Vision-based autonomous vehicle guidance in indoor environments using odometer and house corner location information

Abstract

An approach to vehicle guidance using odometer and house corner location information is proposed for vision-based vehicle navigation in indoor environments. A small vehicle with wireless control and image grabbing capabilities is used as a test bed. A camera with the pantilt-zoom capability is equipped on the vehicle. The vehicle is guided to follow a path consisting of nodes learned in advance, which include the information of travel distances and turning angles provided by the odometer. A vehicle location method using house corners is proposed to estimate vehicle location which can be used to correct vehicle location, thus preventing mechanic error accumulation in long-distance navigation. Good experimental results show the feasibility of the proposed approach.