SPIRIT - A Software Framework for the Efficient Setup of Industrial Inspection Robots

摘要

SPIRIT aims to develop an “inspection skill” for robots that takes the step from programming of complex inspection tasks to configuring such tasks. Result of the project is a software framework that includes an “offline framework” with features such as model-based automatic coverage planning for complex parts, automatic robot program generation and an “inline framework” that deals with sensor data mapping to transfer sensor measurements to the 3D object model. At the heart of the project is an accurate process-specific model that represents the sensor data acquisition process. This representation is sufficiently accurate to allow automatic planning in off-line settings using simulated workcells and then reproducing the inspection procedure on the real one, with some adaptations and corrections. More in detail, the “offline framework” 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 robot kinematic structure). The generic “inline framework” will provide the backbone for the execution of the actual inspection process. Relying on such a proven frameworks will reduce the risks of implementing complex inspection tasks and thus help the deployment of inspection robots. In this work initial results from the two main use cases are presented, they consist of inspection tasks for the automotive and aerospace industry respectively.