Evolution of a subsumption architecture neurocontroller

Julian Togelius

    Research output: Contribution to journalArticle

    Abstract

    An approach to robotics called layered evolution and merging features from the subsumption architecture into evolutionary robotics is presented, and its advantages are discussed. This approach is used to construct a layered controller for a simulated robot that learns which light source to approach in an environment with obstacles. The evolvability and performance of layered evolution on this task is compared to (standard) monolithic evolution, incremental and modularised evolution. To corroborate the hypothesis that a layered controller performs at least as well as an integrated one, the evolved layers are merged back into a single network. On the grounds of the test results, it is argued that layered evolution provides a superior approach for many tasks, and it is suggested that this approach may be the key to scaling up evolutionary robotics.

    Original languageEnglish (US)
    Pages (from-to)15-20
    Number of pages6
    JournalJournal of Intelligent and Fuzzy Systems
    Volume15
    Issue number1
    StatePublished - 2004

    Fingerprint

    Robotics
    Evolutionary Robotics
    Controllers
    Merging
    Light sources
    Evolvability
    Controller
    Robots
    Robot
    Architecture
    Scaling

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Control and Systems Engineering

    Cite this

    Evolution of a subsumption architecture neurocontroller. / Togelius, Julian.

    In: Journal of Intelligent and Fuzzy Systems, Vol. 15, No. 1, 2004, p. 15-20.

    Research output: Contribution to journalArticle

    @article{66d70f73c5514b6493a063c9092bcee9,
    title = "Evolution of a subsumption architecture neurocontroller",
    abstract = "An approach to robotics called layered evolution and merging features from the subsumption architecture into evolutionary robotics is presented, and its advantages are discussed. This approach is used to construct a layered controller for a simulated robot that learns which light source to approach in an environment with obstacles. The evolvability and performance of layered evolution on this task is compared to (standard) monolithic evolution, incremental and modularised evolution. To corroborate the hypothesis that a layered controller performs at least as well as an integrated one, the evolved layers are merged back into a single network. On the grounds of the test results, it is argued that layered evolution provides a superior approach for many tasks, and it is suggested that this approach may be the key to scaling up evolutionary robotics.",
    author = "Julian Togelius",
    year = "2004",
    language = "English (US)",
    volume = "15",
    pages = "15--20",
    journal = "Journal of Intelligent and Fuzzy Systems",
    issn = "1064-1246",
    publisher = "IOS Press",
    number = "1",

    }

    TY - JOUR

    T1 - Evolution of a subsumption architecture neurocontroller

    AU - Togelius, Julian

    PY - 2004

    Y1 - 2004

    N2 - An approach to robotics called layered evolution and merging features from the subsumption architecture into evolutionary robotics is presented, and its advantages are discussed. This approach is used to construct a layered controller for a simulated robot that learns which light source to approach in an environment with obstacles. The evolvability and performance of layered evolution on this task is compared to (standard) monolithic evolution, incremental and modularised evolution. To corroborate the hypothesis that a layered controller performs at least as well as an integrated one, the evolved layers are merged back into a single network. On the grounds of the test results, it is argued that layered evolution provides a superior approach for many tasks, and it is suggested that this approach may be the key to scaling up evolutionary robotics.

    AB - An approach to robotics called layered evolution and merging features from the subsumption architecture into evolutionary robotics is presented, and its advantages are discussed. This approach is used to construct a layered controller for a simulated robot that learns which light source to approach in an environment with obstacles. The evolvability and performance of layered evolution on this task is compared to (standard) monolithic evolution, incremental and modularised evolution. To corroborate the hypothesis that a layered controller performs at least as well as an integrated one, the evolved layers are merged back into a single network. On the grounds of the test results, it is argued that layered evolution provides a superior approach for many tasks, and it is suggested that this approach may be the key to scaling up evolutionary robotics.

    UR - http://www.scopus.com/inward/record.url?scp=10044228483&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=10044228483&partnerID=8YFLogxK

    M3 - Article

    VL - 15

    SP - 15

    EP - 20

    JO - Journal of Intelligent and Fuzzy Systems

    JF - Journal of Intelligent and Fuzzy Systems

    SN - 1064-1246

    IS - 1

    ER -