Lidar SLAM algorithm based on optimized loop closure detection
In complex environments,Simultaneous Localization and Mapping(SLAM)based on lidar will accumulate localization errors over time.To solve this problem,a lidar SLAM algorithm based on optimized loop closure detection is proposed.Using the Lidar-Iris point cloud global descriptor,the similarity between point cloud images is compared by calculating the Hamming distance of the binary image.The current key frame is compared with all the historical key frames in the database to determine the loopback key frame.The algorithm is tested on the public data set KITTI.Compared with the LeGO-LOAM algorithm,the loop closure detection performance is significantly improved.
万方数据
维普
