Cargando…

Multi-Objective Optimal Trajectory Planning for Robotic Arms Using Deep Reinforcement Learning

This study investigated the trajectory-planning problem of a six-axis robotic arm based on deep reinforcement learning. Taking into account several characteristics of robot motion, a multi-objective optimization approach is proposed, which was based on the motivations of deep reinforcement learning...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhang, Shaobo, Xia, Qinxiang, Chen, Mingxing, Cheng, Sizhu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10346668/
https://www.ncbi.nlm.nih.gov/pubmed/37447823
http://dx.doi.org/10.3390/s23135974
_version_ 1785073367710171136
author Zhang, Shaobo
Xia, Qinxiang
Chen, Mingxing
Cheng, Sizhu
author_facet Zhang, Shaobo
Xia, Qinxiang
Chen, Mingxing
Cheng, Sizhu
author_sort Zhang, Shaobo
collection PubMed
description This study investigated the trajectory-planning problem of a six-axis robotic arm based on deep reinforcement learning. Taking into account several characteristics of robot motion, a multi-objective optimization approach is proposed, which was based on the motivations of deep reinforcement learning and optimal planning. The optimal trajectory was considered with respect to multiple objectives, aiming to minimize factors such as accuracy, energy consumption, and smoothness. The multiple objectives were integrated into the reinforcement learning environment to achieve the desired trajectory. Based on forward and inverse kinematics, the joint angles and Cartesian coordinates were used as the input parameters, while the joint angle estimation served as the output. To enable the environment to rapidly find more-efficient solutions, the decaying episode mechanism was employed throughout the training process. The distribution of the trajectory points was improved in terms of uniformity and smoothness, which greatly contributed to the optimization of the robotic arm’s trajectory. The proposed method demonstrated its effectiveness in comparison with the RRT algorithm, as evidenced by the simulations and physical experiments.
format Online
Article
Text
id pubmed-10346668
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-103466682023-07-15 Multi-Objective Optimal Trajectory Planning for Robotic Arms Using Deep Reinforcement Learning Zhang, Shaobo Xia, Qinxiang Chen, Mingxing Cheng, Sizhu Sensors (Basel) Article This study investigated the trajectory-planning problem of a six-axis robotic arm based on deep reinforcement learning. Taking into account several characteristics of robot motion, a multi-objective optimization approach is proposed, which was based on the motivations of deep reinforcement learning and optimal planning. The optimal trajectory was considered with respect to multiple objectives, aiming to minimize factors such as accuracy, energy consumption, and smoothness. The multiple objectives were integrated into the reinforcement learning environment to achieve the desired trajectory. Based on forward and inverse kinematics, the joint angles and Cartesian coordinates were used as the input parameters, while the joint angle estimation served as the output. To enable the environment to rapidly find more-efficient solutions, the decaying episode mechanism was employed throughout the training process. The distribution of the trajectory points was improved in terms of uniformity and smoothness, which greatly contributed to the optimization of the robotic arm’s trajectory. The proposed method demonstrated its effectiveness in comparison with the RRT algorithm, as evidenced by the simulations and physical experiments. MDPI 2023-06-27 /pmc/articles/PMC10346668/ /pubmed/37447823 http://dx.doi.org/10.3390/s23135974 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Zhang, Shaobo
Xia, Qinxiang
Chen, Mingxing
Cheng, Sizhu
Multi-Objective Optimal Trajectory Planning for Robotic Arms Using Deep Reinforcement Learning
title Multi-Objective Optimal Trajectory Planning for Robotic Arms Using Deep Reinforcement Learning
title_full Multi-Objective Optimal Trajectory Planning for Robotic Arms Using Deep Reinforcement Learning
title_fullStr Multi-Objective Optimal Trajectory Planning for Robotic Arms Using Deep Reinforcement Learning
title_full_unstemmed Multi-Objective Optimal Trajectory Planning for Robotic Arms Using Deep Reinforcement Learning
title_short Multi-Objective Optimal Trajectory Planning for Robotic Arms Using Deep Reinforcement Learning
title_sort multi-objective optimal trajectory planning for robotic arms using deep reinforcement learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10346668/
https://www.ncbi.nlm.nih.gov/pubmed/37447823
http://dx.doi.org/10.3390/s23135974
work_keys_str_mv AT zhangshaobo multiobjectiveoptimaltrajectoryplanningforroboticarmsusingdeepreinforcementlearning
AT xiaqinxiang multiobjectiveoptimaltrajectoryplanningforroboticarmsusingdeepreinforcementlearning
AT chenmingxing multiobjectiveoptimaltrajectoryplanningforroboticarmsusingdeepreinforcementlearning
AT chengsizhu multiobjectiveoptimaltrajectoryplanningforroboticarmsusingdeepreinforcementlearning