Perception planning for model-based robot vision

Abstract

This paper presents a method for automatic sensor placement for model-based robot vision. In such a vision system, the sensor often needs to be moved from one pose to another around the object to sample all features of interest. This allows multiple 3D images to be taken from different vantage viewpoints. The task involves determination of the optimal sensor placements and a shortest path through these viewpoints. Object features are sampled as individual points attached with surface normals. The optimal sensor placement graph is achieved by a genetic algorithm in which a min-max criterion is used for the evaluation. A shortest path is determined by Christofides algorithm. A Viewpoint Planner is developed to generate the sensor placement plan. It includes many functions, such as 3D animation of the object geometry, sensor specification, initialization of the viewpoint number and their distribution, viewpoint evolution, shortest path computation, scene simulation of a specific viewpoint, parameter amendment. Experiments are also carried out on a real robot vision system to demonstrate the effectiveness of the proposed method.