2024年12月16日 · The SLAM system utilizes graph optimization to enhance localization and mapping accuracy, ultimately generating an accurate global trajectory and a global map that support reliable navigation for the USV in inland waterway scenarios.

mastr1325是一个新的大规模海洋语义分割训练数据集，专门用于开发小型沿海usv的障碍物检测方法。该数据集包含了在两年时间内用真实的usv捕获的1325幅不同的图像，涵盖了在沿海监视任务中遇到的一系列现实条件。

2019年1月3日 · In this study, the relative navigation with respect to the surrounding coastlines is performed in the framework of simultaneous localization and mapping (SLAM) for a USV operation in coastal waters. In particular, coastline features are parameterized by using B-splines for efficient map management, instead of the conventional point cloud ...

2021年3月12日 · 最近，欧卡智舶联合清华大学与西北工业大学的研究学者公开了一个针对真实内河水域场景下多传感器、多天气条件下的内河无人船数据集USVlnland 。 为无人船及水面自动驾驶领域相关研究者提供一个平台和基准，推动解决内河无人船在真实场景应用中面临的挑战。 近年来，内河无人船因其潜在的应用价值而受到广泛关注，不同于海面无人船和路面自动驾驶场景，内河行驶的无人船的定位和感知面临着独特的挑战。

2023年2月1日 · To satisfy the USV positioning needs in the positioning satellite signal obscured areas, such as under a dock or bridge or in a tunnel, we propose a LiDAR SLAM-assisted unmanned surface vessel fusion positioning method ‘Navigation of USV’, abbreviated as NavUSV, which adopts a carrier-based phase-difference separation based GNSS/INS loosely ...

To meet the requirement of perception and localization for USV in real-world inland waterways, the dataset mainly contains three tasks: SLAM/odometry, stereo matching, and water segmentation.

To address the challenges of visual SLAM algorithms in unmanned surface vehicles (USVs) during nearshore navigation or docking, where dynamic feature points degrade localization accuracy and dynamic objects impede static dense mapping, this study proposes an improved visual SLAM algorithm that removes dynamic feature points. Building upon the ORB-SLAM3 framework, the improved SLAM algorithm ...

针对这些问题，本文提出一种基于改进LIO-SAM（Lidar Inertial Odometry via Smoothing and Mapping）的USV（Unmanned Surface Vehicle）激光SLAM（Simultaneous Localization and Mapping）算法。 首先，通过优化惯性测量单元预积分过程，在保持算法水面动态环境下精度的同时，降低了计算负担；其次，引入了一种基于复合滤波的水波干扰抑制方法，降低了水波对激光SLAM的影响；最后，采用了一种改进的图优化方法，有效解决了局部极值问题。 实验结果表 …

2024年12月16日 · Therefore, this paper proposes a laser-based simultaneous localization and mapping (SLAM) algorithm for accurate localization and mapping in inland waterway scenarios. Inertial measurement unit...

2016年1月1日 · In this paper, a radar-based localization via automatic map matching is proposed for unmanned surface vehicle (USV) navigation in a littoral area. A pulse radar is employed to collect surrounding coastline information, and relative position of the vehicle with respect to the pre-built map is estimated by coastline matching.