No abstract

Automation mechanisms are increasingly established in the field of visual quality control. UAVs can be used for particularly large components, such as those used in aircraft or ship production, but also for critical infrastructures. This paper concentrates on the problem of visual quality control in the field of perspective-dependent route planning. It is shown how the requirements for such a system can be implemented and elaborated. Furthermore we investigate how sensor positions can be calculated offline, based on optical-and geometrical requirements and how a trajectory can be planned which contains the found sensor positions for each given area on the component. It is shown how the systems architecture can be designed in order to be able to adapt it to different requirements for the planning of sensor positions and trajectory. The implementation was tested in a simulation environment, evaluated using a benchmark data set and it was shown how above-average results can be achieved on this data set.

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 UAVsupported 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.