A Fuzzy Logic-Based Adaptive EKF for Real-Time Mobile Robot Localization and Path Planning

Abstract

Accurate localization of mobile robots in indoor environments is essential for autonomous navigation. This paper presents a framework that integrates a Fuzzy Adaptive Extended Kalman Filter (FAEKF) with the Rapidly-exploring Random Tree Star (RRT*) path planning algorithm. The FAEKF uses a Mamdani-type Fuzzy Inference System to dynamically adjust the measurement noise covariance, improving localization precision. The estimated position from the FAEKF serves as input to the RRT* algorithm to generate optimal paths. Simulation results demonstrate that the proposed method achieves accurate trajectory tracking and effective navigation in indoor environments. This research confirms the effectiveness of combining adaptive filtering with samplingbased planning for mobile robot applications.