Multipolicy Robot-Following Model Based on Reinforcement Learning

We propose in this paper a new approach to solve the decision problem of robot-following. Different from the existing single policy model, we propose a multipolicy model, which can change the following policy in time according to the scene. The value of this paper is to obtain a multipolicy robot-fo...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ning Yu, Lin Nan, Tao Ku
Formato:	article
Lenguaje:	EN
Publicado:	Hindawi Limited 2021
Materias:	Computer software QA76.75-76.765
Acceso en línea:	https://doaj.org/article/c6b6f860eb3d419ebc23d40186038802
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c6b6f860eb3d419ebc23d40186038802
record_format	dspace
spelling	oai:doaj.org-article:c6b6f860eb3d419ebc23d401860388022021-11-22T01:11:07ZMultipolicy Robot-Following Model Based on Reinforcement Learning1875-919X10.1155/2021/5692105https://doaj.org/article/c6b6f860eb3d419ebc23d401860388022021-01-01T00:00:00Zhttp://dx.doi.org/10.1155/2021/5692105https://doaj.org/toc/1875-919XWe propose in this paper a new approach to solve the decision problem of robot-following. Different from the existing single policy model, we propose a multipolicy model, which can change the following policy in time according to the scene. The value of this paper is to obtain a multipolicy robot-following model by the self-learning method, which is used to improve the safety, efficiency, and stability of robot-following in the complex environments. Empirical investigation on a number of datasets reveals that overall, the proposed approach tends to have superior out-of-sample performance when compared to alternative robot-following decision methods. The performance of the model has been improved by about 2 times in situations where there are few obstacles and about 6 times in situations where there are lots of obstacles.Ning YuLin NanTao KuHindawi LimitedarticleComputer softwareQA76.75-76.765ENScientific Programming, Vol 2021 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer software QA76.75-76.765
spellingShingle	Computer software QA76.75-76.765 Ning Yu Lin Nan Tao Ku Multipolicy Robot-Following Model Based on Reinforcement Learning
description	We propose in this paper a new approach to solve the decision problem of robot-following. Different from the existing single policy model, we propose a multipolicy model, which can change the following policy in time according to the scene. The value of this paper is to obtain a multipolicy robot-following model by the self-learning method, which is used to improve the safety, efficiency, and stability of robot-following in the complex environments. Empirical investigation on a number of datasets reveals that overall, the proposed approach tends to have superior out-of-sample performance when compared to alternative robot-following decision methods. The performance of the model has been improved by about 2 times in situations where there are few obstacles and about 6 times in situations where there are lots of obstacles.
format	article
author	Ning Yu Lin Nan Tao Ku
author_facet	Ning Yu Lin Nan Tao Ku
author_sort	Ning Yu
title	Multipolicy Robot-Following Model Based on Reinforcement Learning
title_short	Multipolicy Robot-Following Model Based on Reinforcement Learning
title_full	Multipolicy Robot-Following Model Based on Reinforcement Learning
title_fullStr	Multipolicy Robot-Following Model Based on Reinforcement Learning
title_full_unstemmed	Multipolicy Robot-Following Model Based on Reinforcement Learning
title_sort	multipolicy robot-following model based on reinforcement learning
publisher	Hindawi Limited
publishDate	2021
url	https://doaj.org/article/c6b6f860eb3d419ebc23d40186038802
work_keys_str_mv	AT ningyu multipolicyrobotfollowingmodelbasedonreinforcementlearning AT linnan multipolicyrobotfollowingmodelbasedonreinforcementlearning AT taoku multipolicyrobotfollowingmodelbasedonreinforcementlearning
_version_	1718418306368536576

Multipolicy Robot-Following Model Based on Reinforcement Learning

Ejemplares similares