Visual Servoing by Optimization of a 2D/3D Hybrid Objective Function

A.H. Abdul HafezCSE Department, Osmania University, Hyderabad, India

C.V. JawaharCVIT, International Institute of Information Technology, Hyderabad, India

• We present a new hybrid visual servoing algorithm for robot arm positioning task.

• The objective function has been designed to include the full 2D and 3D information.

• The positioning task is formulated as a first order and second order minimization problem.

• Simulation results show that the two methods provide an efficient solution to the camera retreat and features visibility problems. Model-free and model-based 3D error

functions