POMPEI, ITALY – After centuries of being shattered and buried, ancient Roman frescoes in Pompeii have been given a second life thanks to a pioneering robotic assembly system designed to assist archaeologists with one of the most arduous tasks: restoring fragmented artifacts.
Developed under an EU-funded project called RePAIR, the technology combines advanced image recognition, AI-driven puzzle solving and ultra-precise robotic hands to accelerate repair tasks that are traditionally slow and often frustrating.
Pompeii, a once prosperous city near Naples, and its surrounding countryside were submerged in volcanic ash following the eruption of Mount Vesuvius in 79 AD. Ironically, even though the eruption killed thousands of people, it saved much of the city.
Among the most valuable items on this site are the original frescoes found inside homes and businesses. Some frescoes still remain on the walls, others are in a fragmentary state. Archaeologists hope to reassemble the painting and restore it to its former glory.
The process is not easy. “It’s like buying four or five jigsaw puzzles. You mix them all together, then throw away the box and try to solve four or five puzzles at the same time,” said Dr. Marcello Perillo, a computer science professor at the University of Venice and coordinator of the robotics project.
The system consists of two robotic arms with soft, flexible hands in two sizes. You can grab and assemble the pieces by hand without damaging delicate surfaces. The visual system identifies specific fragments.
Experts in artificial intelligence and machine learning have developed an algorithm to reconstruct the fresco by matching colors and patterns that may be invisible to the human eye. Experts say the task is similar to solving a giant jigsaw puzzle, but with additional challenges such as missing pieces and no reference image of the final result.
After capturing and digitizing images of individual fragments, the system attempts to solve the puzzle, sometimes working with archaeologists who can identify mistakes or make suggestions. Once the system identifies a match, it instructs the robot to place the fragment in the desired location.
Looking for quick answers on assembly and manufacturing topics?
Try Ask ASM, our new smart AI search tool.
Contact ASM
