Skip navigation
User training | Reference and search service

Library catalog

Content aggregators
Please use this identifier to cite or link to this item:

Title: odNEAT: an algorithm for decentralised online evolution of robotic controllers
Authors: Silva, F.
Urbano, P.
Correia, L.
Christensen, A. L.
Keywords: Artificial neural networks
Decentralised algorithms
Multirobot systems
Online evolution
Issue Date: 2015
Publisher: MIT Press
Abstract: Online evolution gives robots the capacity to learn new tasks and to adapt to changing environmental conditions during task execution. Previous approaches to online evolution of neural controllers are typically limited to the optimisation of weights in networks with a prespecified, fixed topology. In this article, we propose a novel approach to online learning in groups of autonomous robots called odNEAT. odNEAT is a distributed and decentralised neuroevolution algorithm that evolves both weights and network topology. We demonstrate odNEAT in three multirobot tasks: aggregation, integrated navigation and obstacle avoidance, and phototaxis. Results show that odNEAT approximates the performance of rtNEAT, an efficient centralised method, and outperforms IM-( mu + 1), a decentralised neuroevolution algorithm. Compared with rtNEAT and IM( mu + 1), odNEAT's evolutionary dynamics lead to the synthesis of less complex neural controllers with superior generalisation capabilities. We show that robots executing odNEAT can display a high degree of fault tolerance as they are able to adapt and learn new behaviours in the presence of faults. We conclude with a series of ablation studies to analyse the impact of each algorithmic component on performance.
Peer reviewed: yes
DOI: 10.1162/EVCO_a_00141
ISSN: 1063-6560
Accession number: WOS:000362839000004
Appears in Collections:CTI-RI - Artigos em revistas científicas internacionais com arbitragem científica

Files in This Item:
File Description SizeFormat 
p1059_single.pdfPré-print474.3 kBAdobe PDFView/Open

FacebookTwitterDeliciousLinkedInDiggGoogle BookmarksMySpace
Formato BibTex MendeleyEndnote Currículo DeGóis 

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.