Abstract

Abstract. Real world manipulation tasks vary in their demands for precision and freedoms controlled. In particular, during any one task the complexity may vary with time. For a robotic hand-eye system, precise tracking and control of full pose is computationally expensive and less robust than rough tracking of a subset of the pose parameters (e.g. just translation). We present an integrated vision and control system in which the vision component provides (1) the continuous, local feedback at the required complexity for robot manipulation and (2) the discrete state information needed to switch between control modes of differing complexity. 1 Introduction In robotic hand-eye tasks (which we will also refer to as visual servoing or visionbased manipulation), the rote motions of classical industrial robotics are replaced by a flexible control strategy which is robust to deviations in camera positioning, robot calibration, and placement of objects in the robot workspace. In large part, this robustness is due to feedback from vision systems which observe a robot action in progress, allowing for continual adaptation of robot motion. Despite the importance of vision in these tasks, vision systems which support hand-eye robot coordination have generally been developed ad hoc, designed specifically for particular tasks. In this paper, we present a principled approach to vision and control system design which supports complex vision-based manipulation.

Citations