Hybrid Probabilistic Road Map Path Planning for Maritime Autonomous Surface Ships Based on Historical AIS Information and Improved DP Compression

A hybrid probabilistic road map (PRM) path planning algorithm based on historical automatic identification system (AIS) information and Douglas–Peucker (DP) compression is proposed to address the issues of low path quality and the need for extensive sampling in the traditional PRM algorithm. This in...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Journal of marine science and engineering Ročník 13; číslo 1; s. 184
Hlavní autori: Wu, Gongxing, Guo, Liepan, Shi, Danda, Han, Bing, Yang, Fan
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Basel MDPI AG 01.01.2025
Predmet:
Accuracy
AIS historical data
Algorithms
Artificial intelligence
Autonomous navigation
Cleaning
Compression
Data compression
Deep learning
Dijkstra, Edsger W
Efficiency
Heuristic
hybrid probabilistic route map (HPRM) algorithm
improved DP compression algorithm
maritime autonomous surface ships
Methods
Navigation
Optimization algorithms
Path planning
Planning
Probability theory
Roads & highways
Sea vessels
Search algorithms
ship path planning
Shipping industry
Ships
Smoothness
Trajectories
ISSN:2077-1312, 2077-1312
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:A hybrid probabilistic road map (PRM) path planning algorithm based on historical automatic identification system (AIS) information and Douglas–Peucker (DP) compression is proposed to address the issues of low path quality and the need for extensive sampling in the traditional PRM algorithm. This innovative approach significantly reduces the number of required samples and decreases path planning time. The process begins with the collection of historical AIS data from the autonomous vessel’s navigation area, followed by comprehensive data-cleaning procedures to eliminate invalid and incomplete records. Subsequently, an enhanced DP compression algorithm is employed to streamline the cleaned AIS data, minimizing waypoint data while retaining essential trajectory characteristics. Intersection points among various vessel trajectories are then calculated, and these points, along with the compressed AIS data, form the foundational dataset for path searching. Building upon the traditional PRM framework, the proposed hybrid PRM algorithm integrates the B-spline algorithm to smooth and optimize the generated paths. Comparative experiments conducted against the standard PRM algorithm, A*, and Dijkstra algorithms demonstrate that the hybrid PRM approach not only reduces planning time but also achieves superior path smoothness. These improvements enhance both the efficiency and accuracy of path planning for maritime autonomous surface ships (MASS), marking a significant advancement in autonomous maritime navigation.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2077-1312
2077-1312
DOI:10.3390/jmse13010184