论文/arXiv 2609.24195·1 个月前

使用前视声呐的水下机器人里程计辅助实时建图

面向水下低能见度中的FLS实时建图难题，提出级联特征重建与姿态感知投影，在3 m×5 m水池验证2.5D局部建图。

AI 整理

• 感知与导航
• 端侧部署

原文链接：Odometry-Aided Real-Time Mapping for Underwater Robots Using Forward-Looking Sonar（arXiv 2609.24195 · 发布日期：2026-09-21）

Odometry-Aided Real-Time Mapping for Underwater Robots Using Forward-Looking Sonar

面向水下低能见度中的FLS实时建图难题，提出级联特征重建与姿态感知投影，在3 m×5 m水池验证2.5D局部建图。

核心要点

• 低可见环境削弱光学感知，FLS虽可声学成像，但高程缺失、非均匀噪声和边界碎片阻碍实时建图。
• 方法结合FFT去噪、快速MCFAR检测和梯度自适应边界连接，低延迟提取退化声呐图像几何特征。
• 通过姿态感知几何投影和增量占据累积，构建有深度参考的2.5D局部地图。
• 3 m×5 m水池三段序列RMSE低于3 cm，平均每帧处理42.4 ms；目标高程基于显式几何假设赋值。

验证范围与局限：仅在3 m×5 m水池的三段序列中验证，目标高程由几何假设赋值而非FLS直接测量。

英文摘要 (Abstract)

Reliable perception is essential for underwater vehicles operating in complex environments, where light attenuation and scattering often degrade visibility and compromise optical sensing. Forward-looking sonar (FLS) offers an alternative by providing high-frame-rate acoustic imaging under poor optical conditions. However, real-time FLS mapping remains challenging due to unresolved target elevation, spatially non-uniform noise, and fragmented target boundaries, which hinder feature extraction and introduce geometric ambiguity during projection. To address these challenges, we propose a cascaded feature reconstruction pipeline combining fast Fourier transform (FFT)-based denoising, fast multiscale constant false alarm rate (MCFAR) detection, and gradient-adaptive boundary connection to extract geometric features from degraded sonar images with low latency. We integrate attitude-aware geometric projection with incremental occupancy accumulation to construct a depth-referenced 2.5D map for local mapping in confined underwater environments. The sonar's vertical position is referenced to an external sensor, while target elevation is assigned under an explicit geometric assumption rather than measured directly by FLS. Experiments in a 3 m X 5 m pool demonstrate centimeter-scale planar mapping accuracy, with a root-mean-square error (RMSE) below 3 cm across three sequences and an average processing time of 42.4 ms per frame.

作者：Siyuan Du, Kanzhong Yao, Youdong Wang, Yingqi Liu, Qingwen Liu, Qunhui Yang, Zhe Sun, Xuelong Li

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2609.24195：Odometry-Aided Real-Time Mapping for Underwater Robots Using Forward-Looking Sonar访问 2026-10-21