AI Daily - Artificial Intelligence News

View Original

AI Develops More Lifelike Game Characters

It is agreed that, to make an extraordinary video game, striking graphics, skilful animation and clever code – plus many hours of diligence is required.

Researchers at ElectronicArts – the corporates behind FIFA, the Sims and other popular games - are testing contemporary advances in artificial intelligence as a way to speed the development process and make games appear more practical.

Here are examples of some of the multitude of games owned by EA. Image credit: Google

A team from EA and the University of British Columbia in Vancouver are using a technique called reinforcement learning which is essentially the use of an algorithm performing certain tasks and receiving rewards or punishments depending on how close it is achieving the task that’s been set. By doing this, it automatically animates humanoid characters.

Customarily, characters and their movement are crafted manually in video games. Sports games, akin to FIFA, make use of a motion capture – the process of recording the movement of objects or people. However, the possibilities are restricted by the movement that’s been recorded, and code nonetheless must be written to animate the character.

Through automation of the animation process, along with other elements of game design and development, AI could save firms that specialise in games million of dollars while making games more efficient and appear more authentic. This is to ensure a complex game can run on a smartphone, for example.

Reinforcement learning has ignited excitement in recent years by allowing computers to learn in order to play complex games and solve vexing problems without any instructions. In 2013, researchers at DeepMind used reinforcement learning to design a computer programme that learned to play several Atari video games to a superhuman level. The program learned to play through experimentation and feedback from pixels and the game score. The same technique was later employed to construct a programme that accomplished the fiendishly complex and subtle board game Go, amongst other things.

To make the character, a machine-learning model was first trained to identify and reproduce statistical patterns in motion-capture data. Reinforcement learning was then used to train another model to reproduce realistic motion with a specific objective, such as passing a ball to another player. This primarily means the program learns how the soccer player moves and can then animate the moves accordingly.

As consoles, computers, and smartphones have become ever-more exceptional, games will become increasingly sophisticated, requiring greater expenditure from game companies. Existing equipment can help assist both designers and animators to become more efficient, but they’re still necessary at every step. Just as AI can simply concoct photo-realistic faces and scenes when given enough data, algorithms may automate the fabrication of new characters and scenes.

AI could generate content for other genres, including action and role-playing games. Some establishments are experimenting with procedural technology in order to make video games more expansive. A simple method is used to generate new worlds for players to explore in No Man’s Sky, a space-based survival game released in 2016.

At the other end of the spectrum, AI can be seen to generate simple video games from scratch. Researchers from the University of Toronto, MIT, and Nvidia, revealed an AI engine that learned how to recreate the classic PAC-Man without any of the original code.

Researchers showed how a programme called GameCAN can recreate simple games by watching the screen and monitoring controls used during 50,000 games of PAC-Man. Image Credit: Getty Images

It took 10 engineers at Namco, the company behind PAC-Man, 17 months to design, program, and test the original game. If given enough data, such an algorithm might eventually create a compelling new game – Candy Crush or Angry Birds that no one needed to code.