A computationally efficient EKF-vSLAM

This paper presents an efficient extended Kalman filter implementation of a single-camera visual simulataneous localization and mapping (vSLAM) algorithm, vSLAM is a novel algorithm for simultaneous localization and mapping problem widely studied in mobile robotics field. The algorithm is vision and odometry-based. The problem with the implementation of all SLAM algorithms is the state vector size and the full covariance matrix, which in large environments may become prohibitively large. In this paper we show that moving landmark from the state vector to the map vector, using the camera characteristics, can maintain a reasonable number of landmarks in the state vector and then reduce the computational complexity of the update loop. At each time the algorithm maintains the map vector, which contains invisible landmarks, separated from the state vector. We use a Pioneer II robot and motorized pan tilt camera models to implement the algorithm.

[1]  Daniel C. Asmar,et al.  Towards benchmarks for vision SLAM algorithms , 2006, Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006..

[2]  Nobuyuki Kita,et al.  3D simultaneous localisation and map-building using active vision for a robot moving on undulating terrain , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[3]  David W. Murray,et al.  Mobile Robot Localisation Using Active Vision , 1998, ECCV.

[4]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[5]  Sebastian Thrun,et al.  Probabilistic robotics , 2002, CACM.

[6]  Hugh F. Durrant-Whyte,et al.  A computationally efficient solution to the simultaneous localisation and map building (SLAM) problem , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[7]  G. Dissanayake,et al.  Simultaneous localisation and mapping problems in indoor environments with stereovision , 2005, 31st Annual Conference of IEEE Industrial Electronics Society, 2005. IECON 2005..

[8]  Andrew J. Davison,et al.  Real-time simultaneous localisation and mapping with a single camera , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[9]  Wolfram Burgard,et al.  A real-time algorithm for mobile robot mapping with applications to multi-robot and 3D mapping , 2000, Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065).

[10]  John J. Leonard,et al.  Explore and return: experimental validation of real-time concurrent mapping and localization , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).