AR-TurtleSLAM: EKF-based Localization and Mapping using ArUco Feature Detection on Mobile Robots

Abstract

Localization is fundamental for mobile robots, especially in indoor environments where GPS cannot work properly. This paper presents an Extended Kalman Filter (EKF)-based approach for simultaneous localization and mapping (SLAM) utilizing ArUco marker detection for mobile robots. The EKF framework integrates sensor data from the robot’s odometry for prediction and camera for update, effectively managing the uncertainties inherent in real-world environments. Experimental results demonstrate that the EKF-based SLAM system achieves reliable performance in controlled environments, maintaining precise localization and producing accurate maps. This approach offers a cost-effective and computational efficient solution for localizing mobile robots in indoor environments, with potential applications in robotics research and controlled industry scenarios.