Konecranes and FCAI collaborate to develop intelligent cranes
Academy-industry collaboration can be a real win-win. The fourth video in this series presents the collaboration between FCAI and Konecranes, a world-leading manufacturer of lifting equipment.
The objective of this research collaboration is to develop safe and sustainable technologies for the cranes of the future, with automation and AI assisting the crane operator.
Associate Professor Laura Ruotsalainen from the department of computer science at the University of Helsinki and her group of 12 researchers work on a project called Artificial Intelligence for Industrial Vision. Ruotsalainen is also a member of FCAI’s steering group.
“The project focuses on developing a computer vision technique known as visual SLAM, simultaneous localization and mapping, in which cameras are used to generate a continuously updating map of a machine’s surroundings as well as information on its exact position,” says Ruotsalainen.
For monitoring the presence of moving objects, especially humans, multi-object tracking methods are required. This technique requires the development of sophisticated computer vision and deep learning techniques.
Research supported by Konecranes
The Artificial Intelligence for Industrial Vision project is funded by Konecranes. The research collaboration started in 2020, and Konecranes renewed the project’s funding in October 2022.
“The technology being developed will have an important role in observing and measuring material flows of a factory. Currently, laser technology is used for similar perception of physical surroundings, however, the use of camera technology is significantly more cost-effective and will therefore be more easily available for a wider group of users,” says research engineer Sami Terho from Konecranes.
“Our group decides the methods we develop to reach the agreed research goals. At the same time we benefit from collaboration because it provides a target and application area and opportunity to test results. It ensures that research is aimed at improving practical things,” says Niclas Joswig, a doctoral researcher under the supervision of Laura Ruotsalainen.
Joswig is developing novel methods for computer vision-based navigation, which means tracking the camera position attached to an object such as a crane or a human.
“We want to put the crane in an unknown and changing environment and navigate around seamlessly. The crane needs to know its own position relative to its environment to move around obstacles,” says Joswig.
Safety is of course paramount.
“While avoiding safety hazards is by far the top priority, our future goals are that the crane can automatically detect objects in its environment and in the very far future pick them up autonomously and move them to another location, even if they are objects of undefined size,” says Joswig.
The university research team is building a theoretical foundation that Konecranes can learn from when developing new technologies and automation solutions.
“We have identified many practical applications. One is the possibility to measure material streams using the crane: what is moved, when, and where. This would give the crane a larger role in material handling,” Sami Terho says.
Ilmatar crane for research and teaching
Konecranes has also donated a crane, named Ilmatar, to Aalto University for use in research and teaching. Researchers have the chance to work in a laboratory simulating a genuine factory environment. The environment includes a digital twin of the crane, enabling research and development from anywhere in the world.
“During the project, we will collect data and identify the biggest problems. At the same time we are developing the visual SLAM technique and deep learning to tackle these problems,” says Ruotsalainen.
The results of the research project will enable the development of sustainable industrial spaces that are more cost-efficient than before and safer for the employees.
“Konecranes appreciates the nature of this research. A company that looks to the future and wants to develop its technologies in the long run is easy and rewarding to work with,” says Ruotsalainen.