ATNN and SVM for Autonomous Mobile Robot

Abstract

If a robot does not know where it is, it can be difficult to determine what to do next. In order to localizeitself, a robot has access to relative and absolute measurements giving the robot feedback about its driving actions andthe situation of the environment around the robot. Given this information, the robot has to determine its location asaccurately as possible. What makes this difficult is the existence of uncertainty in both the driving and the sensing ofthe robot. The uncertain information needs to be combined in an optimal way. The Kalman Filter is a technique fromestimation theory that combines the information of different uncertain sources to obtain the values of variables ofinterest together with the uncertainty in these. In this work we provide a thorough discussion of the robot localizationproblem resolved by Kalman Filter, Adaptive Time Delay Neural Network and Support Vector machines.