Title :
Iteration effect on vision based simultaneous localization and mapping using Kalman filters family
Author :
Darabi, S. ; Shahri, A. Mohamad
Author_Institution :
Sch. of Electr. & Comput. Eng., Qazvin Islamic Azad Univ., Qazvin, Iran
Abstract :
Simultaneous Localization and Mapping (SLAM) is one of the most fundamental and challenging problems in mobile robotics. In this paper solving vision based SLAM problem using Kalman filters family have been provided. It is focused on mobile robot equipped with stereo vision sensor which moves in an indoor environment. The mobile robot navigated among the landmarks which were detected by Scale Invariant Feature Transform (SIFT) method. The Extended Kalman Filter (EKF) and Sigma Point Kalman Filter (SPKF) approaches have been used to solve this SLAM problem. Then the role of Iteration in these filters to improve estimation state accuracy in SLAM has been investigated. Finally in the experimental results the better state estimation accuracy in iterated EKF and SPKF has been shown.
Keywords :
Kalman filters; SLAM (robots); indoor environment; iterative methods; mobile robots; navigation; nonlinear filters; robot vision; state estimation; stereo image processing; transforms; Kalman filters family; SIFT method; estimation state accuracy; extended Kalman filter; indoor environment; iterated EKF; iterated SPKF; iteration effect; landmarks; mobile robot navigation; mobile robotics; scale invariant feature transform method; sigma point Kalman filter; stereo vision sensor; vision based SLAM problem; vision based simultaneous localization and mapping; Accuracy; Covariance matrix; Kalman filters; Mathematical model; Simultaneous localization and mapping; Trajectory; Vehicles;
Conference_Titel :
Robotics and Biomimetics (ROBIO), 2011 IEEE International Conference on
Conference_Location :
Karon Beach, Phuket
Print_ISBN :
978-1-4577-2136-6
DOI :
10.1109/ROBIO.2011.6181432
