Google: Stadia to fight lag with machine learning to predict inputs

Google: Stadia to fight lag with machine learning to predict inputs

Upcoming streaming platform Stadia will be using machine learning and modelling techniques to predict user inputs.

That's according to Google VP of engineering Madj Bakar, who told Edge - as reported by PCGamesN - that the search and software giant planned to use AI to help cut down on lag, a concept he calls "negative latency."

This would combat one of the main issues facing streaming technology; that an internet connection to a remote server farm would not be able to convey a user input and respond as fast as if the player pressed a button on a piece of hardware in the same room.

“Ultimately, we think in a year or two we’ll have games that are running faster and feel more responsive in the cloud than they do locally,” Bakar said, “regardless of how powerful the local machine is.”

The obvious problem here is how accurate the predictions Stadia's machine learning tech would be making are - it might anticipate one course of action with the user deciding to take another.

Google announced its Stadia platform at GDC 2019, though failed to address many of the basic questions the world had about how the tech would actually work. Microsoft's Phil Spencer has taken issue with the search firm's claim that Stadia will have no lag, saying that the Big M hasn't made similar claims with its own xCloud streaming service for a reason.

Google has also said multiple times that it is committed to Stadia, having previously launched and subsequently myriad initiatives.

Oh, and here is who is working on Stadia over at Google

PCGamesInsider Contributing Editor

Alex Calvin is a freelance journalist who writes about the business of games. He started out at UK trade paper MCV in 2013 and left as deputy editor over three years later. In June 2017, he joined Steel Media as the editor for new site In October 2019 he left this full-time position at the company but still contributes to the site on a daily basis. He has also written for, VGC, Games London, The Observer/Guardian and Esquire UK.