In contrast to other non-destructive testing methods, industrial endoscopy, which is used specifically for inspecting cavities, has so far been little automated. This is largely due to the demanding handling of the devices within areas that are difficult to access as well as the complex evaluation of the recorded measurement data due to highly variant recording conditions. In this paper, a novel continuum robot is presented that enables non-contact guidance of the probe head on a circular path, creating more reproducible and improved viewing conditions. Additionally, a concept for automated measurement data analysis based on Deep Learning is presented.
