Título: SLAM baseado em Scan-Matching com Otimização por Enxame de Partículas
Autores: Oliveira, Pedro Jorge;Nedjah, Nadia;Mourelle, Luiza
This paper presents a method for solving the problem of Simultaneous Localization and Mapping (SLAM) based on the application of Particle Swarm Optimization (PSO) to the estimation of occupancy grid maps from laser scan data. The registration task is cast in the form of a nonlinear optimization problem and used to get an adequate approximation of the relative motion of the robot in between data frames. The method presented has the advantage of requiring no landmarks and being fast enough to perform online. Furthermore, we elaborate on how to tune the parameters of the algorithm to obtain satisfactory results.
Código DOI: 10.21528/CBIC2017-96
Artigo em pdf: cbic-paper-96.pdf
Arquivo BibTeX: cbic-paper-96.bib