Localization of Mobile Robots with Omnidirectional Cameras

Localization of mobile robots are important tasks for
developing autonomous mobile robots. This paper proposes a method
to estimate positions of a mobile robot using a omnidirectional
camera on the robot. Landmarks for points of references are set
up on a field where the robot works. The omnidirectional camera
which can obtain 360 [deg] around images takes photographs of
these landmarks. The positions of the robots are estimated from
directions of these landmarks that are extracted from the images
by image processing. This method can obtain the robot positions
without accumulative position errors. Accuracy of the estimated
robot positions by the proposed method are evaluated through some
experiments. The results show that it can obtain the positions with
small standard deviations. Therefore the method has possibilities of
more accurate localization by tuning of appropriate offset parameters.





References:
[1] J.J. Leonard and H.F. Durrant-whyte, "Mobile Robot Localization by
Tracking Geometric Beacons,” IEEE Trans. on Robotics and Automation,
Vol. 7, No. 3, pp. 376–382, 1991.
[2] A. Elfes, "Sonar-Based Real-World Mapping and Navigation,” IEEE
Trans. on Robotics and Automation, Vol. 3, No. 3, pp. 249–265, 1987.
[3] S. Godha and M.E. Cannon, "Development of a DGPS / MEMS IMU
Integrated System for Navigation in Urban Canyon Conditions,” Proc.
of International Symposium on GPS / GNSS, 2005.
[4] M. Betke and L. Gurvits, "Mobile Robot Localization Using Landmark,”
IEEE Trans. on Robotics and Automation, Vol. 13, No. 2, pp. 251–263,
1997.
[5] A. Nuchter, K. Lingemann, J. Hertzberg, and H. Surmann, "6D SLAM
– 3D Mapping Outdoor Environments,” J. of Field Robotics, Vol. 24,
No. 8–9, pp. 699–722, 2007.
[6] H. Seki, Y. Kamiya, and M. Hikizu, "Real-time Obstacle Avoidance
Using Potential Field for a Nonholonomic Vehicle,” Factory Automation,
pp. 523–542, InTech, 2010.
[7] A. Hornung, M. Phillips, E.G. Jones, M. Bennewitz, M. Likhachev, and
S. Chitta, "Navigation in Three-Dimensional Cluttered Environments
for Mobile Manipulation,” Proc. of the 2012 Int. Conf. on Robotics and
Automation, 2012.