Scan Similarity-based Pose Graph Construction method for Graph SLAM

Scan similarity-based pose graph construction method for graph SLAM is proposed. To perform delicate pose graph SLAM, front-end that constructs a graph as well as back-end that optimizes the constructed graph is an important task. Generally, there is an error accumulation phenomenon during the odometry estimation process. This paper focuses on the method of creating a high quality graph by suggesting ways to improve the graph accuracy since the accumulated errors in the graph might degrade the performance of the entire graph SLAM. We deal with one of our previous works, dynamic keyframe selection technique, based on scan similarity computation method more precisely and suggest a loop closure detection method by exploiting previously proposed 2-D laser scan descriptor. To verify objective performance of the proposed method, the experimental results of the odometry estimation are shown by using the benchmark dataset and the real world dataset. Additionally, results of the pose graph SLAM are shown for the real world dataset which include the loop clorues.