Towards Generation and Evaluation of Comprehensive Mapping Robot\n Datasets

Abstract

This paper presents a fully hardware synchronized mapping robot with support\nfor a hardware synchronized external tracking system, for super-precise timing\nand localization. We also employ a professional, static 3D scanner for ground\ntruth map collection. Three datasets are generated to evaluate the performance\nof mapping algorithms within a room and between rooms. Based on these datasets\nwe generate maps and trajectory data, which is then fed into evaluation\nalgorithms. The mapping and evaluation procedures are made in a very easily\nreproducible manner for maximum comparability. In the end we can draw a couple\nof conclusions about the tested SLAM algorithms.\n