Through a series of demonstrations and evaluations the developments in the project were iteratively assessed and the next development steps were identified. In the last stages of the project all developments were evaluated on a total of 17 use cases, including 6 robotic workcells, 7 different inspection technologies and 17 different parts with a size of 20cm up to several meters in length.
The main results include:
Offline coverage planning, which is used to plan inspection paths that ensure full coverage, avoid collision and optimize reachability for the robot. The path is planned based on shape primitives and is then morphed to the shape of the part. This makes the resulting scanning path more predictable and better understandable for the user.
An offline global re-planning module, which is used to adapt a previously planned path to the actual shape of the part, based e.g. on a 3D measurement. This can be relevant if the part position varies and for non-rigid parts.
An inline reactive planning module, which adjusts the path during the inspection process. This helps to inspect parts with small deviations in shape where a prior full 3D measurement is not possible.
A generic calibration method for hand-eye calibration of image-based sensors. The method works for eye-in-hand as well as eye-on-base configurations depending on whether the robot is holding the sensor or the part.
An image backprojection method that maps the acquired 2D images to the 3D model of the part. This creates a fully textured model for better visualization. Backprojection is combined with image stitching, to remove any remaining discontinuities between adjacent images and also to make the illumination of the single images more homogeneous to improve the visual appearance.
All of the developments were integrated into one of two components of the overall software framework. The "offline framework" includes the offline path planning, the modelling of the robot, the workcell, the process model of the inspection process and the global re-planning. The "inline framework" includes the calibration procedures, the execution of the motion program on the robot, the reactive path planning and the data mapping.
Exploitation of the results will be mainly through licensing of the resulting software and through its integration into robotic inspection systems. The two main software components (offline and inline framework) can be exploited jointly, but also separately as they both have standardized interfaces that are suitable for data formats typically used in production environments.
Dissemination included several scientific papers, blog entries, newspaper articles and the presentation of the results at (physical and later virtual) fairs. A data set relating to the single use cases is made available in the Zenodo repository.
