A high precision stereo-vision robotic system for large-sized object measurement and grasping in non-structured environment

Abstract

Handling and loading of large-sized objects represent a challenging task in industrial environments, especially when the object is a metal object with reflective surface features. Active stereo vision technology is not good for measuring the posture of reflective metal object, a high-precision pose measurement system based on passive stereo vision is proposed to automatic measurement, handling and loading of large objects by industrial robots in industrial environments. The system adopts advanced coarse and fine stereo vision positioning strategy, and realises the high-precision positioning of the measured target for the premise of ensuring stability. For coarse positioning, an improved multi-models template matching method based on machine learning is proposed to robust recognition of the multiple objects in complex background. A RANSAC-based method for the ellipse fitting and multi-points plane fitting is proposed for the 6-DOF pose of object accurately obtained in fine positioning step. Compared with the classical CAD-views method, experiments show that the method proposed in this paper has better performance in positioning accuracy and recognition robustness.