Open Access

Martin Schörner, Constantin Wanninger, Raphael Katschinsky, Simon Hornung, Christian Eymüller, Alexander Poeppel, Wolfgang Reif

• Automation is playing an increasing role in the field of quality assurance. For the visual inspection of larger assemblies such as aircraft fuselages or ship hulls, the use of UAVs is an option. This paper deals with one aspect of the UAV-supported inspection of assemblies in production. Here, newly added components have to be checked for correct assembly. The planning of the shortest possible route from which all components to be inspected can be viewed as well as the estimation of the UAV’s position relative to the component have already been presented in previous work. We propose strategies that can be used if an inspection point cannot be reached by the UAV or the component to be inspected cannot be seen by the UAV’s camera from the inspection point. For this purpose, we generate alternative inspection points that can be used if errors occur during the inspection from the original inspection point. To achieve this, we present a metric that can be used to select an alternativeAutomation is playing an increasing role in the field of quality assurance. For the visual inspection of larger assemblies such as aircraft fuselages or ship hulls, the use of UAVs is an option. This paper deals with one aspect of the UAV-supported inspection of assemblies in production. Here, newly added components have to be checked for correct assembly. The planning of the shortest possible route from which all components to be inspected can be viewed as well as the estimation of the UAV’s position relative to the component have already been presented in previous work. We propose strategies that can be used if an inspection point cannot be reached by the UAV or the component to be inspected cannot be seen by the UAV’s camera from the inspection point. For this purpose, we generate alternative inspection points that can be used if errors occur during the inspection from the original inspection point. To achieve this, we present a metric that can be used to select an alternative inspection point that is as suitable as possible. We conclude by demonstrating how this strategy works by evoking different failure cases in a simulated environment.…