Online Evolution of Adaptive Robot Behaviour

Fernando Silva, Paulo Urbano and Anders Lyhne Christensen
Additional contact information
Fernando Silva: Instituto de Telecomunicações, Lisboa, Portugal and LabMAg, Faculdade de Ciências, Universidade de Lisboa, Lisboa, Portugal
Paulo Urbano: LabMAg, Faculdade de Ciências, Universidade de Lisboa, Lisboa, Portugal
Anders Lyhne Christensen: Instituto de Telecomunicações, Lisboa, Portugal and Instituto Universitário de Lisboa (ISCTE-IUL), Lisboa, Portugal

International Journal of Natural Computing Research (IJNCR), 2014, vol. 4, issue 2, 59-77

Abstract: The authors propose and evaluate a novel approach to the online synthesis of neural controllers for autonomous robots. The authors combine online evolution of weights and network topology with neuromodulated learning. The authors demonstrate our method through a series of simulation-based experiments in which an e-puck-like robot must perform a dynamic concurrent foraging task. In this task, scattered food items periodically change their nutritive value or become poisonous. The authors demonstrate that the online evolutionary process, both with and without neuromodulation, is capable of generating controllers well adapted to the periodic task changes. The authors show that when neuromodulated learning is combined with evolution, neural controllers are synthesised faster than by evolution alone. An analysis of the evolved solutions reveals that neuromodulation allows for a more effective expression of a given topology's potential due to the active modification of internal dynamics. Neuromodulated networks learn abstractions of the task and different modes of operation that are triggered by external stimulus.

Date: 2014
References: Add references at CitEc
Citations:

Downloads: (external link)
http://services.igi-global.com/resolvedoi/resolve. ... 018/ijncr.2014040104 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:igg:jncr00:v:4:y:2014:i:2:p:59-77

Access Statistics for this article

International Journal of Natural Computing Research (IJNCR) is currently edited by Xuewen Xia

More articles in International Journal of Natural Computing Research (IJNCR) from IGI Global
Bibliographic data for series maintained by Journal Editor ().