Robust pose determination for autonomous docking

Abstract

This paper describes current work at Oak Ridge National Laboratory to develop a robotic vision system capable of determining the position and orientation (pose) of designated objects from their geometry. A method has been developed that connects 2-D point features from a single image into higher-order shapes and then matches these features with corresponding features of a polyhedral model. Pose estimates are made from these matches using a closed-form point solution based on model features of four coplanar points. Rotations are represented by quaternions, which are four component numbers, that simplify the calculations in determining the least-squares solution for the coordinate transformation. This pose determination method, including image acquisition, feature extraction, feature correspondence, and pose calculation, has been implemented on a real-time system using a commercial camera and image processing hardware. Experimental results from this implementation are given for relative ...