New trends on computer vision applied to mobile robot localization

Abstract

This work presents a systematic review of computer vision techniques for locating mobile robots. Its main objectives are to analyze the latest technology in use to locate mobile robots. In addition, this work violated the advances achieved so far, assesses the challenges to be overcome and provides an analysis of future prospects. There is a lot of research related to the location of mobile robots, but the number of review articles on the topic is small, which makes this work of remarkable value. The research covered the works published in Web of Science, Scopus, Science Direct and IEEEXplore until June 2021. Each work found proposes a vision-based localization technique. After being analyzed individually, it can be concluded that it is necessary to assess the level of accuracy of these techniques through a single standard, it is necessary to assess the cost-benefit of the computational cost and the need for more powerful computers or systems to perform the localization task. Finally, the main contributions of this work are the creation of a table summarizing the main methods of localization by computer vision, the statistical analysis performed on the keywords of the selected works and providing an overview of this line of research that can be a basis for future research.