ZHENGZHOU, China - In Zhengzhou, a police officer wearing facial recognition glasses spotted a heroin smuggler at a train station. In Qingdao, a city famous for its German colonial heritage, cameras powered by artificial intelligence helped police snatch two dozen criminal suspects in the midst of a big annual beer festival. In Wuhu, a fugitive murder suspect was identified by a camera as he bought food from a street vendor. With millions of cameras and billions of lines of code, China is building a high-tech authoritarian future. Beijing is embracing technologies like facial recognition and artificial intelligence to identify and track 1.4 billion people.

While Artificial Intelligence (AI) is being created for self-driving cars, medical advancements and generally for the betterment of humanity, or to beat a top Chess player, we don't see it used too often in the gaming industry. I'm not talking about AI in the sense of NPCs running away from danger or throwing a grenade back at you in a Call of Duty title, but instead, about powerful AI that could one day change the way games are developed. Well, some researchers have managed to get AI to build levels for the original DOOM without the help of humans. Let me be the first to say that I, for one, welcome our new AI overlords. This comes from a research paper, published by the Cornel University Library, entitled "DOOM Level Generation using Generative Adversarial Networks" authored by Edoardo Giacomello, Pier Luca Lanzi, and Daniele Loiacono.

An artificial intelligence network has designed new levels for the original Doom video game. The technique could be used to create future video games, more quickly and less expensively, researchers said. The AI was "trained" to make new levels by showing it human-designed ones for the popular first-person shooter. There are large numbers of Doom levels - both official and player-created - freely available online, providing a rich vein of data. Doom was released in 1993 and is considered to be a major milestone in video games history.

One of the longest-lasting and most successful video-game franchises is the Doom series, launched in 1993 and still going strong with over 10 million copies sold. The game is a first-person shooter in which a space marine battles to survive against various demons and zombies. The game is notable because it pioneered 3-D graphics for PCs running MS-DOS, introduced networked multiplay, and even allowed players to create their own game levels. Indeed, large numbers of Doom levels--both official and player-created--are now freely available online, forming a formidable corpus for study and research. And that raises an interesting possibility. Is it possible to use this data to train a deep-learning algorithm to create its own levels of Doom that a human would find compelling?

One of the longest-lasting and most successful video-game franchises is the Doom series, launched in 1993 and still going strong with over 10 million copies sold. The game is a first-person shooter in which a space marine battles to survive against various demons and zombies. The game is notable because it pioneered 3-D graphics for PCs running MS-DOS, introduced networked multiplay, and even allowed players to create their own game levels. Indeed, large numbers of Doom levels--both official and player-created--are now freely available online, forming a formidable corpus for study and research. And that raises an interesting possibility.

AI researchers do love their games and two papers have shown that they can use general adversarial networks (GANs) to make old favorites a lot more interesting. In two separate papers, AI researchers built general adversarial networks to construct new video game levels for Super Mario Bros, a popular platform game controlling a mustachioed man in red overalls to collect coins and avoid enemies to reach a princess, and DOOM, the classic first person shooter from the early 1990s. GANs were first introduced in 2014. The system is made up of two networks: a generator and a discriminator. The generator creates fake samples of training data, and a discriminator tries to determine if the samples are real or fake. Both networks spar with one another, and over time the generator learns to forge more realistic samples to trick the discriminator.

We applied Generative Adversarial Networks (GANs) to learn a model of DOOM levels from human-designed content. Initially, we analysed the levels and extracted several topological features. Then, for each level, we extracted a set of images identifying the occupied area, the height map, the walls, and the position of game objects. We trained two GANs: one using plain level images, one using both the images and some of the features extracted during the preliminary analysis. We used the two networks to generate new levels and compared the results to assess whether the network trained using also the topological features could generate levels more similar to human-designed ones. Our results show that GANs can capture intrinsic structure of DOOM levels and appears to be a promising approach to level generation in first person shooter games.