Volume 22 Issue 10/11- Publication Date: 1 October 2003
Uncalibrated Eye-in-Hand Visual Servoing
J.A. Piepmeier U.S. Naval Academy, Annapolis, MD 21402, USA and H. Lipkin Georgia Institute of Technology, Atlanta, GA 30332, USA

In this paper we present new uncalibrated control schemes for vision-guided robotic tracking of a moving target using a moving camera. These control methods are applied to an uncalibrated robotic system with eye-in-hand visual feedback. Without <i>a priori</i> knowledge of the robot's kinematic model or camera calibration, the system is able to track a moving object through a variety of motions and maintain the object's image features in a desired position in the image plane. These control schemes estimate the system Jacobian as well as changes in target features due to target motion. Four novel strategies are simulated and a variety of parameters are investigated with respect to performance. Simulation results suggest that a Gauss-Newton method utilizing a partitioned Broyden's method for model estimation provides the best steady-state tracking behavior.

Multimedia Key
= Video = Data = Code = Image
Example One: This file provides an animation of an eye-in-hand robotic system as it tracks a square target moving along a square path. The left window shows the robot and target motion. The right window shows the camera view as the robot is servoing. The Blue polygon represents the desired view of the target, and the red polygon represents where the target is actually seen. The target appears as a polygon (and not a square) because the optical axis of the camera is not perpemdicular to the surface of the target object. (3.2MB)
Return to Contents