Recognition and localization of solid objects by a monocular vision system for robotic tasks

In this paper, we present a model-based vision system using a CCD camera mounted on the end-effector of an industrial robot. We describe an autonomous monocular vision system which is used as a feedback signal to control the position and orientation of the manipulator with respect to a dynamic object part of a 3D scene. Without any previous knowledge of the part's placement or motion, this visual feedback would allow a robot to track a pattern in real time. Applications for such a vision-guided robot include 3D object recognition, by extracting 2D image features and rebuilding 3D features. This is performed via rigidity constraint and search comparison in model database geometric inference. Kinematic redundancy is used for general solution of joint velocity represented by the generalized inverse of Jacobian matrix. The problem of redundancy utilization can generally be formulated in the framework of tasks with the order of priority. We present a visual servoing scheme using the task function approach in term of 6 degrees of freedom of robot's gripper regulation. Redundancy theory allows to control position and orientation of the end-effector of an industrial robot in less than 80 ms of cycle time.<
>