN

    T1 - Generation of behavior automaton on neural network

    AU - Ogata, Tetsuya

    AU - Hayashi, Kazuki

    AU - Kitagishi, Ikuo

    AU - Sugano, Shigeki

    PY - 1997

    Y1 - 1997

    N2 - To plan behavior procedures, it is necessary for an agent to have a world model concerning the temporal sequences information. In this paper, a temporal information learning algorithm is proposed with a three layer neural network implemented the `effectiveness of simulation accumulation' algorithm. This algorithm can construct `behavior automaton' in the neural network. From the results of some learning experiments using a mobile robot simulation, the generated automaton express the complexity of the simulation environments. The robot agent acquires a behavior automaton for obstacle avoidance behavior which is influenced by the simulation environment.

    AB - To plan behavior procedures, it is necessary for an agent to have a world model concerning the temporal sequences information. In this paper, a temporal information learning algorithm is proposed with a three layer neural network implemented the `effectiveness of simulation accumulation' algorithm. This algorithm can construct `behavior automaton' in the neural network. From the results of some learning experiments using a mobile robot simulation, the generated automaton express the complexity of the simulation environments. The robot agent acquires a behavior automaton for obstacle avoidance behavior which is influenced by the simulation environment.

    UR - http://www.scopus.com/inward/record.url?scp=0031384393&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0031384393&partnerID=8YFLogxK

    M3 - Conference contribution

    AN - SCOPUS:0031384393

    VL - 2

    SP - 608

    EP - 613

    BT - IEEE International Conference on Intelligent Robots and Systems

    A2 - Anon, null

    PB - IEEE

    CY - Piscataway, NJ, United States

    ER -