An Automated View Planning Method of Robot 3D Measurement

Precision measurement of large-scale workpiece is one of the most difficult problems in industrial measurement. In order to select suitable viewpoints to obtain precise measurement data, a lot of research has been done in the past decades. This paper proposes an automated view planning method of robot 3D measurement for large-scale workpiece. A viewpoint constraint model is used for landmarks inspection. The viewpoints are generated based on the visual cone theory and checked for validity. A cost function for robot motion is designed based on path length minimization, after what the optimal viewpoint can be determined. The simulated annealing algorithm is used to calculate the optimal sequence for robot to pass through all optimal viewpoints with the shortest total distance. Experimental result shows that the view planning method proposed in this paper increases the automation and efficiency of the whole system.