Artificial wrestling: A dynamical formulation of autonomous agents fighting in a coupled inverted pendula framework

We develop autonomous agents that fight with each other, inspired by human wrestling. For this purpose, we propose a coupled inverted pendula (CIP) framework in which: (a) the tips of two inverted pendula are linked by a connecting rod, (b) each pendulum is primarily stabilized by a proportional-der...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Katsutoshi YOSHIDA, Shigeki MATSUMOTO, Yoichi MATSUE
Formato:	article
Lenguaje:	EN
Publicado:	The Japan Society of Mechanical Engineers 2015
Materias:	multiagent system competitive problem intelligent control nonlinear dynamics reachable set Mechanical engineering and machinery TJ1-1570
Acceso en línea:	https://doaj.org/article/9aea5e1cdec14f2f9decb6acdd1ad500
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:9aea5e1cdec14f2f9decb6acdd1ad500
record_format	dspace
spelling	oai:doaj.org-article:9aea5e1cdec14f2f9decb6acdd1ad5002021-11-26T06:30:10ZArtificial wrestling: A dynamical formulation of autonomous agents fighting in a coupled inverted pendula framework2187-974510.1299/mej.14-00518https://doaj.org/article/9aea5e1cdec14f2f9decb6acdd1ad5002015-10-01T00:00:00Zhttps://www.jstage.jst.go.jp/article/mej/2/5/2_14-00518/_pdf/-char/enhttps://doaj.org/toc/2187-9745We develop autonomous agents that fight with each other, inspired by human wrestling. For this purpose, we propose a coupled inverted pendula (CIP) framework in which: (a) the tips of two inverted pendula are linked by a connecting rod, (b) each pendulum is primarily stabilized by a proportional-derivative (PD) controller, (c) and each is additionally equipped with an intelligent controller. Based on this framework, we dynamically formulate an intelligent controller designed to store dynamical correspondence from initial states to final states of the CIP model, to receive state vectors of the model, and to output impulsive control forces to produce the desired final states of the model. By developing a quantized and reduced-order design for this controller, we obtain a practical control procedure based on an off-line learning method. We then conduct numerical simulations to investigate the individual performance of the intelligent controller, and we show that the performance can be improved by adding a delay element. The results show that the performance depends not only on the quantization resolution of the learning data but also on the delay time of the introduced element. Finally, we install the intelligent controllers into both pendula in the proposed framework in order to demonstrate autonomous competitive behavior between inverted pendula.Katsutoshi YOSHIDAShigeki MATSUMOTOYoichi MATSUEThe Japan Society of Mechanical Engineersarticlemultiagent systemcompetitive problemintelligent controlnonlinear dynamicsreachable setMechanical engineering and machineryTJ1-1570ENMechanical Engineering Journal, Vol 2, Iss 5, Pp 14-00518-14-00518 (2015)
institution	DOAJ
collection	DOAJ
language	EN
topic	multiagent system competitive problem intelligent control nonlinear dynamics reachable set Mechanical engineering and machinery TJ1-1570
spellingShingle	multiagent system competitive problem intelligent control nonlinear dynamics reachable set Mechanical engineering and machinery TJ1-1570 Katsutoshi YOSHIDA Shigeki MATSUMOTO Yoichi MATSUE Artificial wrestling: A dynamical formulation of autonomous agents fighting in a coupled inverted pendula framework
description	We develop autonomous agents that fight with each other, inspired by human wrestling. For this purpose, we propose a coupled inverted pendula (CIP) framework in which: (a) the tips of two inverted pendula are linked by a connecting rod, (b) each pendulum is primarily stabilized by a proportional-derivative (PD) controller, (c) and each is additionally equipped with an intelligent controller. Based on this framework, we dynamically formulate an intelligent controller designed to store dynamical correspondence from initial states to final states of the CIP model, to receive state vectors of the model, and to output impulsive control forces to produce the desired final states of the model. By developing a quantized and reduced-order design for this controller, we obtain a practical control procedure based on an off-line learning method. We then conduct numerical simulations to investigate the individual performance of the intelligent controller, and we show that the performance can be improved by adding a delay element. The results show that the performance depends not only on the quantization resolution of the learning data but also on the delay time of the introduced element. Finally, we install the intelligent controllers into both pendula in the proposed framework in order to demonstrate autonomous competitive behavior between inverted pendula.
format	article
author	Katsutoshi YOSHIDA Shigeki MATSUMOTO Yoichi MATSUE
author_facet	Katsutoshi YOSHIDA Shigeki MATSUMOTO Yoichi MATSUE
author_sort	Katsutoshi YOSHIDA
title	Artificial wrestling: A dynamical formulation of autonomous agents fighting in a coupled inverted pendula framework
title_short	Artificial wrestling: A dynamical formulation of autonomous agents fighting in a coupled inverted pendula framework
title_full	Artificial wrestling: A dynamical formulation of autonomous agents fighting in a coupled inverted pendula framework
title_fullStr	Artificial wrestling: A dynamical formulation of autonomous agents fighting in a coupled inverted pendula framework
title_full_unstemmed	Artificial wrestling: A dynamical formulation of autonomous agents fighting in a coupled inverted pendula framework
title_sort	artificial wrestling: a dynamical formulation of autonomous agents fighting in a coupled inverted pendula framework
publisher	The Japan Society of Mechanical Engineers
publishDate	2015
url	https://doaj.org/article/9aea5e1cdec14f2f9decb6acdd1ad500
work_keys_str_mv	AT katsutoshiyoshida artificialwrestlingadynamicalformulationofautonomousagentsfightinginacoupledinvertedpendulaframework AT shigekimatsumoto artificialwrestlingadynamicalformulationofautonomousagentsfightinginacoupledinvertedpendulaframework AT yoichimatsue artificialwrestlingadynamicalformulationofautonomousagentsfightinginacoupledinvertedpendulaframework
_version_	1718409795483992064

Artificial wrestling: A dynamical formulation of autonomous agents fighting in a coupled inverted pendula framework

Ejemplares similares