Research on SLAM Algorithm for Mobile Robots Based on LIDAR/RGBD Camera Fusion
AN He
CUI Min
ZHANG Peng
LIU Peng
Abstract：In order to solve the problems of insufficient environmental information description and low mapping accuracy in the process of map construction using separate 2D LiDAR and RGBD cameras,this study proposes a SLAM algorithm based on infor-mation fusion of 2D LiDAR and RGBD cameras.Firstly,this paper obtains the camera's internal and external parameters through joint calibration,and establishes the conversion relationship between laser data and radar data.Secondly,time interpolation method is used to complete the laser frame at the corresponding visual frame,in order to achieve time synchronization of the two types of da-ta.Finally,a weighted error joint loss function is introduced to optimize the mapping and localization effects.The experimental re-sults show that in the testing of long corridor environments with single features and complex indoor environments,compared with a single SLAM,this algorithm has achieved significant improvement in both mapping and localization.Compared to laser SLAM,the positioning accuracy is improved by 17％,and compared to visual SLAM,the fusion accuracy is improved by 24％.
Keywords：2D LiDARRGBD camerainformation fusionsimultaneous localization and mapping(SLAM)
Publication Date：2025-12-20
Online Publishing Date：2026-03-23(First online date of this platform, not the publication date of the document)
Pages：6( 200-205 )