Diagnosing Deep SLAM for Domain-Shift Localization
Diagnosing Deep SLAM for Domain-Shift Localization
复制标题
诊断域转移定位的深度 SLAM
DOI：
10.1109/sii52469.2022.9708872
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Kanji Tanaka
中科院分区：
文献类型：
--
作者：
Mitsuki Yoshida;Kanji Tanaka
在这项研究中，我们提出了一个新的“域移定位(DSL)”问题，通过该问题，深度SLAM系统中的“用户机器人”在它们的日常导航过程中定位机器人工作空间中的域移区域。此外，我们提供了一个关于一个简单的深度SLAM系统的案例研究，该系统包括视觉位置分类器和视觉里程计，分别作为外部感觉模块和本体感觉模块。这样的DSL方法使“映射机器人”能够专注于域移位区域中的可用资源(例如，时间、能量和计算)，而不是整个工作空间，从而显著降低了每个域DNN维护的成本。与传统的SLAM诊断场景不同，深度SLAM系统包含具有黑盒特性的深度神经网络，这使得直接诊断SLAM模块的内部信号变得困难。因此，我们提出了一种新的诊断算法，该算法不依赖于内部信号，而只使用DNN的输入/输出信号作为DSL的输入。实验结果表明，与未反映故障诊断的普通深度SLAM系统相比，所提出的深度SLAM框架能够获得更接近实际测量路径的路径。
In this study, we address a novel "domain-shift localization (DSL)" problem, by which "user robots" of a deep SLAM system localize a domain-shifted region in the robot workspace during their daily navigation. Furthermore, we present a case study pertaining to a simple deep SLAM system comprising a visual place classifier and visual odometry as exteroceptive and proprioceptive modules, respectively. Such a DSL method enables "mapper robots" to focus on available resources (e.g., time, energy, and computation) in the domain-shifted region, rather than the entire workspace, thereby significantly reducing the cost of per-domain DNN maintenance. Unlike conventional scenarios of SLAM diagnosis, the deep SLAM system comprises deep neural networks (DNNs) with black-box characteristics, which render it difficult to directly diagnose the internal signals of SLAM modules. Hence, we present a novel diagnosis algorithm that does not rely on internal signals but uses only the input/output signals of DNNs as input to DSL. Experiments demonstrate that, compared with a vanilla deep SLAM system that does not reflect fault diagnosis, the proposed deep SLAM framework can achieve a path that is more similar to the actual measured GPS path.