The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
A evolução incremental com aprendizagem (IEWL) é proposta para o desenvolvimento de robôs autônomos, e a validade do método é avaliada com um robô móvel real para adquirir uma tarefa complexa. O desenvolvimento do sistema de controle para uma tarefa complexa, ou seja, aproximar-se de um objeto alvo evitando obstáculos em um ambiente, é realizado de forma incremental em dois estágios. Na primeira etapa, são desenvolvidos controladores para evitar obstáculos no ambiente. Utilizando o conhecimento adquirido no primeiro estágio, os controladores são desenvolvidos no segundo estágio para se aproximar do objeto alvo, evitando obstáculos no ambiente. Verifica-se que o uso da aprendizagem em conjunto com a evolução incremental é benéfico para manter a diversidade na população em evolução. Os desempenhos de dois controladores, um desenvolvido por IEWL e outro desenvolvido por evolução incremental sem aprendizagem (IENL), são comparados na tarefa dada. Os resultados experimentais mostram que o desempenho robusto é alcançado quando os controladores são desenvolvidos pela IEWL.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Md. Monirul ISLAM, Kazuyuki MURASE, "Incremental Evolution with Learning to Develop the Control System of Autonomous Robots for Complex Task" in IEICE TRANSACTIONS on Information,
vol. E85-D, no. 7, pp. 1118-1129, July 2002, doi: .
Abstract: Incremental evolution with learning (IEWL) is proposed for the development of autonomous robots, and the validity of the method is evaluated with a real mobile robot to acquire a complex task. Development of the control system for a complex task, i.e., approaching toward a target object by avoiding obstacles in an environment, is incrementally carried out in two-stage. In the first-stage, controllers are developed to avoid obstacles in the environment. By using acquired knowledge of the first-stage, controllers are developed in the second-stage to approach toward the target object by avoiding obstacles in the environment. It is found that the use of learning in conjunction with incremental evolution is beneficial for maintaining diversity in the evolving population. The performances of two controllers, one developed by IEWL and the other developed by incremental evolution without learning (IENL), are compared on the given task. The experimental results show that robust performance is achieved when controllers are developed by IEWL.
URL: https://global.ieice.org/en_transactions/information/10.1587/e85-d_7_1118/_p
Copiar
@ARTICLE{e85-d_7_1118,
author={Md. Monirul ISLAM, Kazuyuki MURASE, },
journal={IEICE TRANSACTIONS on Information},
title={Incremental Evolution with Learning to Develop the Control System of Autonomous Robots for Complex Task},
year={2002},
volume={E85-D},
number={7},
pages={1118-1129},
abstract={Incremental evolution with learning (IEWL) is proposed for the development of autonomous robots, and the validity of the method is evaluated with a real mobile robot to acquire a complex task. Development of the control system for a complex task, i.e., approaching toward a target object by avoiding obstacles in an environment, is incrementally carried out in two-stage. In the first-stage, controllers are developed to avoid obstacles in the environment. By using acquired knowledge of the first-stage, controllers are developed in the second-stage to approach toward the target object by avoiding obstacles in the environment. It is found that the use of learning in conjunction with incremental evolution is beneficial for maintaining diversity in the evolving population. The performances of two controllers, one developed by IEWL and the other developed by incremental evolution without learning (IENL), are compared on the given task. The experimental results show that robust performance is achieved when controllers are developed by IEWL.},
keywords={},
doi={},
ISSN={},
month={July},}
Copiar
TY - JOUR
TI - Incremental Evolution with Learning to Develop the Control System of Autonomous Robots for Complex Task
T2 - IEICE TRANSACTIONS on Information
SP - 1118
EP - 1129
AU - Md. Monirul ISLAM
AU - Kazuyuki MURASE
PY - 2002
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E85-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2002
AB - Incremental evolution with learning (IEWL) is proposed for the development of autonomous robots, and the validity of the method is evaluated with a real mobile robot to acquire a complex task. Development of the control system for a complex task, i.e., approaching toward a target object by avoiding obstacles in an environment, is incrementally carried out in two-stage. In the first-stage, controllers are developed to avoid obstacles in the environment. By using acquired knowledge of the first-stage, controllers are developed in the second-stage to approach toward the target object by avoiding obstacles in the environment. It is found that the use of learning in conjunction with incremental evolution is beneficial for maintaining diversity in the evolving population. The performances of two controllers, one developed by IEWL and the other developed by incremental evolution without learning (IENL), are compared on the given task. The experimental results show that robust performance is achieved when controllers are developed by IEWL.
ER -