Genetic Algorithms in Real Life Applications

Designing with evolution

NASA is responsible for perhaps the most famous application of genetic algorithms, as they used them to evolve the design of an antenna for maximum efficiency aboard their ST5 mission. They were able to produce a number of viable designs in a short amount of time, replacing the usual labor-intensive work of designing by hand. Their algorithms also produced a number of unique designs that likely would never have been considered by human designers.

The concept of evolving designs extends to other fields as well. For example, game designers use artificial intelligence to develop unique levels. As you learned in the previous lesson, you can use evolution as a viable alternative to other machine learning approaches. Imagine you were a game designer tasked with designing new levels for a new puzzle game. Your task is to design 500 unique levels. Using a genetic algorithm, you could evolve levels from a collection of a few hand-designed levels to be sufficiently different from one another, adding penalties for levels that are invalid or impossible to complete.