Fisheye-based visual aligned regulation for wheeled mobile robots

Abstract

In this paper, a fisheye-based visual servo regulation method is proposed for wheeled mobile robots, which utilizes motion planning algorithms to provide trajectories for driving the robot to desired poses in an aligned pattern. To satisfy the wide field-of-view (FOV) requirement in robotic systems, the image projection model of fisheye is analyzed, and derivation and estimation of homography for fisheye vision are implemented to facilitate robotic pose calculation. Compared with traditional visual regulation schemes, motion planning and trajectory tracking techniques are combined to make mobile robots reach given poses in the frontal aligned style, which guarantees the robot to move smoothly and is extendable such as for car-like robots. Desired image trajectories are calculated reversely by the fisheye model with respect to the planned geometric path, and then a tracking controller is employed for maneuvering the mobile robot. Simulation and comparative experimental results are collected to verify effectiveness of the proposed strategy.