Literature DB >> 27443311

Behavioural plasticity in evolving robots.

Jônata Tyska Carvalho1,2, Stefano Nolfi3.   

Abstract

In this paper, we show how the development of plastic behaviours, i.e., behaviour displaying a modular organisation characterised by behavioural subunits that are alternated in a context-dependent manner, can enable evolving robots to solve their adaptive task more efficiently also when it does not require the accomplishment of multiple conflicting functions. The comparison of the results obtained in different experimental conditions indicates that the most important prerequisites for the evolution of behavioural plasticity are: the possibility to generate and perceive affordances (i.e., opportunities for behaviour execution), the possibility to rely on flexible regulatory processes that exploit both external and internal cues, and the possibility to realise smooth and effective transitions between behaviours.

Keywords:  Action switching; Autonomous robotics; Behavioural plasticity; Evolutionary robotics; Modularity; Multiple behaviours

Mesh:

Year:  2016        PMID: 27443311     DOI: 10.1007/s12064-016-0233-y

Source DB:  PubMed          Journal:  Theory Biosci        ISSN: 1431-7613            Impact factor:   1.919


  5 in total

1.  Duplication of modules facilitates the evolution of functional specialization.

Authors:  R Calabretta; S Nolfi; D Parisi; G P Wagner
Journal:  Artif Life       Date:  2000       Impact factor: 0.667

2.  Mosaic model for sensorimotor learning and control.

Authors:  M Haruno; D M Wolpert; M Kawato
Journal:  Neural Comput       Date:  2001-10       Impact factor: 2.026

3.  Learning to perceive the world as articulated: an approach for hierarchical learning in sensory-motor systems.

Authors:  J Tani; S Nolfi
Journal:  Neural Netw       Date:  1999-10

4.  The geometry of evolution.

Authors:  M Conrad
Journal:  Biosystems       Date:  1990       Impact factor: 1.973

5.  Emergent exploration via novelty management.

Authors:  Goren Gordon; Ehud Fonio; Ehud Ahissar
Journal:  J Neurosci       Date:  2014-09-17       Impact factor: 6.167

  5 in total
  1 in total

1.  Robust optimization through neuroevolution.

Authors:  Paolo Pagliuca; Stefano Nolfi
Journal:  PLoS One       Date:  2019-03-01       Impact factor: 3.240

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.