Open AccessSLAM in Duckietown Simulator Using the OpenVSLAM Framework
Author(s) -
A. D. Devyatovskaya,
N. E. Biryuchkov,
Tatiana Liakh,
Konstantin Chaika
Publication year - 2022
Publication title -
vestnik novosibirskogo gosudarstvennogo universiteta. seriâ: informacionnye tehnologii/vestnik novosibirskogo gosudarstvennogo universiteta. seriâ: informacionnye tehnologii v obrazovanii
Language(s) - English
Resource type - Journals
eISSN - 2410-0420
pISSN - 1818-7900
DOI - 10.25205/1818-7900-2021-19-4-36-49
Subject(s) - computer science , task (project management) , robot , mobile robot , simultaneous localization and mapping , simulation , human–computer interaction , artificial intelligence , systems engineering , engineering
The article is devoted to evaluating the applicability of SLAM frameworks for the task of mobile robots of the Duckietown project. The paper provides a comparative analysis of existing SLAM algorithms and frameworks and se-lects frameworks taking into account all the constraints imposed by the project robots. The practical results of testing OpenVSLAM framework on the Duckietown environment and Duckietown simulator data are presented.