Proximal policy optimization based dynamic path planning algorithm for mobile robots

Abstract For the scenario where the overall layout is known and the obstacle distribution information is unknown, a dynamic path planning algorithm combining the A* algorithm and the proximal policy optimization (PPO) algorithm is proposed. Simulation experiments show that in all six test environmen...

Full description

Bibliographic Details
Main Authors: Xin Jin, Zhengxiao Wang
Format: Article
Language:English
Published: Wiley 2022-01-01
Series:Electronics Letters
Subjects:
Online Access:https://doi.org/10.1049/ell2.12342
_version_ 1811183596639092736
author Xin Jin
Zhengxiao Wang
author_facet Xin Jin
Zhengxiao Wang
author_sort Xin Jin
collection DOAJ
description Abstract For the scenario where the overall layout is known and the obstacle distribution information is unknown, a dynamic path planning algorithm combining the A* algorithm and the proximal policy optimization (PPO) algorithm is proposed. Simulation experiments show that in all six test environments, the proposed algorithm finds paths that are on average about 2.04% to 5.86% shorter compared to the state‐of‐the‐art algorithms in the literature, and reduces the number of training epochs before stabilization from tens of thousands to about 4000.
first_indexed 2024-04-11T09:48:37Z
format Article
id doaj.art-603f649473774c549a98ad90b0e7a856
institution Directory Open Access Journal
issn 0013-5194
1350-911X
language English
last_indexed 2024-04-11T09:48:37Z
publishDate 2022-01-01
publisher Wiley
record_format Article
series Electronics Letters
spelling doaj.art-603f649473774c549a98ad90b0e7a8562022-12-22T04:30:52ZengWileyElectronics Letters0013-51941350-911X2022-01-01581131510.1049/ell2.12342Proximal policy optimization based dynamic path planning algorithm for mobile robotsXin Jin0Zhengxiao Wang1Department of Mechanical Engineering Zhejiang University No.38, ZheDa Street, XiHu District Hangzhou People's Republic of ChinaDepartment of Mechanical Engineering Zhejiang University No.38, ZheDa Street, XiHu District Hangzhou People's Republic of ChinaAbstract For the scenario where the overall layout is known and the obstacle distribution information is unknown, a dynamic path planning algorithm combining the A* algorithm and the proximal policy optimization (PPO) algorithm is proposed. Simulation experiments show that in all six test environments, the proposed algorithm finds paths that are on average about 2.04% to 5.86% shorter compared to the state‐of‐the‐art algorithms in the literature, and reduces the number of training epochs before stabilization from tens of thousands to about 4000.https://doi.org/10.1049/ell2.12342Computer communicationsMobile radio systemsOptimisation techniquesSpatial variables controlMobile robotsMultiprocessing systems
spellingShingle Xin Jin
Zhengxiao Wang
Proximal policy optimization based dynamic path planning algorithm for mobile robots
Electronics Letters
Computer communications
Mobile radio systems
Optimisation techniques
Spatial variables control
Mobile robots
Multiprocessing systems
title Proximal policy optimization based dynamic path planning algorithm for mobile robots
title_full Proximal policy optimization based dynamic path planning algorithm for mobile robots
title_fullStr Proximal policy optimization based dynamic path planning algorithm for mobile robots
title_full_unstemmed Proximal policy optimization based dynamic path planning algorithm for mobile robots
title_short Proximal policy optimization based dynamic path planning algorithm for mobile robots
title_sort proximal policy optimization based dynamic path planning algorithm for mobile robots
topic Computer communications
Mobile radio systems
Optimisation techniques
Spatial variables control
Mobile robots
Multiprocessing systems
url https://doi.org/10.1049/ell2.12342
work_keys_str_mv AT xinjin proximalpolicyoptimizationbaseddynamicpathplanningalgorithmformobilerobots
AT zhengxiaowang proximalpolicyoptimizationbaseddynamicpathplanningalgorithmformobilerobots