Localization by DKF Multi Sensor Fusion in the Uncertain Environments for Mobile Robot

This paper presents an optimized algorithm for robot localization which increases the correctness and accuracy of the estimating position of mobile robot to more than 150% of the past methods [1] in the uncertain and noisy environment. In this method the odometry and vision sensors are combined by an adapted wellknown discrete kalman filter [2]. This technique also decreased the computation process of the algorithm by DKF simple implementation. The experimental trial of the algorithm is performed on the robocup middle size soccer robot; the system can be used in more general environments. Keywords—Discrete Kalman filter, odometry sensor, omnidirectional vision sensor, Robot Localization.