FIFA 22 brings machine learning to the field with HyperMotion



[ad_1]

As Sam Rivera explained to me, the success of FIFA 22New animation technology will be seen in what was not recorded during a groundbreaking motion capture session – involving 22 players all playing a football game from start to finish – earlier this year.

“We started working on an algorithm about three years ago,” explained Rivera, FIFA 22Senior Gameplay Producer at EA Vancouver. “What this algorithm does is learn from all the data for this motion capture shoot – how the players approach the ball, how many steps do they take to reach the ball, is it three long steps and one short? step: what is the right angle, with the right cadence, to hit this ball correctly? “

Then, says Rivera, “he creates this solution, he creates the animation in real time. It’s very, very forward-thinking technology. It’s basically the beginning of machine learning taking over from animation. .

In a dozen or so years of covering sports video games, I have found their near-annual demand for new animation, often in record numbers, more than ever, to be a marketing cliché. Recording a bunch of eye-catching acrobatics doesn’t necessarily mean regular gamers will see one. Almost a decade ago, the designers of NBA Live told me they sifted through the remnants of NBA Elite 11 and discovered tons of amazing blocks and dunks that the game engine would simply never serve. The lesson: recording this stuff is good, delivering it where the rubber meets the road.

In FIFA 22In the case of, their motion capture team could have felt the genuine anguish of a goalkeeper beaten by the decisive score, in a 4-2 game between two real rivals of the Spanish Primera División RFEF (third division of the country). But neither that, nor CD Gerena’s desperate play leading up to Atlético Sanluqueño’s overwhelming counterattack, should be the reason home players feel like they’re watching a more realistic presentation of football, or find it more fluid and responsive when playing it.

HyperMotion, as it’s called – because, yes, marketers are going to market these animations as well – allows Rivera and her development colleagues a two-way proposition when it comes to player movement and interaction, has he declared. “In the past, we used to prioritize short animations, so the game is responsive,” he explained. “If you’re in a long animation, the game looks good, right?” But if the situation changes [in the middle of the animation], there’s a defender coming in, you’re stuck, you’re probably going to get tackled, and it doesn’t feel good.

“With access to HyperMotion, we can put longer animations on it, longer ball control animations,” Rivera said, “but the technology allows us to move from the middle of animation to a different kind of animation. ‘animation, if the situation changes. “

More concretely, HyperMotion is going to be seen in things like defensive formation maintaining its shape and moving together more consistently. This will probably be the first and most visible evidence players will see of the 22-recording session in the new game. In previous editions of FIFA, the AI ​​typically led players in pairs, perhaps three, depending on who was closest or if someone was manually called for help.

The players of FIFA 22 should find the defense more difficult to separate or challenge one-on-one. And in response, offensive players will move more naturally to support a run, perhaps improving a common frustration felt in higher difficulties or online multiplayer.

“Now that we have received feedback on FIFA 22 and the closed beta, people are clearly saying that there are a lot of features that make the game different – it’s different, ”Rivera said. “We were recording something with our pro [esports] players, and they were trying to play a game similar to FIFA 21. And they didn’t necessarily score a lot of goals. Even the game of creation of chance, you have to think a little differently. All the things that the animations have changed, that we have changed in the game, in terms of positioning, very different experience. And that [experience] was, “It’s cool. “

As Rivera said, this is “the beginning of machine learning taking precedence over animation,” and the FIFA team at EA Vancouver are aware that their work could have applications in other products. EA Sports, and even in other Electronic Arts games in general. In HyperMotion’s first year of implementation, however, Rivera said his team was completely focused on getting that right in. FIFA 22, and less on using that as a proof of concept.

Most of Rivera’s work implementing HyperMotion wasn’t into the algorithm (which was done by an advanced work division at EA Vancouver) or motion capture. Rivera and her team were working to create pipelines and processes to accept, interpret, and use whatever their machine had learned and spat out. These processes are specific to their game, he said. If the designers of Madden NFL were to attempt the same in their sport, they should develop theirs. And Rivera’s first customer is the FIFA 22 player, anyway, not another developer in his company.

“At high level, what we heard the most is that people wanted more differentiation” between the players on the virtual field. Every year there are certain baffles and issues and exploits, he said, but “we knew what people wanted was a leap in terms of differentiation and realism, making sure that the game is better. So we knew we needed a bigger investment in animation and technology.

It took three years, capped at 90 minutes on a pitch in Spain. “You multiply that 22 times, that’s what allows us to bring to the game over, what, 4000 animations just in FIFA 22? “

Ah, there it is! The number of events. But Rivera is legitimately proud of it, all the same. “It’s a record for us,” he said.

List file is Polygon’s news and opinion column on the intersection of sports and video games.

[ad_2]

Source link