SPIRIT aims to develop an “inspection skill” for robots that takes the step from programming of complex inspection tasks to configuring such tasks. This will substantially reduce the engineering costs when setting up inspection robots in industrial environments.
The main result will be a software framework that consists of two parts.
The “offline framework” defines the model-based planning of the automatic coverage for complex parts, manages the image-based inspection processes and generates automatically the robot program. It will include a generic interface to allow the easy exchange of process models (for different inspection technologies), of the CAD model of the part (for a different type of product to be inspected) or of the work-cell model (for a different kinematic structure).
The generic “inline framework” deals with sensor data mapping to transfer 2D image data to the 3D object model. It will provide the backbone for the real-time execution of the actual inspection process, including the synchronization of data acquisition and robot motion.
CRF, as end user, will evaluate the progress of the project through a series of demonstrations with respect to its main research objectives. This allow the consortium and the coordinator to evaluate the status and make decisions about the project planning.