Е-Публикации
Технически университет - София

Abstract: One of the main operations performed in industrial robotics is motion control. Robot’s sensors provide information for robot localization, mapping and feature recognition. Many methods and corresponding algorithms are presented that use this information for robot motion control. Most of them use a single sensor for localization and therefore, the achieved precision depends on the accuracy of data perception of the corresponding sensor and vary when the conditions of the robot’s environment change. The goal of this paper is to propose and evaluate a method and algorithm which combines the information perceived by several robot sensors for robot localization and mapping and uses them for robot position estimation and path planning. The results of the simulation tests and of the algorithm being applied to a real robot is presented for evaluating the precision of the suggested algorithm by comparing the results to those obtained from a singlesensor- based localization system.

References

1. “Probabilistic Robotics : SLAM”, Invited talk at University of California at Santa Barbara, USA - May 28th, 2008
2. Nguyen, V., Martinelli, A., Tomatis, N., & Siegwart, R., 2005, A comparison of line extraction algorithms using 2D laser rangefinder for indoor mobile robotics, Proceedings of the IEEE/RSJ intenational conference on intelligent robots and systems, Volume 2(3), pp. pp.37-45
3. Forsyth, D.A. and Ponce, J., 1950, Computer Vision: A Modern Approach, London, Prentice Hall,
4. Choi, W. , Ryu, C., Kim, H.,, 1999, Navigation of a mobile robot using mono-vision and mono-audition, Proceedings of the IEEE International Conference on Systems, Man and Cybernetics, Volume VOLUME 4, pp. pp.686-691
5. H. Durrant-Whyte and T. Bailey., 2006, Simultaneous localization and mapping (SLAM), Robotics & Automation Magazine,, Volume 13(2), pp. pp.99 – 110

Issue