Mimetic visual servoing with adaptive neural network (ANN)

In this paper we present a model free hybrid visual servoing system. The "model free" term refers to the system with the unknown kinematics model that has to be estimated on-line, while "hybrid" specifies the visual controller architecture. The proposed system has a conventional Jacobian estimation part necessary for control output generation and it is supplemented with an additional adaptive neural network (ANN). It is shown that ANN could be used to improve the visual servoing performances of the conventional visual servoing controller, as well as to enable the mimetic control of the robot which dynamics differs from the robot which it mimics.