A Novel Fuzzy Kalman Filter for Mobile Robots Localization

A new method to implement fuzzy Kalman filters is introduced in this paper. This has special application in fields where inaccurate models or sensors are involved, such as in mobile robotics. The innovation consists in using possibility distributions, instead of gaussian distributions. The main advantage of this approach is that uncertainty is not needed to be symmetric, while a region of possible solutions is allowed. The contribution of this work also includes a method to propagate uncertainty through both the process and the observation models. This one is based on quantifying uncertainty as trapezoidal possibility distributions. Finally, the way to reduce the EKF inconsistence when large number of iterations are carried out is shown.