View in EDS

Simultaneous incremental neuroevolution of motor control, navigation and object manipulation in 3D virtual creatures

Saved in:
Bibliographic Details
Title: Simultaneous incremental neuroevolution of motor control, navigation and object manipulation in 3D virtual creatures
Authors: Stanton, Adam James
Committee Members: Channon, A. D.
Summary: There have been numerous attempts to develop 3D virtual agents by applying evolutionary processes to populations that exist in a realistic physical simulation. Whilst often contributing useful knowledge, no previous work has demonstrated the capacity to evolve a sequence of increasingly complex behaviours in a single, unified system. This thesis has this demonstration as its primary aim. A rigorous exploration of one aspect of incremental artificial evolution was carried out to understand how subtask presentations affect the whole-task generalisation performance of evolved, fixed-morphology 3D agents. Results from this work led to the design of an environment–body–control architecture that can be used as a base for evolving multiple behaviours incrementally. A simulation based on this architecture with a more complex environment was then developed and explored. This system was then adapted to include elements of physical manipulation as a first step toward a fully physical virtual creature environment demonstrating advanced evolved behaviours. The thesis demonstrates that incremental evolutionary systems can be subject to problems of forgetting and loss of gradient, and that different complexification strategies have a strong bearing on the management of these issues. Presenting successive generations of the population to a full range of objective functions (covering and revisiting the range of complexity) outperforms straightforward linear or direct presentations, establishing a more robust approach to the evolution of naturalistic embodied agents. When combining this approach with a bespoke control architecture in a problem requiring reactive and deliberative behaviours, we see results that not only demonstrate success at the tasks, but also show a variety of intricate behaviours being used. This is the first ever example of the simultaneous incremental evolution in 3D of composite behaviours more complex than simple locomotion. Finally, the architecture demonstrably supports extension to manipulation in a feedback control task. Given the problem-agnostic controller architecture, these results indicate a system with potential for discovering yet more advanced behaviours in yet more complex environments.
URL: https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.727000
Database: OpenDissertations
FullText Text:
  Availability: 0
Header DbId: ddu
DbLabel: OpenDissertations
An: ddu.oai.ethos.bl.uk.727000
AccessLevel: 6
PubType: Dissertation/ Thesis
PubTypeId: dissertation
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Simultaneous incremental neuroevolution of motor control, navigation and object manipulation in 3D virtual creatures
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Stanton%2C+Adam+James%22">Stanton, Adam James</searchLink>
– Name: Author
  Label: Committee Members
  Group: Au
  Data: <searchLink fieldCode="CO" term="%22Channon%2C+A%2E+D%2E%22">Channon, A. D.</searchLink>
– Name: Abstract
  Label: Summary
  Group: Ab
  Data: There have been numerous attempts to develop 3D virtual agents by applying evolutionary processes to populations that exist in a realistic physical simulation. Whilst often contributing useful knowledge, no previous work has demonstrated the capacity to evolve a sequence of increasingly complex behaviours in a single, unified system. This thesis has this demonstration as its primary aim. A rigorous exploration of one aspect of incremental artificial evolution was carried out to understand how subtask presentations affect the whole-task generalisation performance of evolved, fixed-morphology 3D agents. Results from this work led to the design of an environment–body–control architecture that can be used as a base for evolving multiple behaviours incrementally. A simulation based on this architecture with a more complex environment was then developed and explored. This system was then adapted to include elements of physical manipulation as a first step toward a fully physical virtual creature environment demonstrating advanced evolved behaviours. The thesis demonstrates that incremental evolutionary systems can be subject to problems of forgetting and loss of gradient, and that different complexification strategies have a strong bearing on the management of these issues. Presenting successive generations of the population to a full range of objective functions (covering and revisiting the range of complexity) outperforms straightforward linear or direct presentations, establishing a more robust approach to the evolution of naturalistic embodied agents. When combining this approach with a bespoke control architecture in a problem requiring reactive and deliberative behaviours, we see results that not only demonstrate success at the tasks, but also show a variety of intricate behaviours being used. This is the first ever example of the simultaneous incremental evolution in 3D of composite behaviours more complex than simple locomotion. Finally, the architecture demonstrably supports extension to manipulation in a feedback control task. Given the problem-agnostic controller architecture, these results indicate a system with potential for discovering yet more advanced behaviours in yet more complex environments.
– Name: URL
  Label: URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.727000" linkWindow="_blank">https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.727000</link>
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=ddu&AN=ddu.oai.ethos.bl.uk.727000
RecordInfo BibRecord:
  BibEntity:
    Languages:
      – Code: eng
        Text: English
    Subjects:
      – SubjectFull: 006.3
        Type: general
      – SubjectFull: QA Mathematics
        Type: general
    Titles:
      – TitleFull: Simultaneous incremental neuroevolution of motor control, navigation and object manipulation in 3D virtual creatures
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Stanton, Adam James
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2017
ResultId 1