A robotic complex control method based on deep reinforcement learning of recurrent neural networks for automatic harvesting of greenhouse crops

The modern development of technology determines the feasibility of the transition in agriculture from manual labor to automatic production. One of the promising areas is the automation of growing vegetable crops in greenhouse complexes. Necessary factors for intensive plant growth and unfavorable fo...

ver descrição completa

Na minha lista:

Detalhes bibliográficos
Главные авторы:	Petrenko, V. I., Петренко, В. И., Tebueva, F. B., Тебуева, Ф. Б., Gurchinsky, M. M., Гурчинский, М. М., Antonov, V. O., Антонов, В. О.
Formato:	Статья
Idioma:	English
Publicado em:	ATLANTIS PRESS 2021
Assuntos:	Automation and robotics Decision- making Deep reinforcement learning Recurrent neural networks Recurrent Q-networks
Acesso em linha:	https://dspace.ncfu.ru/handle/20.500.12258/18124
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!

id	ir-20.500.12258-18124
record_format	dspace
spelling	ir-20.500.12258-181242021-09-08T09:04:19Z A robotic complex control method based on deep reinforcement learning of recurrent neural networks for automatic harvesting of greenhouse crops Petrenko, V. I. Петренко, В. И. Tebueva, F. B. Тебуева, Ф. Б. Gurchinsky, M. M. Гурчинский, М. М. Antonov, V. O. Антонов, В. О. Automation and robotics Decision- making Deep reinforcement learning Recurrent neural networks Recurrent Q-networks The modern development of technology determines the feasibility of the transition in agriculture from manual labor to automatic production. One of the promising areas is the automation of growing vegetable crops in greenhouse complexes. Necessary factors for intensive plant growth and unfavorable for human health, such as high temperature and humidity, as well as an atmosphere saturated with chemicals, make the task of robotizing agricultural operations urgent in this area. The method for controlling a robotic complex for automatic fruit collection in greenhouse complexes is proposed. Work in greenhouse complexes is characterized as non-deterministic and with partial observability of the environment; therefore, the deep recurrent neural network DRQN was used as the basis for the method of controlling the robotic complex. Deep learning with reinforcement was used for optimizing its weights. The presented simulation results demonstrate the efficiency of the proposed method and the need for its further development 2021-09-08T09:02:02Z 2021-09-08T09:02:02Z 2020 Статья Petrenko, V. I.; Tebueva, F. B.; Gurchinsky, M. M.; Antonov, V. O. A robotic complex control method based on deep reinforcement learning of recurrent neural networks for automatic harvesting of greenhouse crops // 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 340-346 http://hdl.handle.net/20.500.12258/18124 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	Automation and robotics Decision- making Deep reinforcement learning Recurrent neural networks Recurrent Q-networks
spellingShingle	Automation and robotics Decision- making Deep reinforcement learning Recurrent neural networks Recurrent Q-networks Petrenko, V. I. Петренко, В. И. Tebueva, F. B. Тебуева, Ф. Б. Gurchinsky, M. M. Гурчинский, М. М. Antonov, V. O. Антонов, В. О. A robotic complex control method based on deep reinforcement learning of recurrent neural networks for automatic harvesting of greenhouse crops
description	The modern development of technology determines the feasibility of the transition in agriculture from manual labor to automatic production. One of the promising areas is the automation of growing vegetable crops in greenhouse complexes. Necessary factors for intensive plant growth and unfavorable for human health, such as high temperature and humidity, as well as an atmosphere saturated with chemicals, make the task of robotizing agricultural operations urgent in this area. The method for controlling a robotic complex for automatic fruit collection in greenhouse complexes is proposed. Work in greenhouse complexes is characterized as non-deterministic and with partial observability of the environment; therefore, the deep recurrent neural network DRQN was used as the basis for the method of controlling the robotic complex. Deep learning with reinforcement was used for optimizing its weights. The presented simulation results demonstrate the efficiency of the proposed method and the need for its further development
