Emergent Behaviours At The Edge of Chaos

Lorenzo Riano, TM McGinnity

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

    Abstract

    Emergent behaviours are a welcome feature in a robot that is expected to work in the real world. However they are too often the result of careful engineering, thus lacking a ``true emergent'' component. Here we explore the emergence of behaviours in a chaos driven robot. A random recurrent neural network drives the activation of several behaviours. Attractors in the network are created by using an unsupervised Hebbian learning mechanism. These attractors live at the edge between chaos and low-period dynamics. We show, with three experiments conducted on a real robot, that emergent behaviours arise when online learning is adopted. An analysis of results proves that this is the case when attractor learning is adopted. This suggests a methodology to obtain surprising emergent behaviours.
    LanguageEnglish
    Title of host publicationUnknown Host Publication
    Number of pages7
    Publication statusPublished - 2010
    EventProc. of Towards Autonomous Robotic Systems, TAROS 10 -
    Duration: 1 Jan 2010 → …

    Conference

    ConferenceProc. of Towards Autonomous Robotic Systems, TAROS 10
    Period1/01/10 → …

    Fingerprint

    Chaos theory
    Robots
    Unsupervised learning
    Recurrent neural networks
    Chemical activation
    Experiments

    Cite this

    Riano, L., & McGinnity, TM. (2010). Emergent Behaviours At The Edge of Chaos. In Unknown Host Publication
    Riano, Lorenzo ; McGinnity, TM. / Emergent Behaviours At The Edge of Chaos. Unknown Host Publication. 2010.
    @inproceedings{8fc3995f474141c998cf3af4367b66fe,
    title = "Emergent Behaviours At The Edge of Chaos",
    abstract = "Emergent behaviours are a welcome feature in a robot that is expected to work in the real world. However they are too often the result of careful engineering, thus lacking a ``true emergent'' component. Here we explore the emergence of behaviours in a chaos driven robot. A random recurrent neural network drives the activation of several behaviours. Attractors in the network are created by using an unsupervised Hebbian learning mechanism. These attractors live at the edge between chaos and low-period dynamics. We show, with three experiments conducted on a real robot, that emergent behaviours arise when online learning is adopted. An analysis of results proves that this is the case when attractor learning is adopted. This suggests a methodology to obtain surprising emergent behaviours.",
    author = "Lorenzo Riano and TM McGinnity",
    year = "2010",
    language = "English",
    booktitle = "Unknown Host Publication",

    }

    Riano, L & McGinnity, TM 2010, Emergent Behaviours At The Edge of Chaos. in Unknown Host Publication. Proc. of Towards Autonomous Robotic Systems, TAROS 10, 1/01/10.

    Emergent Behaviours At The Edge of Chaos. / Riano, Lorenzo; McGinnity, TM.

    Unknown Host Publication. 2010.

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

    TY - GEN

    T1 - Emergent Behaviours At The Edge of Chaos

    AU - Riano, Lorenzo

    AU - McGinnity, TM

    PY - 2010

    Y1 - 2010

    N2 - Emergent behaviours are a welcome feature in a robot that is expected to work in the real world. However they are too often the result of careful engineering, thus lacking a ``true emergent'' component. Here we explore the emergence of behaviours in a chaos driven robot. A random recurrent neural network drives the activation of several behaviours. Attractors in the network are created by using an unsupervised Hebbian learning mechanism. These attractors live at the edge between chaos and low-period dynamics. We show, with three experiments conducted on a real robot, that emergent behaviours arise when online learning is adopted. An analysis of results proves that this is the case when attractor learning is adopted. This suggests a methodology to obtain surprising emergent behaviours.

    AB - Emergent behaviours are a welcome feature in a robot that is expected to work in the real world. However they are too often the result of careful engineering, thus lacking a ``true emergent'' component. Here we explore the emergence of behaviours in a chaos driven robot. A random recurrent neural network drives the activation of several behaviours. Attractors in the network are created by using an unsupervised Hebbian learning mechanism. These attractors live at the edge between chaos and low-period dynamics. We show, with three experiments conducted on a real robot, that emergent behaviours arise when online learning is adopted. An analysis of results proves that this is the case when attractor learning is adopted. This suggests a methodology to obtain surprising emergent behaviours.

    M3 - Conference contribution

    BT - Unknown Host Publication

    ER -

    Riano L, McGinnity TM. Emergent Behaviours At The Edge of Chaos. In Unknown Host Publication. 2010