A groundbreaking AI (artificial intelligence) technology for robot work has been successfully developed, allowing robots to seamlessly integrate into manufacturing processes. This innovative technology, developed by the Korea Institute of Machinery and Materials (KIMM), has the potential to revolutionize various industries, including automobile manufacturing, machine parts production, assembly, and more. The application of this AI technology is expected to enhance the working environment in manufacturing sites.
Led by Chang-hyun Kim, head of the Department of AI Machinery at KIMM, the research team has achieved a major milestone by creating an AI technology that can easily adapt to manufacturing processes. Currently, the technology is being implemented in the manufacturing processes of electronic component producers, with plans to broaden its application to other manufacturers in the future.
The AI technology for robot work, developed by KIMM, is based on the Large Language Model (LLM) and virtual environment. This advanced technology comprehends user commands and automatically generates and executes tasks for the robots. By utilizing this technology, task sequences and movements can be generated through voice or text commands. Additionally, pre-learning in a virtual space allows for the selection of the optimal work point, minimizes the work process, and enables the detection of objects and collision avoidance.
Traditionally, when employing robots for tasks in manufacturing sites, the site itself needed to be modified to accommodate the robot. This limitation restricted the range of tasks that could be performed by robots. Furthermore, integrating different technologies, such as movement and recognition, has also been a challenge. Although AI technologies like LLM have been successfully combined with robots for various tasks, there have been difficulties in applying these technologies directly to real work sites due to limitations in laboratory-only testing.
The newly developed technology overcomes these challenges by allowing for specific task specification for robots. With pre-learning conducted in a virtual space, robots can effortlessly perform tasks with minimal on-site modification. Currently, on-site demonstration tests are being conducted, and it is anticipated that this technology will effectively address the diverse situations that may arise in manufacturing sites.
Chang-hyun Kim, head of the Department of AI Machinery at KIMM, asserts, “For the first time in the world, we have developed specialized intelligence for robot tasks by combining AI and robot technology, and successfully applied it to an actual manufacturing site.” He further adds, “The technology is currently being tested in the manufacturing process of electric vehicle (EV) parts manufacturers, and its application will gradually expand.”
As the AI technology for robot work continues to be refined and tested, it holds immense potential for transforming manufacturing processes across various industries. By seamlessly integrating robots into the workflow, productivity can be enhanced, and the working environment can be improved. This groundbreaking development paves the way for a new era of automation and advanced manufacturing.
*Note:
1. Source: Coherent Market Insights, Public sources, Desk research
2. We have leveraged AI tools to mine information and compile it
