Autor: Ulrich Berger

In the project ARAS (Advanced Robot Assistance Solution) a robot programming assistant was developed, which allows for automated generation of robot programs for assembly processes. By using a multimodal approach for human-machine-interaction, assembly steps are recognized with machine learning algorithms while a worker is showing the robot how an assembly process is performed. Afterwards, a robot program is generated automatically. This way, new robot programs are created within minutes without the user having any knowledge about programming or robotics.

Germany is known to have a very powerful and highly competitive industrial sector. In this context, the manufacturing sector accounts for around 50 % of German exports and is facing a variety of new challenges like an increasing international competitive pressure, more complex value adding networks and more volatile markets [1]. Constant innovation is going to be required and therefore flexible production systems are increasingly gaining in importance. This article discusses the results of a collaborative industry survey about flexible production systems, which have been conducted in the context of the European research project cPAS. On this basis, requirements and potential of an increasing horizontal integration between companies and production planning / runtime systems are discussed.

Actually there are existing significant deficits in the information flow along the NC process chain. The deficits are solved insufficient by introducing CAD-CAM systems and feature-oriented specification languages, because of the usage of the DIN 66025 as NC programming language. In contrast to that the application of new production technologies (like laser treatments) requires a high quantity and quality of information from the planning phases in the shop floor in order to compensate the relatively small collected wealth of experience with these technologies. A guidance system offers the machine operator now the possibility to access additional planning data. Thus it is possible, that new collected experience by setting up a NC program can be stored and reused in order to avoid repetitive errors in the numerical control procedure chain.

Assembly processes are characterized by increasing complexity. Fast ramp-up is a question of vital importance due to the high invests for production lines. A key factor to success is the integrated reuse of experience concerning similar machines and processes. In many cases experiences from shop floor level remain unused in new projects. A main obstacle on production level is to identify and record experience rapidly and precisely. This concept was developed on the base of the Delphi-Method to process experiences of employees effectively and efficiently.