基于多传感器融合SLAM的无人船靠泊技术

贾薇, 王宁, 张富宇, 张雪峰, 李洁龙, 吴浩峻, 孙赫男

doi:10.16411/j.cnki.issn1006-7736.2023.04.008

大连海事大学学报 >

2023 , Vol. 49 >Issue 4: 65 - 75

DOI: https://doi.org/10.16411/j.cnki.issn1006-7736.2023.04.008

基于多传感器融合SLAM的无人船靠泊技术

展开

(1. 大连海事大学 a. 轮机工程学院；b. 船舶电气工程学院，辽宁大连 116026；2. 大连海事局甘井子海事处，辽宁大连 116000）

贾薇（2000 — ），女，硕士生，研究方向：路径规划，航行决策。王宁*（1983 — ），男，博士，教授，博士生导师，研究方向：智能绿色船舶，无人艇及海洋机器人，海洋人工智能，无人系统自主控制。E-mail: n.wang@ieee.org。

收稿日期: 2023-06-04

修回日期: 2023-09-20

录用日期: 2023-09-20

网络出版日期: 2023-09-20

基金资助

国防基础科研计划基础前沿寻宝项目（JCKY2022410C013）

收起

Unmanned surface vehicle berthing technology based on multi-sensor fusion SLAM

Expand

(1a. Marine Engineering College; 1b. Marine Electrical Engineering College, Dalian Maritime University, Dalian 116026, China; 2. Ganjingzi Marine Department, Dalian Maritime Safety Administration, Dalian 116000, China)

Received date: 2023-06-04

Revised date: 2023-09-20

Accepted date: 2023-09-20

Online published: 2023-09-20

Fold

摘要

面向港口区域无人船自主靠泊应用需求，从提高无人船环境感知精度与定位能力角度，提出一种基于多传感器融合同时定位与地图构建（SLAM）的无人船自主靠泊技术。对可航行区域动态变化导致的卫星地图时效性差、环境表征不完备问题，提出水上-水下一体化精准感知方案以获取可通行信息。对卫星定位偏差大、姿态信息获取难的问题，利用无人船实时感知的深度信息与先验点云地图匹配，获取精准的位姿信息。考虑到靠泊时对船舶特定姿态的需求，建立船舶运动模型和避碰模型，通过船舶操纵试验获取无人船运动性能参数，并将其作为Reeds-Shepp优化曲线的约束条件，消除轨迹上的尖锐拐点。根据真实数据构建无人船、传感器及港口环境模型，并进行自主航行靠泊仿真实验。结果表明，本文提出的多传感器融合SLAM的无人船自主靠泊技术可精准完成港口靠泊任务。

关键词： 无人船（USV）; 港口靠泊; 路径规划; 多传感器融合; 同时定位与地图构建(SLAM)

本文引用格式

贾薇, 王宁, 张富宇, 张雪峰, 李洁龙, 吴浩峻, 孙赫男 . 基于多传感器融合SLAM的无人船靠泊技术[J]. 大连海事大学学报, 2023 , 49(4) : 65 -75 . DOI: 10.16411/j.cnki.issn1006-7736.2023.04.008

Abstract

Aiming at the application requirements of autonomous berthing of unmanned surface vehicles(USV) in harbor areas, the autonomous berthing technology of USV based on multi-sensor fusion of simultaneous localization and mapping(SLAM) was proposed from the perspective of enhancing environmental perception accuracy and location ability. In order to solve the problems of poor timeliness and incomplete environmental representation caused by the dynamic changes in navigable areas, an integrated accurate sensing scheme of water-underwater was proposed to obtain passable information. Aiming at the problem of large satellite positioning deviation and difficult to obtain attitude information, the depth information sensed by USV in real time was matched with the prior point cloud map to obtain accurate position and attitude information. Considering the demand for specific attitude of the USV during berthing, the USV motion model and collision avoidance model were established, and the motion performance parameters of the USV were obtained by using ship manipulation tests,and took it as the constraints of the Reeds-Shepp optimization curve to eliminate the sharp inflection points on the trajectory. According to the real data, the USV model, sensor model and port environment model were constructed for autonomous navigation berthing simulation experiments, and results show that the proposed autonomous berthing technology of USV based on multi-sensor fusion SLAM can complete accurately harbor berthing task.

