An approach for environment mapping and control of wall follower cellbot through monocular vision and fuzzy system

摘要

This paper presents an approach using range measurement through homography calculation to build 2D visual occupancy grid and control the robot through monocular vision. This approach is designed for a Cellbot architecture. The robot is equipped with wall following behavior to explore the environment, which enables the robot to trail objects contours, residing in the fuzzy control the responsibility to provide commands for the correct execution of the robot movements while facing the adversities in the environment. In this approach the Cellbot camera works as a sensor capable of correlating the images elements to the real world, thus the system is capable of finding the distances of the obstacles and that information is used for the occupancy grid mapping and for fuzzy control input. Experimental results with V-REP simulator are presented to validate the proposal, and the results were favorable to the use in robotics and in acceptable computing time.