University of Sussex
Browse

File(s) not publicly available

Darwinian dynamics of embodied chaotic exploration

conference contribution
posted on 2023-06-09, 15:32 authored by Yoonsik Shim, Joshua E Auerbach, Phil HusbandsPhil Husbands
We introduce a complementary direction of research into another kind of possible candidate for Darwinian neural dynamics where such dynamics occur at a slightly higher, more abstract level. Crucially the (chaotic) neuro dynamics are embodied and it is the whole neuro-body-environment system that must be considered, although the changes occur at the neural level. The Embodied Chaotic Exploration (ECE) incrementally explores and learns motor behaviors through an integrated combination of chaotic search and reflex learning. The architecture developed here allows realtime goal-directed exploration and learning of the possible motor patterns (e.g., for locomotion) of embodied systems of arbitrary morphology. The overall iterative search process formed from this combination is shown to have a strong parallels with evolutionary search.

History

Publication status

  • Published

Journal

Proceedings of the 2016 on Genetic and Evolutionary Computation Conference Companion

Publisher

Association for Computing Machinery

Page range

1053-1056

Event name

GECCO'16: Genetic and Evolutionary Computation Conference: A Recombination of the 25th Conference on Genetic Algorithms (IGCA) and the 21st Annual Genetic Programming Conference (GP)

Event location

Denver, Colorado

Event type

conference

Event date

July 20-24 2016

ISBN

9781450343237

Department affiliated with

  • Informatics Publications

Research groups affiliated with

  • Centre for Computational Neuroscience and Robotics Publications

Full text available

  • No

Peer reviewed?

  • Yes

Editors

Tobias Friedrich

Legacy Posted Date

2018-10-17

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC