GANTRY CRANES
GH are actively researching AI for gantry cranes.
optimum travel paths can be calculated for each lift by the crane’s own software.
CP Automation graphic shows elements of gantry automation.
Journey to automation Manufacturers recognise several steps on the journey to the fully-autonomous crane. MacGregor, who specialise in ship-borne cranes including ship-borne gantry cranes, put it succinctly. ‘Level 1 (assisted) supports the operator with anti-pendulation and anti-collision features. Level 2 (partially automated) adds auto-motion, auto-grip, and bridge monitoring for limited automation with human oversight. Level 3 (highly automated) is the most advanced, performing tasks autonomously with features like bridge control, cargo scan, and power- balance mode.’ And, to make clear the current situation, ‘Levels 4 and 5 (fully automated and autonomous) are still in development’. MacGregor’s own gantries are at least at level 2. LIDAR sensors scan and plan the ship-unloading process, providing precise movements and optimal positioning so reducing the need for manual intervention. On the grab, their Auto-Grip system is powered by machine learning to adapt to different material characteristics of the load. Anti- collision and Auto Motion systems are built in for safety. Gantry crane manufactures are certainly putting major efforts into research and development for Levels 4 and 5. Thus Spanish manufacturers GH: “The automation of cranes is no longer an option, but rather a necessity in many productive processes where industrial cranes operate. We set ourselves the challenge of evolving our portfolio of existing automation solutions to the next level.”
To which end they are currently running no fewer than six AI-powered projects, of which Project 5 is ‘Object identification using computer vision.’ “It focuses on integrating AI into our end products,” says the company. “It seeks to use machine vision to identify the position of objects, such as coils, in order to improve the safety and efficiency of our automatic cranes. This project is now complete and ready to be brought to the market. In fact, it has already proven its effectiveness with one customer. This is a novel solution that very few companies in the world offer.” Konecranes, moving on from pioneering waste handling, is working along similar lines. “Steering a crane safely in an environment that has people and smaller machinery moving about is no simple task,” they say. Cameras can be part of automating this; Konecranes have teamed up with the University of Helsinki in a multi-year research project that applies computer vision and deep learning to crane navigation. Perfecting computer vision still faces many challenges. In certain tasks, such as recognising objects and finding small details, computer vision already performs much better than human vision. However, understanding context and calculating distances continue to cause significant issues. Importantly, people, who from the crane camera’s point of view are small, distant, and constantly moving, are not easily identified. Detection in 3D is needed to recognise people and obstacles around the crane to avoid collisions. Here AI and deep learning have an important role. One of the key objectives of the University of Helsinki research project is to develop more efficient 3D computer vision methods using a one-lens camera, which is more affordable than the stereo cameras traditionally used. Cameras in cranes are positioned high up in a somewhat peculiar angle; determining distances with single-lens cameras in such positions is one of the priority areas of the research. “In the past few months, we have made
breakthroughs,” says Laura Ruotsalainen, Associate Professor at the Department of Computer Science at the University of Helsinki, who leads the research. “The issue of calculating distances has now been partially resolved, although computer vision technology still has challenges in more complex operating environments that have, for example, clear or reflective surfaces with few visible shapes. Computer vision research today almost always includes elements of deep learning, because it generates significantly better recognition results. Deep learning has developed considerably during the past ten years, and there could be another leap ahead.” “The objective is to develop safe and sustainable
technologies for the cranes of the future, with automation and AI assisting the crane operator,” says Sami Terho, senior specialist, crane intelligence at Konecranes. Konecranes has donated funding – and a crane – to the university. The research will support Konecranes’ product development, but it will also, says Terho, have wider benefits and other applications. “The technology being developed will have an important role in observing and measuring material flows
26 | September 2026 |
www.hoistmagazine.com
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55