format	Статья
author	Petrenko, V. I. Петренко, В. И. Tebueva, F. B. Тебуева, Ф. Б. Gurchinsky, M. M. Гурчинский, М. М. Antonov, V. O. Антонов, В. О.
author_facet	Petrenko, V. I. Петренко, В. И. Tebueva, F. B. Тебуева, Ф. Б. Gurchinsky, M. M. Гурчинский, М. М. Antonov, V. O. Антонов, В. О.
author_sort	Petrenko, V. I.
title	A robotic complex control method based on deep reinforcement learning of recurrent neural networks for automatic harvesting of greenhouse crops
title_short	A robotic complex control method based on deep reinforcement learning of recurrent neural networks for automatic harvesting of greenhouse crops
title_full	A robotic complex control method based on deep reinforcement learning of recurrent neural networks for automatic harvesting of greenhouse crops
title_fullStr	A robotic complex control method based on deep reinforcement learning of recurrent neural networks for automatic harvesting of greenhouse crops
title_full_unstemmed	A robotic complex control method based on deep reinforcement learning of recurrent neural networks for automatic harvesting of greenhouse crops
title_sort	robotic complex control method based on deep reinforcement learning of recurrent neural networks for automatic harvesting of greenhouse crops
publisher	ATLANTIS PRESS
publishDate	2021
url	https://dspace.ncfu.ru/handle/20.500.12258/18124
work_keys_str_mv	AT petrenkovi aroboticcomplexcontrolmethodbasedondeepreinforcementlearningofrecurrentneuralnetworksforautomaticharvestingofgreenhousecrops AT petrenkovi aroboticcomplexcontrolmethodbasedondeepreinforcementlearningofrecurrentneuralnetworksforautomaticharvestingofgreenhousecrops AT tebuevafb aroboticcomplexcontrolmethodbasedondeepreinforcementlearningofrecurrentneuralnetworksforautomaticharvestingofgreenhousecrops AT tebuevafb aroboticcomplexcontrolmethodbasedondeepreinforcementlearningofrecurrentneuralnetworksforautomaticharvestingofgreenhousecrops AT gurchinskymm aroboticcomplexcontrolmethodbasedondeepreinforcementlearningofrecurrentneuralnetworksforautomaticharvestingofgreenhousecrops AT gurčinskijmm aroboticcomplexcontrolmethodbasedondeepreinforcementlearningofrecurrentneuralnetworksforautomaticharvestingofgreenhousecrops AT antonovvo aroboticcomplexcontrolmethodbasedondeepreinforcementlearningofrecurrentneuralnetworksforautomaticharvestingofgreenhousecrops AT antonovvo aroboticcomplexcontrolmethodbasedondeepreinforcementlearningofrecurrentneuralnetworksforautomaticharvestingofgreenhousecrops AT petrenkovi roboticcomplexcontrolmethodbasedondeepreinforcementlearningofrecurrentneuralnetworksforautomaticharvestingofgreenhousecrops AT petrenkovi roboticcomplexcontrolmethodbasedondeepreinforcementlearningofrecurrentneuralnetworksforautomaticharvestingofgreenhousecrops AT tebuevafb roboticcomplexcontrolmethodbasedondeepreinforcementlearningofrecurrentneuralnetworksforautomaticharvestingofgreenhousecrops AT tebuevafb roboticcomplexcontrolmethodbasedondeepreinforcementlearningofrecurrentneuralnetworksforautomaticharvestingofgreenhousecrops AT gurchinskymm roboticcomplexcontrolmethodbasedondeepreinforcementlearningofrecurrentneuralnetworksforautomaticharvestingofgreenhousecrops AT gurčinskijmm roboticcomplexcontrolmethodbasedondeepreinforcementlearningofrecurrentneuralnetworksforautomaticharvestingofgreenhousecrops AT antonovvo roboticcomplexcontrolmethodbasedondeepreinforcementlearningofrecurrentneuralnetworksforautomaticharvestingofgreenhousecrops AT antonovvo roboticcomplexcontrolmethodbasedondeepreinforcementlearningofrecurrentneuralnetworksforautomaticharvestingofgreenhousecrops
_version_	1760601971865157632

A robotic complex control method based on deep reinforcement learning of recurrent neural networks for automatic harvesting of greenhouse crops

Registos relacionados