Novo algoritmo para fusão de mapas invariantes a escala, rotação e translação

Gardado en:
Detalles Bibliográficos
Autor Principal: Ferrão, Victor Terra
Data de Publicación: 2018
Formato: Master thesis
Idioma: por
Fonte: Repositório Institucional da UFG
Download full: http://repositorio.bc.ufg.br/tede/handle/tede/9168
Summary: This work presents a new algorithm that works on the problem of merging occupation maps obtained by different autonomous agents and all the steps taken to develop it. This new method can combine maps, invariant to scale, rotation and translation. During each stage of development, it was compared directly with pre-existing agorithms using both data set and simulated environment. Comparative tables and images are shown between algorithms and versions of the proposed algorithm in each of the tests performed. The new algorithm demonstrates to be faster and also more robust. Finally, the present text tries to show this evolutionarily so as to understand better the modifications introduced.