Fusion of Position Adjustment from Vision System and Wheels Odometry for Mobile Robot in Autonomous Driving

Abstract

Autonomous mobile vehicles need advanced systems to determine their exact position in a certain coordinate system. For this purpose, the GPS and the vision system are the most often used. These systems have some disadvantages, and so the GPS signal is unavailable in rooms and may be inaccurate, while the vision system is strongly dependent on the intensity of the recorded light. This work presents a system for determining the position of the robot base on information about the distance travelled coming from each vehicle wheel and the IMU sensor. However, wheels odometry introduces an additive measurement error (rise in every measure cycle). In this work there has been a vision correction system applied, where corrections are calculated by measuring the distance to artificial markers. This system precisely determines such correction. Each of these systems is described in the paper, in particular the vision system. There is also a description of a fusion algorithm of wheels odometry and vision correction system. The presented system was tested on an artificially built test track.