How does artificial intelligence help F1 teams?
Artificial intelligence has completely transformed how teams use the wealth of data. With the help of McLaren, F1technical's lead journalist Balázs Szabó reveals how AI has changed teams' working methods in recent years.
AI has enjoyed a rapid rise to prominence in recent years, exploding across the wider world and developing even faster than people’s understanding of how to use it. Unlike many inventions from the last few decades, it came with no user manual but so many possibilities, especially in Formula 1, which shares one major trait in common with AI: it loves data.
McLaren reckon that artificial intelligence defines its procedures so much that they do now know how they would now operate without it.
While too much data can be overwhelming and counterintuitive for humans, the AI can digest and cut through it, telling teams precisely what is useful and what they can disregard. And the more data a team feeds AI, the smarter it gets.
What is AI and why is it used in F1?AI, short for Artificial Intelligence, learns by being fed data and instructions, detailing what the data is and how to use it. The more information it consumes and the more instructions it’s given, the better it gets at performing tasks.
McLaren works closely with Dell Technologies who is an industry catalyst for AI innovation. Utilising their AI Factory, a system of services, hardware, data management, and partner integrations, McLaren are able to quickly operationalize all of the components required to plan and deploy their own AI solutions.
Revealing what the AI can be used for, McLaren added that the possibilities include organising and categorising data, spotting anomalies and mistakes, and even searching for images. It can also help teams write instructions, emails, or any other form of copy.
When it comes to the key moments of the evolution of data analysis, McLaren highlightes the moment when when wireless transmission became available, which allows for data transfer from sensors on the car to a Dell Technologies data center.
The second significant change was in weight saving, with the car's sensors becoming considerably lighter and thus impacting speed less.
Data collection has snowballed since, and cars are now kitted out with 300-600 sensors during sessions. More are bolted on during practice when weight isn’t relevant and less during Qualifying and the Grand Prix. The sensors measure everything from the engine and tyre temperatures to air intake, gear ratios and the airflow over cars. The most significant differential, without doubt, is aerodynamic data.
Some of this data is used live during the session for operational reasons or to make decisions, and some is fed back to the team at the factory, who are working on future races and upgrades and use it to improve the car’s design and make it faster. The Woking-based outfit uses that data to figure out the car's strengths and weaknesses which can then help the team define the development path.
Having become McLaren F1's first Data Scientist, Andrew McHutchon reckons that cars are much more complex than before which means that it became vital to digest the data collected throughout on-track sessions.
“The cars are significantly more complicated now than ever,. They have electric hybrid engines, so we need to measure the battery voltages and charge, as well as the fuel, temperature, and oil pressure.
"Then there’s the gearbox, which is computer controlled to change gears faster than the blink of an eye, but can rip itself apart just as quickly if a problem isn't spotted immediately. As the car has become more complicated, we’ve adapted with it and collect data to manage it.”
“Previously, we've collected data that we didn't know what to do with, but now, with AI and by working with Dell Technologies’ AI Factory, we can process the data in a much richer way to extract meaningful learnings from it.
“A lot of the hardware we use is very hard to get hold of. Every company in the world wants to get their hands on these, so we’re fortunate that we can leverage Dell Technologies and get access to this equipment before others are able to, which can give us a bit of an advantage.”
The Woking-based outfit reckons that a lot of the hardware is actually has been created by Dell Technologies to match its exact requirements.
“If you’ve got a problem, they’ll work with you to ensure they’re providing the best kit to tackle that problem, using their list of industry-leading partners to provide a tailor-made solution.
“If it's a decision related to pitting, you may only have a third of a lap before the car passes the pit lane, and after that, you’ve lost your opportunity, so you need to be fast. You could have terabytes and terabytes to analyse, which could take half a day or more to answer just one question without AI.
“But even when it comes to the team back at the factory working on the car’s development, speed matters. You may have five questions, and if it takes you half a day to answer each, that slows everything down. AI speeds all of that up, and the faster we can answer these questions, the faster we can develop the car and the more likely we are to win championships.”
