Deep Learning Applications in Simultaneous Localization and Mapping

Abstract

Simultaneous Location and Mapping (SLAM) is a research hotspot in the field of intelligent robots in recent years. Its processing object is the visual image. Deep learning has achieved great success in the field of computer vision, which makes the combination of deep learning and slam technology a feasible scheme. This paper summarizes some applications of deep learning in SLAM technology and introduces its latest research results. The advantages and disadvantages of deep-learning-based-SLAM technology are compared with those of traditional SLAM. Finally, the future development direction of SLAM plus deep learning technology is prospected.