Data-driven fuzzy logic control method for improved USV path planning

The parameters of the path planning algorithm for unmanned surface vehicles (USVs) usually rely on manual settings, which makes it difficult for the algorithm to achieve the optimal solution when considering multiple factors in path planning. This paper proposes a data-driven method to improve the U...

Full description

Saved in:
Bibliographic Details
Published in:The Journal of supercomputing Vol. 81; no. 7; p. 844
Main Authors: Wang, Feng, Wang, Chenglong, Wang, Yuanhui, Chemori, Ahmed, Zhang, Xiaoyue, Zhang, Kun, Zhang, Yuxuan
Format: Journal Article
Language:English
Published: New York Springer Nature B.V 09.05.2025
Springer Verlag
Subjects:
Algorithms
Automatic
Automatic Control Engineering
Computer Science
Control algorithms
Control methods
Datasets
Engineering Sciences
Fuzzy control
Fuzzy logic
Kinematics
Neural networks
Parameters
Path planning
Robotics
Surface vehicles
Unmanned vehicles
Velocity
Fuzzy logic control
Path planning
Data-driven
Neural network
Dynamic Window Approach
Unmanned Surface Vehicles (USVs)
ISSN:1573-0484, 0920-8542, 1573-0484
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The parameters of the path planning algorithm for unmanned surface vehicles (USVs) usually rely on manual settings, which makes it difficult for the algorithm to achieve the optimal solution when considering multiple factors in path planning. This paper proposes a data-driven method to improve the USV path planning algorithm in response to the problem of unreasonable control caused by manual experience parameter settings in traditional algorithms. Firstly, a dataset is constructed by extracting corresponding parameters from traditional fuzzy logic control algorithms. Then, using two existing fuzzy controllers as samples, a fuzzy neural network is designed. Finally, using this dataset, a new fuzzy logic controller is generated through a fuzzy neural network. Compared with traditional fuzzy logic controllers, data-driven controllers exhibit a more reasonable distribution of variable parameters, thus verifying the superiority of neural network-based controllers. Numerical simulations show that the proposed method improves both the path length and the navigation time, while ensuring safety in complex environments.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1573-0484
0920-8542
1573-0484
DOI:10.1007/s11227-025-07318-3