Wireless hybrid visual servoing of omnidirectional wheeled mobile robots

In this paper, we propose a new wireless hybrid control algorithm for visual servoing of mobile robots. In particular, the hybrid system is developed using the two autonomous control algorithms, i.e., position-based visual servoing (PBVS) and image-based visual servoing (IBVS). The PBVS algorithm is used for global routing, whereas the IBVS algorithm is used for the fine navigation. It helps in the specific steering towards the desired point for approaching the searched object. The proposed algorithm requires only the desired and actual poses of the mobile robot, and does not need any additional requirements such as the map of the environment or artificial landmarks. For the linearization of output signals, neural network extended Kalman filter is used. Several experimental as well as simulation results are presented in order to show the applicability of the proposed algorithm in the hybrid vision based control of mobile robots.