Abstract
The accuracy of localization and mapping of automated guided vehicles (AGVs) using visual simultaneous localization and mapping (SLAM) is significantly reduced in a dynamic environment compared to a static environment due to incorrect data association caused by dynamic objects. To solve this problem, a robust stereo SLAM algorithm based on dynamic region rejection is proposed. The algorithm first detects dynamic feature points from the fundamental matrix of consecutive frames and then divides the current frame into superpixels and labels its boundaries with disparity. Finally, dynamic regions are obtained from dynamic feature points and superpixel boundaries types; only the static area is used to estimate the pose to improve the localization accuracy and robustness of the algorithm. Experiments show that the proposed algorithm outperforms ORB-SLAM2 in the KITTI dataset, and the absolute trajectory error in the actual dynamic environment can be reduced by 84% compared with the conventional ORB-SLAM2, which can effectively improve the localization and mapping accuracy of AGVs in dynamic environments.
Highlights
With the rapid development of industrial automation, automated guided vehicles (AGVs) have been widely used in the fields of material transportation, smart storage, and power grid inspection
The results demonstrate the effectiveness of the proposed simultaneous localization and mapping (SLAM) algorithm in various dynamic environments
Since there are no publicly available datasets for dynamic objects, the data used in this experiment are images from the KITTI dataset [30] containing dynamic objects and a photo set taken by the AGV in real scenes
Summary
With the rapid development of industrial automation, automated guided vehicles (AGVs) have been widely used in the fields of material transportation, smart storage, and power grid inspection. Magnetic guidance must arrange magnetic tapes or magnetic nails in the working area and use the magnetic sensor on the AGV to identify and track these magnetic materials to complete navigation. This method has poor anti-interference ability and low accuracy. After several decades of development, many impressive SLAM systems have emerged, e.g., ORB-SLAM [6], LSD-SLAM [7], and DSO [8] These algorithms are designed based on the assumption that objects in the scene are stationary [9] and interference from dynamic objects would directly affect localization and mapping accuracy. The results demonstrate the effectiveness of the proposed SLAM algorithm in various dynamic environments
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
