Amazon Web Services (AWS) and the NFL have teamed up to simulate entire football games with the goal of predicting and preventing player injuries using a new platform called Digital Athlete.
The system was announced during AWS re:Invent conference in Las Vegas on Thursday. AWS and the NFL have integrated machine learning and artificial intelligence to simulate games while identifying and predicting injury risk scenarios, which they then can apply on the field.
“We believe this will revolutionize the way we do injury prevention, rehabilitation, and player recovery in the NFL,” Dr. Jeff Crandall, chairman of the NFL’s engineering committee and director of the University of Virginia’s Center for Applied Biomechanics, said during Thursday’s press conference.
Crandall said the concept of Digital Athlete is a virtual representation of some of the top-performing athletes in the world and putting them in various virtual scenarios so injuries can be prevented, and so companies making safety equipment like helmets can create better products. The system could also be used to create new rules for the game.
Crandall said they’ve already looked at 100,000 actual helmet impact footage as part of the data collecting, and this aspect is important since players are being subjected to a horrifyingly high risk of concussion and other head trauma. In 2018 alone, there were 214 diagnosed concussions in NFL players.
The Digital Athlete platform uses AWS technology, including Amazon Rekognition, to tap into the NFL’s already massive data set and video feeds.
“By leveraging the breadth and depth of AWS services, the NFL is growing its leadership position in driving innovation and improvements in health and player safety, which is good news not only for NFL players but also for athletes everywhere,” Andy Jassy, CEO of AWS, said in a press release. “This partnership represents an opportunity for the NFL and AWS to develop new approaches and advanced tools to prevent injury, both in and potentially beyond football.”
Beyond football, this kind of predictive technology would be able to become broadly applicable in the future.
“It is hard to overstate its potential. It has opportunities across things like workplace safety, architecture, and building design,” said Dr. Matt Wood, the Vice President of Artificial Intelligence at AWS at the re:Invent conference. “There’s even the possibility of applying it more broadly to healthcare more and more precise models for treatment.”