Department of Electrical and Computer Engineering, Seoul National University, Seoul, Republic of Korea
Abstract—This paper suggests enhanced map building framework based on the scan similarity. Previous map building techniques which are applied various scan matching algorithms are usually dependent on the geometrical structure of the environment. However, those techniques do not consider the property of the scan matching algorithms. Our proposed method represents the geometrical information of the scan data compactly and computes the similarity between scan data to increase the accuracy of the map and the estimated robot pose. Through the experiments, we compared the result of our proposed map building framework with that of the previous one and also verified our new approach shows higher accuracy than the previous method.
—map building, SLAM, robot, scan matching, scan similarity
Cite: Wonsok Yoo, Seung-Hwan Lee, and Beom H. Lee, "An Enhanced Map Building Framework Based on the Scan Similarity," International Journal of Mechanical Engineering and Robotics Research, Vol. 5, No. 1, pp. 39-42, January 2016. DOI: 10.18178/ijmerr.5.1.39-42