AI
Revving Up Efficiency: How NASCAR Teams Harness AI for Game-Changing Pit Stops
To look at this article again, go to My Profile and then click on View saved stories.
NASCAR Pit Teams Employ Artificial Intelligence for Optimal Pit Stops
Liberty Media, the financial backbone of Formula One, has significantly immersed the competition in the American market by introducing three grand prix events in the United States. Despite this, NASCAR is experiencing growth in its television viewership within the country, contrasting with a minor decrease in viewers for the "open wheel" racing series, F1 and IndyCar.
European enthusiasts often look down on stock car racing, yet there's a unique appeal in watching a seemingly basic, naturally aspirated pushrod V8 engine, with a volume of 358 cubic inches (5.8 liters) and producing 670 horsepower, speed around an oval track in a way that other racing circuits don't match or have possibly abandoned.
It's not as if Nascar teams aren't seeking every possible technological edge. Lenovo has partnered with one of the premier entities in the series, Richard Childress Racing, aiming to refine their pit stop strategy during competitions. Given the frequency of pit stops in the Nascar Cup Series, which can range from five to twelve based on the track and race conditions, this collaboration is significant. Specifically, they're leveraging artificial intelligence to obtain instant data on refueling strategies.
Fuel efficiency plays a vital role in the strategy and suspense of Nascar racing, bordering on a form of craft. It's important to note that in Formula 1, refueling during races has been prohibited since 2010 due to concerns over expenses and safety. Nascar vehicles do not come equipped with fuel gauges inside the driver's area, making it essential for team strategists to meticulously track how much fuel is added at pit stops and its consumption rate throughout the race.
Similar to other scenarios, the amount of fuel used is influenced by various factors such as the track's size and layout, as well as the pace at which the vehicles are racing. Throughout a race, there are several instances referred to as "cautions," during which the cars generally consume fuel at half their normal rate.
In Nascar racing, competitors employ a tactic known as "drafting," which allows them to keep up their pace within the group without needing to fully press the gas pedal. This results in lower fuel usage, leading to fewer and shorter pit stops. Generally, a vehicle competing in the Nascar Cup series, which isn't exactly known for its fuel efficiency, will burn through about 100 gallons (380 liters) of fuel during a race.
Speed is Enhanced by Reduced Weight
Although not strictly scientific, Lenovo's artificial intelligence group is dedicated to refining their approach to nearly scientific precision. RCR believed that by accurately gauging the duration the fuel containers were attached to their vehicles, its team could more accurately determine the amount of fuel dispensed.
The assignment given was succinct. In response, Lenovo engineered a solution involving the use of transponders within the vehicle and a camera positioned atop RCR's pit area. This setup was designed to detect the moment a car enters the designated space and initiate a live video stream.
Lenovo's AI data scientist, Sachin Wani, describes how their AI system examines every single image to determine if the fuel canister is connected or not. "We analyze the footage at a rate of 30 frames per second, achieving precision up to approximately 0.03 seconds. Before implementing this technology, the person responsible for refueling had to estimate the need to supply fuel for around seven seconds, without the aid of any instruments due to safety issues," he elaborates.
"Essentially, it boiled down to doing the math in their heads, which resulted in seven seconds possibly stretching to eight or nine, or even more problematic, dropping to five or six. This, of course, throws off the entire strategy, leading to a scenario where they haven't added enough fuel and must make an additional pit stop," explains Wani.
Lenovo's advanced AI is now taking on much of the demanding work in the fast-paced world of car racing. During a pit stop, a fuel canister is attached to the vehicle, allowing around 11 gallons of high-quality racing fuel to be poured into the vehicle's tank. As the pit crew moves from changing the tires on one side of the car to the other, the person responsible for refueling can switch to a new can of fuel. The fuel tank in a Nascar car, known as a fuel cell, can carry up to 20 gallons (76 liters). The weight of a liter of fuel varies around 0.75 kilograms, depending on its specific make-up. In the competitive realm of motor racing, where every detail counts, even a slight delay in refueling can negatively impact the vehicle's weight and its performance on the track. The principle here is straightforward: the lighter the car, the faster it can go.
NASCAR's Numerical Strategy
Eric Kominek, RCR's technical director, notes, “The AI boosts teams' trust in their calculations,” explaining that the combination of telemetry data and precise fuel measurements permits teams to estimate fuel consumption with an accuracy of up to 100 feet. This precision is crucial for teams looking to either avoid unnecessary fueling delays during upcoming pit stops or to strategize for optimal placement at critical points in the race or at its conclusion. The AI's fuel usage predictions play a significant role in these planning efforts.
Sachin Wani mentioned that Lenovo refined its NASCAR AI assistant using a proprietary dataset before optimizing it for the highest precision. "We examined various weather scenarios, races at night, among other factors. There's a chance the driver could miss his target entering the pit stop. Therefore, we had numerous situations to account for. The bulk of 2023 was dedicated to preparing the AI system for the 2024 series," Wani explained.
The efforts continued beyond the initial phase. According to Wani, his group is diligently enhancing the artificial intelligence system, focusing also on other urgent aspects. They are examining the exact angle for connecting the fuel can to improve the efficiency of fuel transfer. Additionally, they intend to equip the tire team with GoPro cameras to assess if the wheels' single lug nuts have been adequately secured during a pit stop.
"David Ellison, the chief data scientist at Lenovo, confessed that none of them were avid Nascar enthusiasts prior to starting this project. He mentioned that they have gained a significant amount of knowledge and have come to truly admire the way the teams function."
Recommended for You…
Direct to your email: A selection of our top stories, curated daily just for you.
A faulty update from CrowdStrike led to a global computer malfunction
Major Headline: The Potential Timeline for the Atlantic Ocean's Disruption
Introducing the age of excessive online consumption
DYSON AIRWRAP OFFER
Receive a complimentary $60 Case and a $40 Gift with your purchase
Receive Up To An Additional 45% Discount During The August Sale
Vista Print Promo Code: Save 20% on Certain Signs
Discount Code for 10% Reduction at Newegg
Peacock Premium Subscriptions Begin at Only $7.99/Month
Discover DJI's Exclusive Educational Discounts for Students in 2024
Additional Content from WIRED
Evaluations and Tutorials
© 2024 Condé Nast. All rights reserved. WIRED might receive a share of revenue from items bought via our website, which is part of our Affiliate Agreements with retail partners. Content on this site cannot be copied, shared, broadcast, stored, or utilized in any form without explicit consent from Condé Nast. Advertising Options
Choose a global website
Discover more from Automobilnews News - The first AI News Portal world wide
Subscribe to get the latest posts sent to your email.