SYSTEM OF SIMULTANEOUS LOCALIZATION AND MAPPING ON THE BASIS OF A CoreSLAM APPROACH
D. A. Baramiya1,2, M. S. D'yakov2, S. A. Kuzikovskii2,3, M. M. Lavrentyev1,3
1Novosibirsk State University, 630090, Novosibirsk, ul. Pirogova, 2
2LLC "SoftLab-NSK", 630090, Novosibirsk, prosp. Akademika Koptyuga, 1
3Institute of Automation and Electrometry, Siberian Branch, Russian Academy of Sciences, 630090, Novosibirsk, prosp. Akademika Koptyuga, 1
Keywords: одновременная локализация и построение карты, SLAM, замыкание циклов, фильтр частиц, предсказание позиции, итеративный алгоритм ближайших точек, ICP, simultaneous localization and mapping, loop closure, particle filter, position prediction, iterative closest point algorithm
Abstract
A new method of loop closure based on storage of local maps of obstacles and meant for reducing an accumulated localization error is proposed. The advantage of this method in comparison with the earlier one is in reducing the amount of RAM. The testing results for the developed system and comparisons with analogues are presented.
|
