Abstract: This paper discusses the implementation of the Kalman
Filter along with the Global Positioning System (GPS) for indoor
robot navigation. Two dimensional coordinates is used for the map
building, and refers to the global coordinate which is attached to the
reference landmark for position and direction information the robot
gets. The Discrete Kalman Filter is used to estimate the robot position,
project the estimated current state ahead in time through time update
and adjust the projected estimated state by an actual measurement at
that time via the measurement update. The navigation test has been
performed and has been found to be robust.
Abstract: 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 well-known 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.
Abstract: The objective of the presented work is to implement the Kalman Filter into an application that reduces the influence of the environmental changes over the robot expected to navigate over a terrain of varying friction properties. The Discrete Kalman Filter is used to estimate the robot position, project the estimated current state ahead at time through time update and adjust the projected estimated state by an actual measurement at that time via the measurement update using the data coming from the infrared sensors, ultrasonic sensors and the visual sensor respectively. The navigation test has been performed in a real world environment and has been found to be robust.