Multi-robot system learning based on evolutionary classification

This paper presents a novel machine learning method for agents of a multi-robot system. The learning process is based on knowledge discovery through continual analysis of robot sensory information. We demonstrate that classification trees and evolutionary forests may be a basis for creation of auton...

Full description

Bibliographic Details
Main Authors:	Manko Sergey, Lokhin Valery, Diane Sekou, Panin Alexander
Format:	Article
Language:	English
Published:	EDP Sciences 2016-01-01
Series:	MATEC Web of Conferences
Online Access:	http://dx.doi.org/10.1051/matecconf/20164203001

id	doaj-e0d0a927d92346cd8c641663f9089d76
record_format	Article
spelling	doaj-e0d0a927d92346cd8c641663f9089d762021-04-02T11:02:44ZengEDP SciencesMATEC Web of Conferences2261-236X2016-01-01420300110.1051/matecconf/20164203001matecconf_iccma2016_03001Multi-robot system learning based on evolutionary classificationManko SergeyLokhin ValeryDiane SekouPanin AlexanderThis paper presents a novel machine learning method for agents of a multi-robot system. The learning process is based on knowledge discovery through continual analysis of robot sensory information. We demonstrate that classification trees and evolutionary forests may be a basis for creation of autonomous robots capable both of learning and knowledge exchange with other agents in multi-robot system. The results of experimental studies confirm the effectiveness of the proposed approach.http://dx.doi.org/10.1051/matecconf/20164203001
collection	DOAJ
language	English
format	Article
sources	DOAJ
author	Manko Sergey Lokhin Valery Diane Sekou Panin Alexander
spellingShingle	Manko Sergey Lokhin Valery Diane Sekou Panin Alexander Multi-robot system learning based on evolutionary classification MATEC Web of Conferences
author_facet	Manko Sergey Lokhin Valery Diane Sekou Panin Alexander
author_sort	Manko Sergey
title	Multi-robot system learning based on evolutionary classification
title_short	Multi-robot system learning based on evolutionary classification
title_full	Multi-robot system learning based on evolutionary classification
title_fullStr	Multi-robot system learning based on evolutionary classification
title_full_unstemmed	Multi-robot system learning based on evolutionary classification
title_sort	multi-robot system learning based on evolutionary classification
publisher	EDP Sciences
series	MATEC Web of Conferences
issn	2261-236X
publishDate	2016-01-01
description	This paper presents a novel machine learning method for agents of a multi-robot system. The learning process is based on knowledge discovery through continual analysis of robot sensory information. We demonstrate that classification trees and evolutionary forests may be a basis for creation of autonomous robots capable both of learning and knowledge exchange with other agents in multi-robot system. The results of experimental studies confirm the effectiveness of the proposed approach.
url	http://dx.doi.org/10.1051/matecconf/20164203001
work_keys_str_mv	AT mankosergey multirobotsystemlearningbasedonevolutionaryclassification AT lokhinvalery multirobotsystemlearningbasedonevolutionaryclassification AT dianesekou multirobotsystemlearningbasedonevolutionaryclassification AT paninalexander multirobotsystemlearningbasedonevolutionaryclassification
_version_	1724165931561648128

Multi-robot system learning based on evolutionary classification

Similar Items