A New Landmark Detection Approach for Slam Algorithm Applied in Mobile Robot

Abstract

Simultaneous Localization and Mapping is a key technique for mobile robot applications and has received much research effort over the last three decades. [cite: 2] A precondition for a robust and life-long landmark-based SLAM algorithm is the stable and reliable landmark detector. [cite: 3] However, traditional methods are based on laser- based data which are believed very unstable, especially in dynamic-changing environments. [cite: 4] In this work, we introduce a new landmark detection approach using vision-based data. [cite: 5] Based on this approach, we exploit a deep neural network for processing images from a stereo camera system installed on mobile robots. [cite: 6] Two deep neural network models named YOLOv3 and PSMNet were re-trained and used to perform the landmark detection and landmark localization, respectively. [cite: 7] The landmark's information is associated with the landmark data through tracking and filtering algorithm. [cite: 8] The obtained results show that our method can detect and localize landmarks with high stability and accuracy, which are validated by laser-based measurement data. [cite: 9] This approach has opened a new research direction toward a robust and life-long SLAM algorithm.