Last updateTue, 20 Apr 2021 11am

AI supports skilled workers during assembly

Kimoknow, a KIT spin-off, develops digital assembly assistant - based on automated AI-supported object recognition

Artificial intelligence (AI) makes it possible for machines to recognise objects. This requires large amounts of high-quality image data with which the algorithms are manually trained. The start-up Kimoknow, which was founded at the Karlsruhe Institute of Technology (KIT), has developed a technology to automate this training. The first use case: a digital assembly assistant for contactless cooperation between humans and machines. It is being tested in cooperation with Elabo GmbH at the Center for Artificial Intelligence Talents (CAIT).

"Training AI systems to recognise objects is still time-consuming, inflexible, expensive, highly environment-dependent and requires a lot of computing effort," explains Kimoknow co-founder Lukas Kriete. The KIT start-up therefore uses image data that are generated for all objects in computer-aided design (CAD) and production data management (PDM) processes anyway. Among other things, they provide information about the material, geometry and position of the respective object. The CAD and PDM data are extracted and used for the automated training of the AI.

The object recognition system trained in this way can be used in a variety of ways, including augmented reality (AR) glasses. They detect relevant objects in the user's field of vision in real time and also have the necessary contextual information about the object in question. As the first use case for such AR glasses, Kimoknow has developed an assistance system to support skilled workers in the assembly of complex devices. The virtual assistant guides users through the entire assembly process, visualises the assembly instructions step by step without an additional display and thus shows which part is processed in which order with which tools and assembly materials. It repeats individual steps if errors occur and documents the process. The assembler has both hands free and communicates with the system via eye contact, hand signals or voice command. "The assembly assistant makes the process more efficient, more productive, faster and more cost-effective with better quality," says Kriete.

The assistant is suitable for all industries where highly complex products are manufactured in small quantities. The prototype is used for the final assembly of highly specialised measuring devices and is currently being tested in cooperation with Elabo GmbH at the Center for Artificial Intelligence Talents (CAIT) at KIT's Institute for Information Management in Engineering (IMI).

Kimoknow is a spin-off of the IMI and was launched on 13 May 2020 as an entrepreneurial company (haftungsbeschränkt). In addition to Lukas Kriete, Roman Wiegand, Aaron Boll, Michael Grethler and Vesa Klumpp are part of the founding team.

Centre for Artificial Intelligence Talents (CAIT)

The Center for Artificial Intelligence Talents (CAIT) specifically promotes research talents who combine methods of artificial intelligence and engineering. In addition to infrastructure, resources and training formats, it offers them above all the opportunity to test and further develop new developments and ideas under real working conditions and in cooperation with potential users, and to quickly bring them into practice. The concept focuses on humans and their interaction with artificial intelligence. "It is not the new technologies that change the world, but the people who use these technologies," emphasises CAIT director Professor Jivka Ovtcharova. Researchers and start-ups get the chance to develop new AI technologies close to the market. Companies benefit from the know-how of these talents and from current research results. "This is a win-win situation and the optimal model for cooperation between science and business," explains Ovtcharova.

The CAIT was opened at IMI in June 2019 under the leadership of Jivka Ovtcharova and continues the concept of the Lifecycle Engineering Solutions Centre (LESC), which had been operating until then, with a focus on AI. In addition to Elabo GmbH, abas Software AG and SolidLine AG, among others, are partners of the CAIT.


  • Latest Post

  • Most Read

  • Twitter

Who's Online

We have 3094 guests and one member online

We use cookies on our website. Some of them are essential for the operation of the site, while others help us to improve this site and the user experience (tracking cookies). You can decide for yourself whether you want to allow cookies or not. Please note that if you reject them, you may not be able to use all the functionalities of the site.