Original title: Programming and execution of skill-based human-robot-crane collaborative tasks
Taneli Lohi, Markku Suomalainen, Roope Mellanen, Tapio Heikkilä · September 2026
Factories and warehouses face constant changes in production, creating tough challenges for indoor logistics and manufacturing. To handle these demands, machines need to be more agile, flexible, and robust. Researchers tackled this by creating a simple CAD-model based system to program and execute parametrized robot skills. Skills combine robot motions, tool controls, and sensor data to perform tasks that have changing requirements. The system controls execution using a modified Behavior TreeA control structure that organizes robot decisions and actions in a tree format.—a dynamic framework that decides what actions to take next—driven only by event-based communicationA method where system parts communicate only when specific events happen, not all the time.. To test the setup, a human instructed an overhead crane and a robot manipulatorA robotic arm used to grasp and move objects. together. The crane supported a heavy object while the manipulator guided it safely into its target goal.
Imagine setting up a large piece of furniture with a friend, where you need to lift one end and they guide it through a narrow hallway. It's tricky to move without bumping into walls because timing and direction have to match perfectly. Here, the system acts like a smart coordinator: a human gives simple instructions, and it automatically syncs a crane to lift and a robot arm to guide, making sure everything fits into place smoothly.
Workers in manufacturing and logistics face more varied tasks each year, making it hard for robots to handle alone. This system makes it simpler for people and machines to work together safely on jobs like moving heavy items.
The abstract doesn't explicitly state limitations, but it notes that the system is showcased in a test example, so its performance in diverse real-world scenarios may require further validation.
Ask anything about this paper. Answers come from its abstract, and say so when the abstract doesn't cover your question.
Programming and execution of skill-based human-robot-crane collaborative tasks — Taneli Lohi, Markku Suomalainen, Roope Mellanen et al.
Abstract licence: CC0
Explanation generated by Synthesis from the abstract — it is not the original paper. This is a preprint, so it hasn't necessarily been peer reviewed.