제목Efficient SLAM Scheme Based ICP Matching Algorithm Using Image and Laser Scan Information
저자명

Sanghun Han, Jaehyun So, Donghyuk Shin, Youngjoon Han

Abstract This paper proposes a scan-matching simultaneous localisation and mapping (SLAM)-based Iterative Closest Point algorithm using laser scan information and images in an indoor environment. The ICP algorithm, which is one of the scan-matching methods calculates the closest position iteratively by adjusting the motion vector and rotation matrix of the model. The matching process requires a great deal of time, in accordance with the size of the point cloud model and repetitive execution. The proposed method uses part of the feature model and performs the matching by setting up the adjusting range of the motion vector and rotation matrix through the maximum velocity of a mobile robot. It then estimates the pose of the mobile robot using the relationship between the models. In order to evaluate the efficiency of the proposed algorithm, experiments driving the mobile robot were executed, such as estimating the pose of the mobile robot and building a map.
원문 수록처

Proceedings of the 2nd International Conference on Machine Vision and Machine Learning

Barcelona, Spain-July 13-14, 2015

Paper No.335

자료유형International Conference