As Sam Rivera explained to me, the success of FIFA 22The new animation technology will look at what it was not recorded during an innovative motion capture session (attended by 22 players all playing a football game from start to finish) earlier this year.
“We started working on an algorithm about three years ago,” Rivera explained, FIFA 22leading game producer at EA Vancouver. “What this algorithm does is learn from all the data in this motion capture session: how the players approach the ball, how many steps they take to get to the ball, are three long steps and one short step; what is the right angle, with the right cadence, to hit that ball properly? “
Then, says Rivera, “create this solution, create the animation in real time. It is a very, very cutting edge technology. This is basically the beginning of machine learning that takes over animation. ”
In a dozen years dedicated to covering sports video games, I’ve found that their almost annual claim to new animations, often a record number and more than ever, is a marketing cliché. Recording a lot of attractive stunts doesn’t necessarily mean regular players see anything of it. Nearly a decade ago, NBA Live designers told me they scoured the remains of the abandoned NBA Elite 11 and discovered a bunch of amazing blocks and dunks that the game engine would simply never serve. The lesson: recording these things is fine, delivering it is where the rubber meets the road.
In FIFA 22In the case, his motion capture team could have captured the real anguish of a goalkeeper beaten by the decisive scoreboard, in a 4-2 match between two real-life rivals of the Spanish First Division RFEF (the third nation level). But neither that, nor the desperate play of CD Gerena leading to Atlético Sanluqueño’s overwhelming counterattack, should be the reason why home players feel they are seeing a more realistic presentation of football or that the they find it more fluid and sensitive as they play it.
HyperMotion, as it is called, because, yes, vendors will also market these animations, allows Rivera and his developing colleagues a proposal that has both modes in terms of player movement and interaction, he said. “We used to prioritize short animations, so the game responded,” he explained. “If you have a long animation, the game looks good, right? But if the situation changes [in the middle of the animation], there is a defender coming, you are trapped, they will probably attack you and that doesn’t feel right.
“With access to HyperMotion, we can introduce longer animations, longer ball control animations,” Rivera said, “but technology allows us to move from animation to another type of animation, if the situation changes “.
More specifically, HyperMotion will be seen in things like defensive training that keeps its shape and moves more constantly. This will probably be the first and most visible evidence of the players from the recording session of the 22 in the new game. In previous editions of FIFA, AI usually directed players in groups of two, perhaps three, depending on who was closest or if someone was asking for support manually.
Players of FIFA 22 you should find the toughest defense to separate or challenge from you to you. And in response, off-ball players on offense will move more naturally to support a run, perhaps ameliorating the common frustration that is noticed in higher difficulties or online multiplayer.
“It simply came to our notice then FIFA 22 and the closed beta version, people definitely shout that there are a lot of features that make the game different: it feels different, ”Rivera said. “We were recording something with our professional [esports] players, and tried to play a game similar to FIFA 21. And they didn’t necessarily score many goals. Even the game of chance creation, you have to think a little differently. All the things that changed the animations, that we changed in the game, in terms of positioning, very different experience. And this [experience] it was, “It feels cool.”
As Rivera said, this is “the beginning of machine learning that takes over animation,” and EA Vancouver’s FIFA team is aware that their work could have applications in other EA products. Sports, if not in other Electronic Arts games in general. However, in the first year of implementation of HyperMotion, Rivera said his team was fully focused on achieving this. FIFA 22, and less on the use of this as proof of concept.
Implementation of most of Rivera’s work HyperMotion was neither in the algorithm (which was done by a division of advanced work in EA Vancouver) nor in motion capture. Rivera and his team worked on building pipes and processes to accept, interpret, and use everything his machine learned and spit out. These processes are game-specific, he said. If NFL designers Madden tried the same in their sport, they would have to develop their own. And Rivera ‘s first client is FIFA 22 player, anyway, not another developer of your company.
“At a high level, what we heard most is that people wanted more differentiation” between players on the virtual playing field. Every year he has certain doubts, problems and feats, he said, but “we knew that what people wanted was a leap in terms of differentiation and realism, making sure the game looked better. So we knew we needed a bigger investment in terms of animation and technology. ”
This took three years, with a 90-minute limit in a field in Spain. “It multiplies 22 times, that’s what allows us to get to the game, what, 4,000 animations alone FIFA 22? ”
Ah, here it is! The count of animations. But Rivera is legitimately proud of it. “It’s a record for us,” he says.
List file is Polygon’s news and opinion column on the intersection of sports and video games.