Artificial intelligence (AI) is changing our lives. Every day, we use it at least a hundred times: via smartphone, online orders or search engines on the Internet. This raises the question:
What is Artificial Intelligence?
The term "artificial intelligence" is not clearly defined. According to the European Parliament, it describes "the ability of a machine to imitate human abilities such as reasoning, learning, planning and creativity." AI thus enables technical systems to "perceive their environment, deal with what they perceive, and solve problems to achieve a specific goal." By "analyzing the consequences of previous actions,"AI systems are "able to adapt their actions" and "operate autonomously."
A subfield of AI relevant to KUKA is what is known as machine learning.
Machine learning is a generic term for the artificial generation of information: an artificial system learns from examples and can generalize them. It does not simply learn examples by heart, but recognizes patterns and regularities.
Why is machine learning relevant for KUKA?
Robotics is moving from the very orderly environment of industrial production to the more "chaotic" private environment. Artificial intelligence helps to adapt robotic systems to imponderables and changes. Until now, robots have been repetitive, working with the same precision and repeatability. The requirements of the future are different - especially in the field of (professional) service robotics and service robotics. If robots want to move into other areas, they will have to become more flexible. Machine learning can help with this.
How much artificial intelligence is already in robots?
In many areas of daily life, AI has already achieved spectacular success for problems that were difficult or impossible to solve using conventional approaches. These include image and speech recognition, for example.
In robotics, too, it is foreseeable that AI can be used to automate new tasks without the need for explicit step-by-step programming. With less programming required, new fields of application will emerge. The combination of AI and automation has great potential.
What developments does KUKA offer with artificial intelligence?
Generally speaking, KUKA offers intelligent machines that relieve humans of burdensome tasks, not artificial intelligence. It relies on open standards to collect and interpret data. So KUKA works with machine learning and integrates it - in its own or existing solutions.
One example: the intelligent control system KUKA AIVI. The software solution helps replace static production facilities with flexibly designed systems. "AIVI, the intelligent heart of a system, uses artificial intelligence to control the driverless transport vehicles - or AGVs for short - and ensures, on the one hand, the optimal flow of materials to the production line and, on the other hand, the perfect utilization of the AGVs. Customers thus invest more selectively and benefit from lower investment costs," explains Markus Steppberger, Head of System Development at KUKA. The fact that this concept also works in practice can be seen, for example, in the body shop at BMW.
In research and development, KUKA is also working on numerous projects to optimize production with the help of artificial intelligence:
- SmartFactoryOWL, a real laboratory for artificial intelligence (AI)
In SmartFactoryOWL, a real laboratory for artificial intelligence (AI), Fraunhofer IOSB-INA is conducting research together with KUKA and other partners on the industrial data economy of tomorrow. In June 2021, the fully networked and AI-supported production of a returnable cup started - with a KR CYBERTECH from KUKA. The central question: How can industry make better use of AI technologies?
- CosiMo - Machine learning for mass production of composites
In 2018, the 3-year CosiMo research project supported by the Bavarian state government started, bringing together KUKA and other partners. The goal: to develop manufacturing processes for the mass production of composite components that can be used in automotive and aircraft manufacturing. Machine learning methods, intelligent tools, KUKA robots and KUKA cloud solutions are to lead to efficient and resource-saving production with low cycle times that can also be transferred to other manufacturing processes.
By adding artificial intelligence to existing robot systems, the aim is to revolutionize the way humans and robots work together.
Artificial intelligence in industry
After winning the virtual awards, the winners told us what makes their innovation special, how they managed the preparation despite Corona, and what they take away from the competition. Read the full interview here: