International Conference on Computer and Knowledge Engineering

Home / 11th International Conference on Computer and Knowledge Engineering

Hybrid navigation based on GPS data and SIFT-based place recognition using Biologically-inspired SLAM

Authors :

Sahar Salimpour Kasebi¹ Hadi Seyedarabi² Javad Musevi Niya³

1- Faculty of Electrical and Computer Engineering University of Tabriz 2- Faculty of Electrical and Computer Engineering University of Tabriz 3- Faculty of Electrical and Computer Engineering University of Tabriz

Keywords :

GPS, Navigation, Place recognition, RatSLAM, SIFT

Abstract :

The RatSLAM algorithm, as a special type of SLAM system, simultaneously localizes and builds maps inspired by mammal’s hippocampus. In the present study, to improve the place recognition in indoor environment, an improved RatSLAM has been proposed based on the Scale Invariant Feature Transform (SIFT) algorithm. Also, to navigate and route the moving agent, a method based on GPS data and pose cell network of mentioned improved RatSLAM has been proposed that the head direction of the robot will coordinate with GPS data. In this paper, a new indoor database has been created checking the RatSLAM using MatLab and Webots. In comparison to main RatSLAM, the improved RatSLAM by SIFT revealed higher recall rate (53% to 71%) and precision rate (93% to 100%) as well as faster recognition and decreased memory cells. Also in the proposed method for navigation, the robot set path correctly to the desired target points.