PROJECT TITLE :

Orthogonal Image Features for Visual Servoing of a 6-DOF Manipulator With Uncalibrated Stereo Cameras

ABSTRACT:

We have a tendency to present an approach to manage a half-dozen-degree-of-freedom (DOF) manipulator using an uncalibrated visual servoing (VS) approach that addresses the challenges of choosing correct image features for target objects and coming up with a VS controller to boost the tracking performance. The main contribution of this paper is that the definition of a new virtual visual house (image house). A unique stereo camera model using virtual orthogonal cameras is used to map 6-D poses from Cartesian house to the present virtual visual house. Every component of the half-dozen-D pose vector outlined during this virtual visual house is linearly independent, leading to a full-rank half dozen × 6 image Jacobian matrix, that permits avoiding classical issues, like image space singularities and local minima. Furthermore, the management for rotational and translational motion of robot is decoupled because of the diagonal image Jacobian. Finally, simulation results with an eye-to-hand robotic system make sure the advance in controller stability and motion performance with respect to conventional VS approaches. Experimental results on a 6-DOF industrial robot are provided to illustrate the effectiveness of the proposed method and also the feasibility of using this method in sensible eventualities.