Simultaneous localization and mapping (SLAM) frameworks for autonomous navigation rely on robust data association to identify loop closures for back-end trajectory optimization. In the case of autonomous underwater vehicles (AUVs) equipped with multibeam echosounders (MBES), data association is particularly challenging due to the scarcity of identifiable landmarks in the seabed, the large drift in dead-reckoning navigation estimates to which AUVs are prone and the low resolution characteristic of MBES data. Deep learning solutions to loop closure detection have shown excellent performance on data from more structured environments. However, their transfer to the seabed domain is not immediate and efforts to port them are hindered by the lack of bathymetric datasets. Thus, in this paper we propose a neural network architecture aimed to showcase the potential of adapting such techniques to correspondence matching in bathymetric data. We train our framework on real bathymetry from an AUV mission and evaluate its performance on the tasks of loop closure detection and coarse point cloud alignment. Finally, we show its potential against a more traditional method and release both its implementation and the dataset used.
翻译:自主导航的同步本地化和绘图(SLAM)框架依靠强大的数据协会来确定回端轨道优化的环状封闭状态。对于配备多波束回声仪(MBES)的自主水下飞行器(AUVs)来说,由于海底缺少可识别的地标、AUVs容易接触到的对流导航估计值的大幅漂移以及MBES数据的低分辨率特征,数据组合尤其具有挑战性。循环闭合探测的深层学习解决方案在结构化环境的数据上表现良好。然而,它们向海底域的转移不是即时的,因此,由于缺乏测深数据集,无法将它们移植到海底域。因此,在本文件中,我们提出一个神经网络结构,旨在展示这种技术适应与测深数据匹配的通信的潜力。我们从AUV飞行任务中培训我们的真正测深框架,并评价其在环封闭探测和粗微点云层调节任务方面的性能。最后,我们展示其潜力与较传统的方法相对,并释放其实施和使用的数据集。