Artificial Intelligence, Robots, and Researchers from Zurich 

Researchers from a technical university are using artificial intelligence and four robots to construct Semiramis. This project carried out by researchers from ETH Zurich is a sort of huge sculptural planter “hanging gardens” inspired by the legendary structures in the ancient city of Babylon. The architectural structure mentioned above will feature five geometrically complex wooden pods, slightly offset from each other and supported by eight thin steel pillars.

The history of this project dates back to 2019. Semiramis is a collaboration between human as well as AI designers. Importantly, the general idea of course came from the creative minds of its creators, professors Fabio Gramazio and Matthias Kohler. However, the design was achieved by putting the basic requirements through a set of computer models and machine learning algorithms. 

During the design process, for instance, researchers might tweak the position of one of the large “pods” that make up the 70-foot structure. They also have the ability to change the layout of the panels that make up its surface. The software created by researchers would then immediately adjust the geometry of the overall structure and the other panels. Hence, they will be able to accommodate these changes, making sure it would still safely bear its own weight. 

Robots, artificial intelligence, and new opportunities 

There are numerous artificial processes in architecture. Still, this project pushes the boundaries out in the level of final control seemingly given to them. This project is very important as it helps to explore new technologies. 

Matthias Kohler expressed his opinion regarding the computer model. He stated that thanks to the computer model researchers can reverse the conventional design process. They can also explore the full design scope of a project. 

The university is shipping individual pod segments to the Tech Cluster Zug by a lorry on a regular basis. Semiramis will consist of 51 to 88 wooden panels. 

Researchers used artificial intelligence to learn more about the design. They developed a custom machine learning algorithm in cooperation with the Swiss data science center. The machine learning algorithm presented researchers with sophisticated options. Each option proposed a certain pod shape as well as spatial arrangement that would affect target variables, like pod irrigation. 

Humans and robots construct Semiramis together. Notably, a set of four robotic arms hold multiple heavy pieces in place while humans apply resin to keep them together.