Method for reconfiguring the kinematic structure of a mechatronic-modular robot in non-deterministic conditions

Modular robots, consisting of many identical modules, are one of the most difficult areas of robotics. Each newly added element changes the shape and capabilities of the end device, for example, adds functionality or allows the robot to move in new planes. The reconfiguration of the kinematic struct...

Ful tanımlama

Kaydedildi:

Detaylı Bibliyografya
Asıl Yazarlar:	Petrenko, V. I., Петренко, В. И., Tebueva, F. B., Тебуева, Ф. Б., Pavlov, A. S., Павлов, А. С., Gurchinsky, M. M., Гурчинский, М. М.
Materyal Türü:	Статья
Dil:	English
Baskı/Yayın Bilgisi:	ATLANTIS PRESS 2021
Konular:	Modular robotic Q-learning Reinforcement learning Path planning Multi-agent systems
Online Erişim:	https://dspace.ncfu.ru/handle/20.500.12258/18122
Etiketler:	Etiketle Etiket eklenmemiş, İlk siz ekleyin!

id	ir-20.500.12258-18122
record_format	dspace
spelling	ir-20.500.12258-181222021-09-08T08:52:41Z Method for reconfiguring the kinematic structure of a mechatronic-modular robot in non-deterministic conditions Petrenko, V. I. Петренко, В. И. Tebueva, F. B. Тебуева, Ф. Б. Pavlov, A. S. Павлов, А. С. Gurchinsky, M. M. Гурчинский, М. М. Modular robotic Q-learning Reinforcement learning Path planning Multi-agent systems Modular robots, consisting of many identical modules, are one of the most difficult areas of robotics. Each newly added element changes the shape and capabilities of the end device, for example, adds functionality or allows the robot to move in new planes. The reconfiguration of the kinematic structure is a sequence of movements of each robot module from the initial position of the initial configuration to the final position of the desired configuration. The paper considers a method for reconfiguration the kinematic structure of a mechatronic-modular robot using reinforcement learning. The proposed method will be built on the basis of a learning algorithm, where the information for training will be the actions taken and the "reward" is a value characterizing the quality of the robot's completion of the target task. The purpose of the training is to build a control algorithm that maximizes the total reward for a certain period of time. The effectiveness of the learning algorithm was tested by computer simulation of a robot, consisting of 5, 10 and 15 modules, in the formation of the target configuration 2021-09-08T08:51:36Z 2021-09-08T08:51:36Z 2020 Статья Petrenko, V. I.; Tebueva, F. B.; Pavlov A. S.; Gurchinsky, M. M. Method for reconfiguring the kinematic structure of a mechatronic-modular robot in non-deterministic conditions // PROCEEDINGS OF THE 8TH SCIENTIFIC CONFERENCE ON INFORMATION TECHNOLOGIES FOR INTELLIGENT DECISION MAKING SUPPORT (ITIDS 2020). - 2020. - Book Series: Advances in Intelligent Systems Research. - Volume 174. - Page 347-352 http://hdl.handle.net/20.500.12258/18122 en PROCEEDINGS OF THE 8TH SCIENTIFIC CONFERENCE ON INFORMATION TECHNOLOGIES FOR INTELLIGENT DECISION MAKING SUPPORT (ITIDS 2020) application/pdf ATLANTIS PRESS
institution	СКФУ
collection	Репозиторий
language	English
topic	Modular robotic Q-learning Reinforcement learning Path planning Multi-agent systems
spellingShingle	Modular robotic Q-learning Reinforcement learning Path planning Multi-agent systems Petrenko, V. I. Петренко, В. И. Tebueva, F. B. Тебуева, Ф. Б. Pavlov, A. S. Павлов, А. С. Gurchinsky, M. M. Гурчинский, М. М. Method for reconfiguring the kinematic structure of a mechatronic-modular robot in non-deterministic conditions
description	Modular robots, consisting of many identical modules, are one of the most difficult areas of robotics. Each newly added element changes the shape and capabilities of the end device, for example, adds functionality or allows the robot to move in new planes. The reconfiguration of the kinematic structure is a sequence of movements of each robot module from the initial position of the initial configuration to the final position of the desired configuration. The paper considers a method for reconfiguration the kinematic structure of a mechatronic-modular robot using reinforcement learning. The proposed method will be built on the basis of a learning algorithm, where the information for training will be the actions taken and the "reward" is a value characterizing the quality of the robot's completion of the target task. The purpose of the training is to build a control algorithm that maximizes the total reward for a certain period of time. The effectiveness of the learning algorithm was tested by computer simulation of a robot, consisting of 5, 10 and 15 modules, in the formation of the target configuration
format	Статья
author	Petrenko, V. I. Петренко, В. И. Tebueva, F. B. Тебуева, Ф. Б. Pavlov, A. S. Павлов, А. С. Gurchinsky, M. M. Гурчинский, М. М.
author_facet	Petrenko, V. I. Петренко, В. И. Tebueva, F. B. Тебуева, Ф. Б. Pavlov, A. S. Павлов, А. С. Gurchinsky, M. M. Гурчинский, М. М.
author_sort	Petrenko, V. I.
title	Method for reconfiguring the kinematic structure of a mechatronic-modular robot in non-deterministic conditions
title_short	Method for reconfiguring the kinematic structure of a mechatronic-modular robot in non-deterministic conditions
title_full	Method for reconfiguring the kinematic structure of a mechatronic-modular robot in non-deterministic conditions
title_fullStr	Method for reconfiguring the kinematic structure of a mechatronic-modular robot in non-deterministic conditions
title_full_unstemmed	Method for reconfiguring the kinematic structure of a mechatronic-modular robot in non-deterministic conditions
title_sort	method for reconfiguring the kinematic structure of a mechatronic-modular robot in non-deterministic conditions
publisher	ATLANTIS PRESS
publishDate	2021
url	https://dspace.ncfu.ru/handle/20.500.12258/18122
work_keys_str_mv	AT petrenkovi methodforreconfiguringthekinematicstructureofamechatronicmodularrobotinnondeterministicconditions AT petrenkovi methodforreconfiguringthekinematicstructureofamechatronicmodularrobotinnondeterministicconditions AT tebuevafb methodforreconfiguringthekinematicstructureofamechatronicmodularrobotinnondeterministicconditions AT tebuevafb methodforreconfiguringthekinematicstructureofamechatronicmodularrobotinnondeterministicconditions AT pavlovas methodforreconfiguringthekinematicstructureofamechatronicmodularrobotinnondeterministicconditions AT pavlovas methodforreconfiguringthekinematicstructureofamechatronicmodularrobotinnondeterministicconditions AT gurchinskymm methodforreconfiguringthekinematicstructureofamechatronicmodularrobotinnondeterministicconditions AT gurčinskijmm methodforreconfiguringthekinematicstructureofamechatronicmodularrobotinnondeterministicconditions
_version_	1760599221524758528

Method for reconfiguring the kinematic structure of a mechatronic-modular robot in non-deterministic conditions

Benzer Materyaller