Inspection planning for optimized coverage of geometrically complex surfaces
Precise automatic product inspection is an important building block of industrial manufacturing. Different products require different inspection techniques and setup configurations to be thoroughly inspected for all their geometrical features. As the design space is large and complex, especially for geometrically complex surfaces with deep cavities, empirical setup design can turn into a very time consuming process with sub-optimal solutions. In today's industry, we are missing a generic automatic method to translate the inspection requirements into optimized solutions. In this paper, we propose an optimization framework based on sensor simulations to automatically propose optimized setup solutions. In this framework, we aim at minimizing the number of acquisitions which maximally fulfill the inspection requirements. As an example, we consider maximizing the surface coverage of a cylinder head in a laser triangulation setup. We characterize the design space and propose integrating the Particle Swarm Optimization algorithm in a greedy approach for solving the problem. We finally demonstrate the planning results which successfully cover hard-to-reach areas on the object.