On the application of RGB-D SLAM systems for practical localization of mobile robots

This paper considers the practical application of the RGBD Simultaneous Localization and Mapping (SLAM) techniques for localization of mobile robots. We attempt to answer the question: how the quality of the estimated sensor trajectory depends on the approach to RGB-D data processing in the SLAM system when RGB-D frames acquired on a real mobile robot are used. Experiments are performed on data obtained from robots of different classes, and from different environment types to present the problems characteristic to RGB-D data. Conclusions as to the robustness of particular architectures and solutions applied in SLAM are drawn on the basis of experimental results. Publicly available data sets and well-established performance metrics are used to ensure that the results are verifiable, reproducible and relevant

---

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę (zadania 2017)