A modifed optical flow approach for robotic tracking and acquisition

Abstract

Abstract A robotic system that can visually track and intercept an arbitrary object which is traveling in 2‐D at an unknown velocity on a conveyor is to be presented. An eye‐in‐hand vision system developed by the Robotics and Intelligent Systems Laboratory at NCSU is used as an integral part of the entire tracking and acquisition system. The eye‐in‐hand system is employed to characterize the object trajectory in real time via a modified optical flow approach. A control strategy has been developed which utilizes the kinematic data that is extracted by the tracking algorithm to intercept the moving object. An overall system configuration and its basic principles are described. The demonstration of the experimental results is presented.