Research on Unmanned System Vision SLAM Technology

摘要

The continuous development of intelligent robot technology has made more and more robots of various forms Industry use. In order to make human life more convenient, more and more researchers have devoted themselves to the field of artificial intelligence. The exploration of unknown environments by mobile robots has always been a hot and difficult point in its autonomous research. Positioning and map construction (Simultaneous Localization and Mapping, SLAM) technology is the key technology for unmanned devices to realize autonomous positioning and navigation. SLAM technology based on vision has gradually become mainstream due to its low cost. At present, SLAM algorithms based on various sensors have made significant progress, especially SLAM solutions based on visual sensors have been widely used in practice. This article firstly expounds the development status of SLAM, and analyzes the principle and mathematical model of SLAM. Then the ORB feature matching algorithm in the visual SLAM algorithm is analyzed and improved, and verified by experiments.