<
>

Formula One plans to give fans data teams do not have have in TV broadcasts

play
F1 2019 predictions: Can Hamilton be caught? (2:34)

Jennie Gow and Jonathan Legard make their predictions for the 2019 F1 season, including Vettel vs Leclerc and Ricciardo at Renault. (2:34)

Formula One will use artificial intelligence to better explain racing to fans during broadcasts of events in 2019, using some data not available to the teams themselves.

F1 has entered into a partnership with Amazon Web Services to provide new graphics using its Sagemaker tool. Broadcasts used several new graphics in the 2018 season and bosses plan to increase this further next year.

While F1's motorsport director Ross Brawn wants to give fans access to some of the data available to teams on the pit-wall, he also believes AI can give TV viewers a unique insight of every race.

"For the 2018 F1 season we started the process," he said. "We're digging deeper to show you where the performance is coming from -- when is a car faster, why is it faster?

"For next season we're expanding F1 Insights for our viewers. By further integrating the telemetry data, such as the car position, the tyre 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."

Brawn showed three different examples on a screen, each of which focused on a key aspect of any grand prix: wheel-to-wheel racing, car performance and pit-stop strategy.

The overtaking graphic used a clip of Sebastian Vettel passing Lewis Hamilton at the Mexican Grand Prix in October, which he did at the end of the long run to Turn 1. During that clip, it showed Vettel's probability of completing the overtake climb from 44 percent up towards 100 as he closed in on the Mercedes, while it also showed he was more likely to pass Hamilton on the right -- which he did -- than on the left.

Brawn said this will be uncharted territory for F1 and its broadcasts.

"Here's another fascinating element for our fans -- overtaking. Wheel-to-wheel racing is the essence and critical aspect of the sport.

"Now, using machine learning and using live data and historical data, we can use predictions of what's going to happen. What's great about this is the teams don't have all this data. We as Formula One know the data from both cars and we can make this comparison, that's never been done before."

Brawn's talk can be seen at the video below.

Another graphic displayed during the talk stood alongside images of Nico HUlkenberg's Renault, showing various numbers to indicate the performance of his car. On the graphic appeared to be percentage figures for tyre life, fuel level and an 'overall performance' of his car.

"We know that someone is in trouble, his rear tyres are overheating, but we can look at the history of the tyres and how they've worked and where he is in the race.

"Machine learning can help provide us a proper analysis of the situation. We can bring that information to the fans and help them understand whether he's in trouble or whether he can manage the situation. These are insights the teams always had but now we're going to bring them out to the fans and show them what's happening."

As for helping fans better understand pit-stops and the strategy around each race, Brawn said: "It's major strategic element of the race and one stop is mandatory. Stopping at the right time, fitting the right tyre, can win or lose a race.

"We're going to take all the data and give the fans and insight into why they stopped and when they stopped -- 'did the team and driver make the right call?'"