USV path planning method with velocity variation and global optimisation based on AIS service platform

被引:41
作者
Yu, Kai [1 ]
Liang, Xiao-feng [1 ,2 ]
Li, Ming-zhi [1 ]
Chen, Zhe [1 ]
Yao, Yan-long [3 ]
Li, Xin [1 ]
Zhao, Zi-xiang [2 ]
Teng, Yue [1 ]
机构
[1] Shanghai Jiao Tong Univ, State Key Lab Ocean Engn, Shanghai 200240, Peoples R China
[2] Shanghai Jiao Tong Univ, Minist Educ, Key Lab Marine Intelligent Equipment & Syst, Shanghai 200240, Peoples R China
[3] Shanghai Jiao Tong Univ, Joint Inst, Shanghai 200240, Peoples R China
关键词
Global path planning; Unmanned surface vehicle; Velocity variation; Optimisation; Feature path; UNMANNED SURFACE VEHICLE; RRT-ASTERISK; A-ASTERISK; ALGORITHM; TRACKING;
D O I
10.1016/j.oceaneng.2021.109560
中图分类号
U6 [水路运输]; P75 [海洋工程];
学科分类号
0814 ; 081505 ; 0824 ; 082401 ;
摘要
Recently, the wide application of unmanned surface vehicles (USVs) in various fields has deemed path planning of USVs in complex environments, particularly in intelligent ports and busy navigation areas, as a research interest. Based on the A* algorithm, this study proposes an A* with velocity variation and global optimisation (A*VVGO) algorithm that realises velocity variation (i.e., acceleration/deceleration/stopping) to avoid obstacles during path planning by including temporal dimension in the map modelling process. This addresses the limitations of existing global path planning methods regarding the independence of path planning from the USV control stage. In addition, the operational objective function of USVs is structured in the algorithm such that the weight of the path length, time, and energy consumption can be varied in the objective function for the algorithm to generate paths with different focuses for various task requirements. Based on the real-time navigation of vessels in the nearby shared region, the developed algorithm predicts the paths of other vessels in the navigation area and realises global path optimisation for long voyages using the AIS information service platform of the China Maritime Safety Administration. Moreover, the algorithm includes an artificial potential field in the map modelling to ensure the determination of smooth and safe paths. The simulation results confirm that the application of this method can realise global optimisation based on the motion of dynamic obstacles and mission requirements. Furthermore, problems regarding existing dynamic path planning detours for avoiding dynamic obstacles in a narrow water channel can be resolved along with the simultaneous fulfilment of various operational objectives, such as navigation based on quickness or the shortest distance, or economic measures. The method proposed here demonstrates a wide application prospect in the field of USVs.
引用
收藏
页数:15
相关论文
共 50 条
[1]  
Adiyatov O, 2017, 2017 IEEE INTERNATIONAL CONFERENCE ON MECHATRONICS AND AUTOMATION (ICMA), P1416, DOI 10.1109/ICMA.2017.8016024
[2]   Multi-objective path planning of an autonomous mobile robot using hybrid PSO-MFB optimization algorithm [J].
Ajeil, Fatin H. ;
Ibraheem, Ibraheem Kasim ;
Sahib, Mouayad A. ;
Humaidi, Amjad J. .
APPLIED SOFT COMPUTING, 2020, 89
[3]   Relaxed Dijkstra and A* with linear complexity for robot path planning problems in large-scale grid environments [J].
Ammar, Adel ;
Bennaceur, Hachemi ;
Chaari, Imen ;
Koubaa, Anis ;
Alajlan, Maram .
SOFT COMPUTING, 2016, 20 (10) :4149-4171
[4]   Grid-based RRT* for minimum dose walking path-planning in complex radioactive environments [J].
Chao, Nan ;
Liu, Yong-kuo ;
Xia, Hong ;
Ayodeji, Abiodun ;
Bai, Lu .
ANNALS OF NUCLEAR ENERGY, 2018, 115 :73-82
[5]   An improved A* algorithm for searching the minimum dose path in nuclear facilities [J].
Chen, Chen ;
Cai, Jiejin ;
Wang, Zhuang ;
Chen, Facheng ;
Yi, Wenjun .
PROGRESS IN NUCLEAR ENERGY, 2020, 126
[6]   A knowledge-free path planning approach for smart ships based on reinforcement learning [J].
Chen, Chen ;
Chen, Xian-Qiao ;
Ma, Feng ;
Zeng, Xiao-Jun ;
Wang, Jin .
OCEAN ENGINEERING, 2019, 189
[7]   Research on fuzzy control of path tracking for underwater vehicle based on genetic algorithm optimization [J].
Chen, JiaWang ;
Zhu, Huangchao ;
Zhang, Lei ;
Sun, Yuxia .
OCEAN ENGINEERING, 2018, 156 :217-223
[8]   Global path planning for autonomous ship: A hybrid approach of Fast Marching Square and velocity obstacles methods [J].
Chen, Pengfei ;
Huang, Yamin ;
Papadimitriou, Eleonora ;
Mou, Junmin ;
van Gelder, Pieter .
OCEAN ENGINEERING, 2020, 214 (214)
[9]   Theta*: Any-Angle Path Planning on Grids [J].
Daniel, Kenny ;
Nash, Alex ;
Koenig, Sven ;
Felner, Ariel .
JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, 2010, 39 :533-579
[10]  
Dijkstra E. W., 1959, THESIS U AMSTERDAM