抄録
In this study, we aim at achieving an autonomous locomotion of the mobile robot in the unknown indoor environment. In priori research, landmark construction based on image and shape features is proposed and the effectiveness of combined landmark is verified by simulation and experiment. We propose a automatic construction method of combined landmark from image and point cloud. To devide attracted scene, we clustering image and shape feature point and calculate each feature value. If image and shape feature value are more than threshold, this method decide that the cluster is landmark. The effectiveness of proposed method is verified by experiment.
