Monte Carlo Uncertainty Maps-based for Mobile Robot Autonomous SLAM Navigation

FERNANDO AUAT CHEEÍN; JUAN MARCOS TOIBERO; FERNANDO DI SCIASCIO; RICARDO CARELLI; FERNANDO LOBO PEREIRA

Viña del Mar

Congreso; IEEE International Conference on Industrial Technology; 2010

IEEE

Abstract—This paper presents an uncertainty maps construction method of an environment by a mobile robot when executing a SLAM (Simultaneous Localization and Mapping) algorithm. The SLAM algorithm is implemented on a Extended Kalman Filter (EKF) and extracts corners (convex and concave) and lines (associated with walls) from the surrounding environment. A navigation approach directs the robot motion to the regions of the environment with the higher uncertainty. The uncertainty of a region is specified by a probability characterization computed at the corresponding representative points. These points are obtained by a Monte Carlo experiment and their probability is estimated by the sum of Gaussians method, avoiding the timeconsuming map-gridding procedure. The mobile robot has a contour-following controller implemented on it to drive the robot to the uncertainty points. SLAM real time experiments within real environments are also included in this work.—This paper presents an uncertainty maps construction method of an environment by a mobile robot when executing a SLAM (Simultaneous Localization and Mapping) algorithm. The SLAM algorithm is implemented on a Extended Kalman Filter (EKF) and extracts corners (convex and concave) and lines (associated with walls) from the surrounding environment. A navigation approach directs the robot motion to the regions of the environment with the higher uncertainty. The uncertainty of a region is specified by a probability characterization computed at the corresponding representative points. These points are obtained by a Monte Carlo experiment and their probability is estimated by the sum of Gaussians method, avoiding the timeconsuming map-gridding procedure. The mobile robot has a contour-following controller implemented on it to drive the robot to the uncertainty points. SLAM real time experiments within real environments are also included in this work.