Multi-UAV Cooperative Path Planning for Sensor Placement Using Cooperative Coevolving Genetic Strategy

被引:5
作者
Sorli, Jon-Vegard [1 ]
Graven, Olaf Hallan [1 ]
Bjerknes, Jan Dyre [2 ]
机构
[1] Univ Coll Southeast Norway, Kongsberg, Norway
[2] Kongsberg Def Syst, Kongsberg, Norway
来源
ADVANCES IN SWARM INTELLIGENCE, ICSI 2017, PT II | 2017年 / 10386卷
关键词
Cooperative coevolution; Multi-UAV; Genetic strategy; ALGORITHM;
D O I
10.1007/978-3-319-61833-3_46
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
With the continuing increase in use of UAVs (Unmanned Aerial Vehicles) in various applications, much effort is directed towards creating fully autonomous UAV systems to handle tasks independently of human operators. One such task is the monitoring of an area, e.g. by deploying sensors in this area utilizing a system of multiple UAVs to autonomously create an efficient dynamic WSN (Wireless Sensor Network). The locations, order and which UAV to deal with deployment of individual sensors is a complex problem which in any real life problem is deemed to be hard to solve using brute force methods. A method is proposed for multi-UAV cooperative path planning by allocation of sensor placement tasks between UAVs, using a cooperative coevolving genetic algorithm as a basis for the solution to the described challenge. Algorithms have been implemented and preliminary tested in order to show proof of concept.
引用
收藏
页码:433 / 444
页数:12
相关论文
共 14 条
[1]  
[Anonymous], 2010, INTRO EVOLUTIONARY A
[2]   Evolutionary Trajectory Planner for Multiple UAVs in Realistic Scenarios [J].
Besada-Portas, Eva ;
de la Torre, Luis ;
de la Cruz, Jesus M. ;
de Andres-Toro, Bonifacio .
IEEE TRANSACTIONS ON ROBOTICS, 2010, 26 (04) :619-634
[3]   Genetic Algorithms for Evolving Computer Chess Programs [J].
David, Omid E. ;
van den Herik, H. Jaap ;
Koppel, Moshe ;
Netanyahu, Nathan S. .
IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION, 2014, 18 (05) :779-789
[4]  
Machado P., 2002, GECCO 2002: Proceedings of the Genetic and Evolutionary Computation Conference, Morgan Kaufmann Publishers, San Francisco, CA, P690
[5]   Multi-mission Path Re-planning for Multiple Unmanned Aerial Vehicles Based on Unexpected Events [J].
Meng, Bo-bo ;
Gao, Xiaoguang ;
Wang, Yunhui .
2009 INTERNATIONAL CONFERENCE ON INTELLIGENT HUMAN-MACHINE SYSTEMS AND CYBERNETICS, VOL 1, PROCEEDINGS, 2009, :423-426
[6]  
Antonio LM, 2013, 2013 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), P2758
[7]   Three-dimensional multi-constraint route planning of unmanned aerial vehicle low-altitude penetration based on coevolutionary multi-agent genetic algorithm [J].
Peng Zhi-hong ;
Wu Jin-ping ;
Chen Jie .
JOURNAL OF CENTRAL SOUTH UNIVERSITY OF TECHNOLOGY, 2011, 18 (05) :1502-1508
[8]  
Potter MA, 1994, LECT NOTES COMPUT SC, V866, P249
[9]   Comparison of Parallel Genetic Algorithm and Particle Swarm Optimization for Real-Time UAV Path Planning [J].
Roberge, Vincent ;
Tarbouchi, Mohammed ;
Labonte, Gilles .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2013, 9 (01) :132-141
[10]   Collision avoidance and path planning of multiple UAVs using flyable paths in 3D [J].
Shanmugavel, Madhavan ;
Tsourdos, Antonios ;
White, Brian A. .
2010 15TH INTERNATIONAL CONFERENCE ON METHODS AND MODELS IN AUTOMATION AND ROBOTICS (MMAR), 2010, :218-222