If it seems like the phrases artificial intelligence and machine learning are creeping more and more into the general lexicon, you aren’t mistaken. As the corporate world has less of an appetite to chalk up mistakes or setbacks to human error, there is pressure to make smarter business decisions and solve problems with the assistance of machines and computing.
Artificial intelligence is similarly making its way into the sports industry. Not just so teams and individual athletes can make smarter in-game or training decisions, but also for its value in enhancing the fan experience. One of the initiatives announced earlier this week at the Amazon Web Services (AWS) re:Invent 2018 Conference is that Formula 1 will be using AI to help power a number of new television graphics that it plans to debut during its 2019 season. Formula 1 had already entered into a partnership with AWS and debuted some graphical changes in the 2018 season, but it plans to increase its offerings next year.
During the ‘F1 Insights’ portion of the AWS conference, Formula 1 shared a bit about the fan experience changes that will tap into a wide range of car data at its disposal, in order to give fans unique insight into the race and car right in the heat of competition.
As F1 managing director Ross Brawn set out to improve the fan experience through data, his focus shifted towards providing fans with access to some of the data that is already available to teams in the pit. He also believes that artificial intelligence can provide television viewers with a unique insight into races and help them see what their favorite racers and race teams see as they make the numerous split-second decisions that are critical for each competition.
"For the 2018 F1 season we started the process," Brawn said. "We're digging deeper to show you where the performance is coming from -- when is a car faster, why is it faster?.
Brawn plans to implement these changes utilizing the Sagemaker tool that Amazon has developed to assist in these decisions through machine learning. Sagemaker is Amazon’s machine learning tool being utilized across multiple industries. For Formula 1 it is being used to improve the viewing experience for fans at home.
"For next season we're expanding F1 Insights for our viewers, Brawn said at re:Invent. “By further integrating the telemetry data, such as the car position, the tire condition, even the weather, we can use Sagemaker to predict car performance, pit-stops and race strategy. There will be some exciting new AI integrations into next year's F1 TV broadcast."
During Brawn’s presentation, he broke down the machine learning objectives for F1 into three categories. The first is to offer improved insight into the state of each driver’s tires so fans can have a better understanding of the dynamics of the importance of tires to an F1 race.
"We know that somebody is in trouble: his rear tires are overheating," said Brawn. "We can look at the history of the tires and how they have worked and where he is in the race, and machine learning can help us apply a proper analysis of the situation. "We can bring that information to the fans and make them understand if the guy is in trouble or if he can manage the situation. These are insights the teams always had but we are going to bring them to the fans and show them what is happening."
The second graphical tool takes historical data and utilizes it to predict, in real time, the probability or likelihood that an overtaking move might occur between drivers. Having the AI tools to access large amounts of previous race data will give fans these unique insights, all in real-time. He even mentioned that teams don't currently have access to this particular data so fans will have information that the race teams themselves don’t even possess during races.
"Wheel-to-wheel racing is the essence, a critical aspect of the sport and now with machine learning and using live data and historical data, we can make predictions about what is going to happen," said Brawn. "The graphic shows what we expect is going to happen in this event. What is great about this, is that the teams don't have all this data. We as F1 know the data from both cars and can make this comparison, and this has never been done before."
The final example that Brawn mentioned is data that resulted from its pitstop analysis which is being used to demonstrate the strategic improvements made to a car during a pitstop. Timing these pit stops correctly and making them more efficient can often make the difference between winning or losing a race. This analysis will offer fans a greater insight into the strategic decisions that determine the utilization of each pit stop during the race.
"Stopping at the right time and fitting the right tire can win or lose a race," Brawn said. "We are going to take all the data and give fans an insight into why they stopped and when they stopped - did the team and driver make the right call?"
Artificial intelligence and machine learning are unquestionably going to change sports, not only for the fans at home but also for the participants in the race or sporting event. It will provide large amounts of data in real time to help optimize each decision. This move forward by F1 demonstrates that large-scale adoption is not only coming but is already here in some cases. Brawn also mentioned that Sagemaker will be utilized as well to evaluate new face formats or starting grids for longer-term decisions for the organization. These uses unquestionably demonstrate that sports will continue to make fundamental changes, thanks to the expanded utilization of machine learning and the strategic analysis of the data it provides.
