Resumen:
In this paper, we present our work on the training of robotised architectural components of intelligent buildings, focusing on how architectural components can learn to behave animalistically, according to the judgment of human users. Our work aims at recovering the lost contact with animals in the urban context, taking advantage of biophilic empathy. The parameters governing the robotised elements we propose are mainly qualitative (emotions and aesthetical perception), which cannot easily be described by mathematical parameters. Additionally, due to their complexity, it is often impossible –or at least impractical, to hardcode suitable controllers for such structures. Thus, we propose the use of Artificial Intelligence learning techniques, concretely Evolutionary Algorithms, to allow the user to teach the robotised components how to behave in response to their resemblance to specific animal behaviors. This idea is tested on an intelligent façade that learns optimal configurations according to the perception of aggressiveness and calmness.