深層生成モデルとパーティクルフィルタの融合による自己位置推定

抄録

The purpose of this research is to construct a probabilistic model of observation from data for the problem of self-position estimation from camera images. In this paper, we propose a method to fuse particle filters with probabilistic distribution images of the robot’s position and posture generated using a deep generative model called Conditional Variational Autoencoder（CVAE）. To evaluate the effectiveness of the proposed method, experiments and evaluations were conducted on self-position estimation using single images and particle filter, respectively. As a result, the estimation error was reduced by fusing the generated image and particle filter, confirming the effectiveness of the proposed method.