Road Boundary Estimation for Mobile Robot using Deep Learning and Particle Filter

Abstract

This research aims to develop a method of estimating road boundaries by deep learning. Existing methods detect boundaries using specifically designed features, and if such features are not available, it is difficult to estimate road boundaries. On the other hand, estimation by deep learning does not require designing features beforehand because it can learn features by itself, and it could estimate boundaries for a more diverse set of roads. In this research, we propose a method of estimating road boundaries by a combination of deep learning and particle filter. By performing a temporal filtering with a particle filter, it is possible to deal with occasional failures in road boundary recognition by deep learning.