Model-based coverage motion planning for industrial 3D shape inspection applications

In this paper, we propose a novel planning method for the shape inspection applications with a sensor-equipped industrial manipulator. In the proposed approach, the view planning problem is formulated as a Set Covering Problem (SCP) and the path planning problem is formulated as a Travelling Salesman Problem (TSP). The combined SCP and TSP problems are then formulated as a sequencing problem, and solved simultaneously via Random-Key Genetic Algorithm (RKGA) in a one-step optimization process. With the proposed method, time-efficient and collision-free motion plan that satisfies the requirement of the robotic inspection tasks can be generated automatically. Computational studies were performed to verify the effectiveness of the proposed planning method. The method was found to outperform other approaches by generating robot paths that complete the inspection task with shorter execution time. The Overall time reductions were found up to 28.4% compared to the previous approaches. To further demonstrate the effectiveness of the proposed method in a real-world inspection task, an experimental test was also performed using an ABB industrial robotic system equipped with an on-board 3D scanner.