[1]沈海青,郭晨,李铁山,等.考虑航行经验规则的无人船舶智能避碰导航方法[J].哈尔滨工程大学学报,2018,39(06):998-1005.[doi:10.11990/jheu.201711024]
 SHEN Haiqing,GUO Chen,LI Tieshan,et al.An intelligent collision avoidance and navigation approach of unmanned surface vessel considering navigation experience and rules[J].hebgcdxxb,2018,39(06):998-1005.[doi:10.11990/jheu.201711024]
点击复制

考虑航行经验规则的无人船舶智能避碰导航方法(/HTML)
分享到:

《哈尔滨工程大学学报》[ISSN:1006-6977/CN:61-1281/TN]

卷:
39
期数:
2018年06期
页码:
998-1005
栏目:
出版日期:
2018-06-05

文章信息/Info

Title:
An intelligent collision avoidance and navigation approach of unmanned surface vessel considering navigation experience and rules
作者:
沈海青1 郭晨1 李铁山2 余亚磊2
1. 大连海事大学 船舶电气工程学院, 辽宁 大连 116026;
2. 大连海事大学 航海学院, 辽宁 大连 116026
Author(s):
SHEN Haiqing1 GUO Chen1 LI Tieshan2 YU Yalei2
1. College of Marine Electrical Engineering, Dalian Maritime University, Dalian 116026, China;
2. Navigation College, Dalian Maritime University, Dalian 116026, China
关键词:
深度竞争Q学习A*算法无人船舶避碰导航避碰规则航行经验
分类号:
U675.7
DOI:
10.11990/jheu.201711024
文献标志码:
A
摘要:
针对无人船舶在海上复杂航行条件下的自动避碰问题,基于深度竞争Q学习算法及A*算法提出了一种考虑航行经验和避碰规则的无人船舶智能避碰导航方法。通过在强化学习避碰任务和A*局部动态导航的设计中融入船舶的操纵特性,缩减了模型训练和A*算法路径规划的时间,以及将避碰经验规则转化成动态的航行限制线以获得本船周围的全部可航区域,并从全局角度衡量本船的航行态势做出避碰决策,使得避碰决策符合国际海上避碰规则和避让经验的要求。在开阔水域和受限水域中完成的仿真结果表明该方法能够成功避让所有船舶和静态障碍物,具有重要的工程应用价值。

参考文献/References:

[1] STATHEROS T, HOWELLS G, MAIER K M. Autonomous ship collision avoidance navigation concepts, technologies and techniques[J]. The journal of navigation, 2008, 61(1):129-142.
[2] XUE Yanzhou, CLELLAND D, LEE B S, et al. Automatic simulation of ship navigation[J]. Ocean engineering, 2011, 38(17/18):2290-2305.
[3] CAMPBELL S, NAEEM W. A rule-based heuristic method for COLREGS-compliant collision avoidance for an unmanned surface vehicle[J]. IFAC proceedings volumes, 2012, 45(27):386-391.
[4] TANG Pingpeng, ZHANG Rubo, LIU Deli, et al. Local reactive obstacle avoidance approach for high-speed unmanned surface vehicle[J]. Ocean engineering, 2015, 106:128-140.
[5] PERERA L P, CARVALHO J P, GUEDES S C. Intelligent ocean navigation and fuzzy-Bayesian decision/action formulation[J]. IEEE journal of oceanic engineering, 2012, 37(2):204-219.
[6] 李丽娜, 王俊玲, 陈国权. 船舶拟人智能避碰决策理论的集成机器学习策略[J]. 信息与控制, 2011, 40(3):359-368.LI Lina, WANG Junling, CHEN Guoquan, Integrated machine learning strategy of PIDVCA theory[J]. Information and control, 2011, 40(3):359-368.
[7] 刘德新, 吴兆麟, 贾传荧. 船舶智能避碰决策与控制系统研究综述[J]. 大连海事大学学报, 2003, 29(3):52-56.LIU Dexin, WU Zhaolin, JIA Chuanying. A summary of recent researches on ship’s intelligent collision avoidance decision-making and controlling system[J]. Journal of Dalian maritime university, 2003, 29(3):52-56.
[8] 康与涛, 朱大奇, 陈伟炯. 船舶避碰路径规划研究综述[J]. 船海工程, 2013, 42(5):141-145.KANG Yutao, ZHU Daqi, CHEN Weijiong. Review of research on collision avoidance path planning for ships[J]. Ship & ocean engineering, 2013, 42(5):141-145.
[9] ZHUO Yongqiang, HEARN G E. A ship based intelligent anti-collision decision-making support system utilizing trial manoeuvres[C]//Proceedings of 2008 Chinese Control and Decision Conference. Yantai, Shandong, China, 2008:3982-3987.
[10] TAM C, BUCKNALL R, GREIG A. Review of collision avoidance and path planning methods for ships in close range encounters[J]. The journal of navigation, 2009, 62(3):455-476.
[11] IMO. Convention on the International Regulations for Preventing Collisions at Sea (COLREGs)[Z]. London:1972.
[12] MNIH V, KAVUKCUOGLU K, SILVER D, et al. Human-level control through deep reinforcement learning[J]. Nature, 2015, 518(7540):529-533.
[13] WANG Ziyu, SCHAUL T, HESSEL M, et al. Dueling network architectures for deep reinforcement learning[C]//Proceedings of the 33rd International Conference on Machine Learning. London, UK, 2015.
[14] HARA K. Proposal of maneuvering standard to avoid collision in congested sea area[J]. The journal of Japan institute of navigation, 1991, 85:33-40.
[15] BANDI S, THALMANN D. Path finding for human motion in virtual environments[J]. Computational geometry, 2000, 15(1/2/3):103-127.
[16] GOODWIN E M. A statistical study of ship domains[J]. The journal of navigation, 1975, 28(3):328-344.
[17] MIERZCHALSKI R. Ships’ domains as collision risk at sea in the evolutionary method of trajectory planning[J]. Computer information and applications, 2004, 2:117-125.
[18] BOLE A G, DINELEY B, WALL A. Radar and ARPA manual[M]. 2nd ed. London:Elsevier, 2005.
[19] 王世远, 施智标. PAD及其局限性[J]. 上海海运学院学报, 1985(1):15-24.WANG Shiyuan, SHI Zhibiao. PAD and its limitation[J]. Journal of Shanghai maritime institute, 1985(1):15-24.

备注/Memo

备注/Memo:
收稿日期:2017-11-07。
基金项目:国家自然科学基金项目(51579024,61374114);辽宁省教育厅重点实验室基础项目(LZ2015006);中央高校基本科研业务专项资金项目(3132016311,3132016313,3132017114).
作者简介:沈海青(1987-),男,博士研究生;郭晨(1956-),男,教授,博士生导师.
通讯作者:郭晨,E-mail:dmuguoc@126.com
更新日期/Last Update: 2018-06-01