Mobile robot localization and navigation system based on monocular vision

Abstract

A system for mobile robot localization and navigation was presented. With the proposed system, the robot can be located and navigated by a single landmark in a single image. And the navigation mode may be following-track, teaching and playback, or programming. The basic idea is that the system computes the differences between the expected and the recognized position at each time and then controls the robot in a direction to reduce those differences. To minimize the robot sensor equipment, only one omnidirectional camera was used. Experiments in disturbing environments show that the presented algorithm is robust and easy to implement, without camera rectification. The root-mean-square error (RMSE) of localization is 1.4 cm, and the navigation error in teaching and playback is within 10 cm.

Keywords

localization algorithm / navigation / omni-vision / monocular vision

References

[1] Xia T., Yang M., Yang Ruqing. Progress in monocular vision based mobile robot navigation[J]. Control and Decision, 2010, 25(1): 1-7.

[2] Temeltas H., Kavak D. SLAM for robot navigation[J]. IEEE A and E Systems Magazine, 2008, 23(12): 16-19.

[3] Royer E., Lhuillier M., Dhome M., et al. Monocular vision for mobile robot localization and autonomous navigation[J]. International Journal of Computer Vision, 2007, 74(3): 237-260.

[4] Ozawa Ryohei, Mae Yasushi. Localization of mobile robots by multiple landmark recognition[C]. In: SICE Annual Conference 2007. Takamatsu, Japan, 2007. 1529–1535.

[5] Hou J., Xu Fang. Design of a visual landmark used for mobile robot self-localization[J]. Microcomputer Information, 2009, 25(2): 205-207.

[6] Dong J., Yang S., Lu Shouyin. Navigation method of the monocular vision based mobile robot[J]. Journal of Shandong University: Natural Science, 2008, 43(11): 1-3.

[7] Yuen D. C. K., MacDonald B. A. Vision-based localization algorithm based on landmark matching, triangulation, reconstruction, and comparison[J]. IEEE Transactions on Robotics, 2005, 21(2): 217-226.

[8] Sinriech D., Shoval S. Landmark configuration for absolute positioning of autonomous vehicles[J]. IIE Transactions, 2000, 32(7): 613-624.

[9] Feng Weijia, Liu Yuli, Cao Zuoliang. Omnidirectional vision tracking and positioning for vehicles[C]. In: The Fourth International Conference on Natural Computation. Jinan, China, 2008. 183–187.

[10] Fu H., Cao Z., Cao Xiaochun. Embedded omni-vision navigator based on multi-object tracking[J]. Machine Vision and Applications, 2009, 22(2): 349-358.

[11] Bais A., Sablatnig R., Gu Jason. Single landmark based selflocalization of mobile robots[C]. The Third Canadian Conference on Computer and Robot Vision, 2006, Canada: IEEE Computer Society 67-74.

[12] Holmes S., Klein G., Murray D. W. A square root unscented Kalman filter for vision monoSLAM[C]. IEEE International Conference on Robotics and Automation, 2008, Pasadena, CA: IEEE Computer Society 3710-3716.

[13] Davison A. J., Reid I. D., Molton N. D., et al. MonoSLAM: Real-time single camera SLAM[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(6): 1052-1067.

[14] Cauchois C., de Chaumont F., Marhic B., et al. Robotic assistance: An automatic wheelchair tracking and following functionality by omnidirectional vision[C]. IEEE International Conference on Intelligent Robots and Systems, 2005, Alberta, Canada: IEEE Computer Society 2560-2565.

[15] Goedeme T., Nuttin M., Tuytelaars T., et al. Omnidirectional vision based topological navigation[J]. Journal of Computer Vision, 2007, 74(3): 219-236.

[16] Krajnik T., Faigl J., Vonasek V., et al. Simple yet stable bearing-only navigation[J]. Journal of Field Robotics, 2010, 27(5): 511-533.

[17] Williames J., Cummins M., Neira J., et al. A comparison of loop closing techniques in monocular SLAM[J]. Robotics and Autonomous Systems, 2009, 57(12): 1188-1197.

[18] Chen Z., Birchfield S. T. Qualitative vision-based mobile robot navigation[C]. IEEE International Conference on Robotics and Automation, 2006, Orlando, Florida: IEEE Computer Society 2686-2692.

[19] Chen Z., Birchfield S. T. Qualitative vision-based path following[J]. IEEE Transactions on Robotics and Automation, 2009, 25(3): 749-754.