Key words： unmanned surface vehicle（USV）; harbor berthing; path planning; multi-senor fusion; simulationeous localization and mapping（SLAM）

参考文献

[1]WANG S J. Brave to do intelligent ship no man's land pathfinder[J]. China Ship Survey, 2020, 237(2): 20-23．
[2]鲁德伟，韩晓宝，牛志斌.无人船在港口水域海事监管中的应用探讨[J]，中国海事, 2020, 174(1): 43-45.
LU D W, HAN X B, NIU Z B. Discussion on the application of unmanned vessel on maritime supervision within port sea area[J]. China Maritime Safety, 2020, 174(1): 43-45. (in Chinese)
[3]HAN J, CHO Y, KIM J, et al. Autonomous collision detection and avoidance for ARAGON USV: Development and field tests[J]. Journal of Field Robotics, 2020, 37(6): 987-1002.
[4]张英俊, 翟鹏宇. 海运船舶自主避碰技术研究进展与趋势[J]. 大连海事大学学报, 2022, 48(3):1-11.
ZHANG Y J, CUI P Y. An autonomous obstacle avoidance method for unmanned vehicles facing unstable obstacles[J]. Journal of Dalian Maritime University, 2022,48(3):1-11.(in Chinese)
[5]LIU J, ZHAN J, GUO C, et al. Data logic structure and key technologies on intelligent high-precision map[J]. Journal of Geodesy and Geoinformation Science, 2020,3(3):1.
[6]SANKALPRAJAN P, MUPPIDI A J, PAGALA P S. Analysis of Computational Need of 2D-SLAM Algorithms for Unmanned Ground Vehicle[C]//2020 4th International Conference on Intelligent Computing and Control Systems (ICICCS). IEEE, 2020: 230-235.
[7]WANG W, SHAN T, LEONI P, et al. Roboat II: A novel autonomous surface vessel for urban environments[C]//2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE,2020: 1740-1747.
[8]CHENG Y, JIANG M, ZHU J, et al. Are we ready for unmanned surface vehicles in inland waterways? The usvinland multisensor dataset and benchmark[J]. IEEE Robotics and Automation Letters,2021,6(2):3964-3970.
[9]ZHOU B, HE Y, QIAN K, et al. S4-SLAM: A real-time 3D LIDAR SLAM system for ground/watersurface multi-scene outdoor applications[J]. Autonomous Robots, 2021,45:77-98.
[10]包涛, 周则兴, 陈卓, 等. 面向不稳定障碍物的无人艇自主避障方法[J]. 大连海事大学学报,47(3):8-15.
BAO T, ZHOU Z X, CHEN Z, et al. An autonomous obstacle avoidance method for unmanned vehicles facing unstable obstacles[J]. Journal of Dalian Maritime University,47(3):8-15.(in Chinese)
[11]崔金龙, 李元奎, 索基源, 等. 基于改进 A* 算法的船舶航向航速协同优化方法[J]. 大连海事大学学报,48(4):29-37.
CUI J L, LI Y K, SUO J Y, et al. Ship heading speed co-optimization method based on improved A* algorithm[J]. Journal of Dalian Maritime University,48(4):29-37.(in Chinese)
[12]LIAO Y, JIA Z, ZHANG W, et al. Layered berthing method and experiment of unmanned surface vehicle based on multiple constraints analysis[J]. Applied Ocean Research,2019,86:47-60.
[13]SUYAMA R, MIYAUCHI Y, MAKI A. Ship trajectory planning method for reproducing human operation at ports[J]. Ocean Engineering,2022,266:112763.
[14]SHI Y, WANG P, WANG X. An Autonomous Valet Parking Algorithm for Path Planning and Tracking[C]//2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall). IEEE,2022:1-7.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献