A Survey on Visual Simultaneously Localization and Mapping

Abstract

Visual simultaneous localization and mapping (VSLAM) is an important branch of intelligent robot technology, which refers to the use of cameras as the only external sensors to achieve self-localization in unfamiliar environments while creating environmental maps. The map constructed by slam is the basis for subsequent robots to achieve autonomous positioning, path planning and obstacle avoidance tasks. This paper introduces the development of visual Slam at home and abroad, the basic methods of visual slam, and the key problems in visual slam, and discusses the main development trends and research hotspots of visual slam.