Chris Liebold
The Technische Universität Ilmenau has just successfully completed the "Engineering for Smart Manufacturing (E4SM)" research project.In the interdisciplinary project, scientists, accompanied by an advisory board of top-class research institutions and companies, researched innovative technologies for the intelligent manufacturing and assembly of the future, focusing on the interaction between humans and machines. The Carl Zeiss Foundation funded the E4SM project with three million euros over five years as part of its "CZS Breakthroughs" program for research into intelligent systems.
Industry 4.0 - the intelligent networking of machines and processes in industry with the help of IT - was once upon a time: with the E4SM project, TU Ilmenau is entering the age of Industry 5.0, which puts people back at the center of manufacturing processes in industry and trade. With the help of artificial intelligence, people and machines are being adapted to each other in such a way that new production tasks can be solved faster and more efficiently than before.
Intelligent machines and robots that help people in industrial production - that was the vision of the E4SM project five years ago. The ambitious goal:The robots were to autonomously coordinate their own actions with those of humans, supported by AI. The focus was on the requirements and special features of the manufacturing and assembly processes of small and medium-sized companies, which predominate in Thuringia, a region dominated by SMEs.
Seven departments at TU Ilmenau worked closely with top-class research institutes and companies on the E4SM project: Honda Research Institute Europe, known for the autonomous humanoid robot "Asimo", Robert Bosch GmbH and the mechanical engineering company Henkel and Roth from Ilmenau with expertise in industrial assembly, the machine and plant designer LASO tech Systems from Suhl, which has extensive knowledge of welding techniques, the Ilmenau-based manufacturer of service robots and robot platforms Metralabs and TÜV Thüringen with its expertise in safety aspects.
The E4SM project achieved pioneering breakthroughs on the way to Industry 5.0:
Breakthrough 1: 3D multi-view stereo system for safe collaboration between humans and robots
Safety is of central importance when humans and robots work together. In order to not only perform its task perfectly in the interaction between man and machine, but also without endangering humans, the robot must be able to detect their actions in the assembly process in the real environment in three dimensions. To achieve this, the researchers used multimodal imaging, in which thermal images were combined with RGB color images and 3D point clouds to create highly accurate large-scale three-dimensional images of the spatial environment. In the innovative sensor-based 3D multi-view stereo system, the various cameras calibrate themselves robotically.
TU Ilmenau/Barbara AichrothBreakthrough 2: Recognition of the assembly action and corresponding autonomous assistance
Perfect cooperation between humans and robots - experts refer to this as human-robot collaboration - is particularly necessary away from fully automated production chains, where robots assist humans by taking on subtasks in the assembly of small batches. Without the need for lengthy training, the robot should be able to monitor the progress of the assembly and work independently on recurring tasks.
A significant breakthrough in collaborative assembly by humans and robots: the AI-based E4SM robot recognizes the actions that the human is currently carrying out, as well as the tools and workpieces being used. In this way, it records the respective assembly progress and can decide independently where it can provide assistance. The robot can also find and grasp any objects in the working environment that it is not familiar with. According to the current state of the art, this only works for previously defined, known objects. The E4SM project has thus created the necessary conditions to plan ahead and to fetch and deliver the objects required later.
AdobeStock/BijacBreakthrough 3: Flexible and cost-saving AI-supported laser beam welding
Until now, laser beam welding required the use of complex and expensive clamping devices to fix the metal sheets that were to be joined together. The vision of the E4SM project: the sheets to be joined are held by robotic arms. With the help of artificial intelligence, a decisive breakthrough was achieved by analyzing the welding process without contact and predicting in real time when a gap will occur. This can be avoided by pressing the sheets together in a controlled manner so that the laser can continue to hit both sheets and weld them together. The AI predicts the force that needs to be applied to optimally adjust the position of the sheets for the welding process.
Breakthrough 4: Interactive visual tool chain for small and medium-sized enterprises
In addition to the development of AI-supported robots, the E4SM project also aimed to design processes for industry to develop AI-based assistance systems themselves. The breakthrough: Small and medium-sized enterprises are supported by an interactive visual tool chain to develop efficient and safe applications that can be used in their own production. As no detailed specialist knowledge is required for this, the development process is significantly simplified for users.
About the Carl Zeiss Foundation
The Carl Zeiss Foundation has set itself the goal of creating scope for scientific breakthroughs. As a partner of excellent science, it supports basic research as well as application-oriented research and teaching in the STEM disciplines (mathematics, computer science, natural sciences and technology). Founded in 1889 by the physicist and mathematician Ernst Abbe, the Carl Zeiss Foundation is one of the oldest and largest private science-promoting foundations in Germany. It is the sole owner of Carl Zeiss AG and SCHOTT AG. Its projects are financed from the dividends distributed by the two foundation companies.