Control movement of mobile robots inside building based on pattern recognition algorithm
Ivan A. Shcherbatov, Nguyen Tuan Dung, V. P. Glazkov, Oleg Protalinskiy · 2017
In the movement management system of mobile robots, simultaneous detection of obstacles and creation of obstacles' map in the near field of the mobile robot are extremely urgent and complex tasks. In general, environment around robot is very complicated due to differences in change of lighting conditions and viewing angles. These problems lead to decrease accuracy of obstacles recognition. In this paper, we propose algorithms to solve this problem and increase effectiveness of mobile robots: to detect obstacles and create map of environment around robots could be used algorithm, which based on 3D-point cloud. In addition, algorithm “SURF” is implemented to detect landmark. Using this algorithm allows satisfying requirements for obstacle detection in real time. The experimental results show the effectiveness of proposed approach using in vision system of a mobile robot platform.