An Optimized Fuzzy Control Algorithm for Three-Dimensional AUV Path Planning

被引:79
作者
Sun, Bing [1 ]
Zhu, Daqi [2 ]
Yang, Simon X. [3 ]
机构
[1] Shanghai Maritime Univ, Lab Underwater Vehicles & Intelligent Syst, Informat Engn, Haigang Ave 1550, Shanghai 201306, Peoples R China
[2] Shanghai Maritime Univ, Informat Engn Coll, Lab Underwater Vehicles & Intelligent Syst, Haigang Ave 1550, Shanghai 201306, Peoples R China
[3] Univ Guelph, Sch Engn, Adv Robot & Intelligent Syst Lab, Guelph, ON N1G 2W1, Canada
基金
中国国家自然科学基金;
关键词
AUV; Fuzzy controller; Velocity synthesis approach; Quantum; behaved particle swarm optimization; Three-dimensional path planning; AUTONOMOUS UNDERWATER VEHICLES; SONAR;
D O I
10.1007/s40815-017-0403-1
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Path planning is an important issue for autonomous underwater vehicle (AUV) underwater mission. In this paper, an optimized fuzzy control algorithm is proposed for three-dimensional (3D) AUV path planning. Based on the sonar model, it can be used for path planning in the complex underwater environment. First, the path planning is established based on the two sonars arranged on the horizontal plane and vertical plane. On the environment information collected by sonars, the virtual acceleration and velocity of AUV in the three-dimensional space can be obtained through the fuzzy system with accelerate/break module which enables AUV to avoid dynamic obstacles automatically. Considering the fuzzy boundary choice has great subjectivity, the generated path cannot guarantee to be optimal. Therefore, in order to deal with this problem, two optimized methods are compared to do the optimization of the fuzzy set. Simulation results indicate that the proposed method can generate an optimal 3D path under three-dimensional underwater environment and can be used in real case in the future.
引用
收藏
页码:597 / 610
页数:14
相关论文
共 24 条
[1]   Observer-Based Adaptive Neural Network Trajectory Tracking Control for Remotely Operated Vehicle [J].
Chu, Zhenzhong ;
Zhu, Daqi ;
Yang, Simon X. .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2017, 28 (07) :1633-1645
[2]  
Ganesan V., 2015, AUTON ROBOT, V39, P1
[3]   Underwater Data Collection Using Robotic Sensor Networks [J].
Hollinger, Geoffrey A. ;
Choudhary, Sunav ;
Qarabaqi, Parastoo ;
Murphy, Christopher ;
Mitra, Urbashi ;
Sukhatme, Gaurav S. ;
Stojanovic, Milica ;
Singh, Hanumant ;
Hover, Franz .
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2012, 30 (05) :899-911
[4]   A Hybrid Chaos-Particle Swarm Optimization Algorithm for the Vehicle Routing Problem with Time Window [J].
Hu, Wenbin ;
Liang, Huanle ;
Peng, Chao ;
Du, Bo ;
Hu, Qi .
ENTROPY, 2013, 15 (04) :1247-1270
[5]   Application of cellular automata and type-2 fuzzy logic to dynamic vehicle path planning [J].
Huang, Chenn-Jung ;
Wang, Yu-Wu ;
Chen, Heng-Ming ;
Tsai, Han-Wen ;
Jian, Jui-Jiun ;
Cheng, Ai-Lin ;
Liao, Jia-Jian .
APPLIED SOFT COMPUTING, 2014, 19 :333-342
[6]  
Khatib O., 1986, 1985 INT C ROB AUT, P500
[7]  
Li I., 2016, INT J FUZZY SYST, V18, P1
[8]   Neural-Dynamics-Driven Complete Area Coverage Navigation Through Cooperation of Multiple Mobile Robots [J].
Luo, Chaomin ;
Yang, Simon X. ;
Li, Xinde ;
Meng, Max Q. -H. .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2017, 64 (01) :750-760
[9]   Research of biogeography particle swarm optimization for robot path planning [J].
Mo, Hongwei ;
Xu, Lifang .
NEUROCOMPUTING, 2015, 148 :91-99
[10]   A behavior-based approach for collision avoidance of mobile robots in unknown and dynamic environments [J].
Nakhaeinia, D. ;
Karasfi, B. .
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2013, 24 (02) :299-311