Active Position-Pose Estimation of Nuts Using a Monocular Eye-In-Hand System

Abstract

Position-pose estimation of objects is a vital step for robotic intelligent grasping. In this paper, we propose an active 6D position-pose estimation algorithm for a spatial circle exploiting monocular eye-in-hand system. First, the influence of the monocular eye-in-hand system's positions on the performance of position-pose estimation from two images taken by a monocular eye-in-hand system from two different views was analyzed. Then, an active movement strategy of the monocular eye-in-hand system was proposed for more accurate position-pose estimation. Finally, experiments were conducted to demonstrate the effectiveness of the proposed method for position and pose estimation of circles printed on paper and real nuts.