Project Description

Intelligent System for Assembly Support

To increase the competitiveness of companies, local production sites are already being established in emerging markets around the world. However, cultural differences and country-specific variations in the qualification levels of the workforce make it difficult for globally active companies to guarantee uniformly high quality levels in complex value-added networks. This challenge is now being addressed by the international research project "Augmented Intelligence based Quality Assurance of Assembly Tasks in Global Value Networks" (AuQuA), which is being conducted jointly by the Mechatronics Group of the University of São Paulo and the Machine Tool Laboratory WZL of RWTH Aachen University in cooperation with the Universidade de Brasília. In this project, an assembly support system will be developed that uses methods of Artificial Intelligence (AI) to automatically create, use and continuously improve Augmented Reality (AR)-based assembly instructions. These assembly instructions serve on the one hand to guide employees in the running process and on the other hand to train them in new processes. The assembly instructions are projected in real time both on the work surface and on the workpiece to be assembled, so that workers remain free of wearables.

To implement the project, the international research consortium is developing a context and action recognition system, which will enable the assembly support system to evaluate optical data and thus recognize and analyze objects and work step sequences. The assembly support system should independently recognize the movement sequences of the worker as well as the geometric properties of the assembly objects and learn independently how a high-quality assembly process should be designed.

Based on the acquired knowledge, the system should be able to guide new workers and propose corrective actions. What is special about the system is that the researchers will allow Artificial Intelligence to be transferred to the physical world and interact with it. In this way, they enable a complementary and interwoven performance - a symbiosis of human and artificial intelligence.

More...