Added the Odometry Optimized SLAM Loop Closure Detection System

Abstract

Simultaneous localization and mapping (SLAM) in an unknown environment has always been one of the research focus of mobile robots. Loop closure detection is a key step in SLAM system. In this paper, a laser SLAM loop closure detection method with odometry optimization is proposed. The lidar point cloud data is processed, and the estimated value of the lidar odometry is optimized by registering planar points and edge points. Coupling segment matching loop closure detection module reduces the missed detection rate and optimizes the global map. Finally, this method was evaluated on the Kitti datasets, and the successful loop closure detection after the addition of the odometry optimization was demonstrated. Experimental results show that this method can indeed reduce the possibility of loop closure detection failure and improve the stability of the SLAM system.