As Part of the Autonomous Racing League Event That Pitted a Self-driving Car Against an F1 Driver – Autoblog

Wander through the box At any professional motorsport event, especially Formula 1, you will see endless computer screens full of telemetry. Modern teams are inundated with real-time digital feedback from the cars. I’ve been in many of these pits over the years and marveled at the streams of data, but I’ve never seen an instance of the Microsoft Visual Studio software development suite running there amidst the chaos.

However, I have never taken part in anything like the first event of the Abu Dhabi Autonomous Racing League last weekend. The so-called A2RL isn’t the first autonomous racing series: There’s the Roborace series, in which autonomous race cars set fast lap times while avoiding virtual obstacles, and the Indy Autonomous Challenge, which most recently took place at the Las Vegas Motor Speedway during CES 2024.

While the Roborace focuses on single-car time trials and the Indy Autonomous series focuses on oval action, A2RL has set out to break new ground in some areas.

A2RL brought four cars onto the track and competed at the same time for the first time. And perhaps even more significantly, the most powerful autonomous car competed against a human, former Formula 1 driver Daniil Kvyat, who drove for various teams between 2014 and 2020.

The real challenge lay behind the scenes, with teams made up of an impressively diverse cadre of engineers, from aspiring programmers to graduate students to full-time race engineers, all battling to find the limit in a whole new way.

Unlike Formula 1, where ten manufacturers design, develop and produce completely bespoke cars (sometimes with the help of AI), the A2RL race cars are completely standardized to create a level playing field. The 550 hp machines borrowed from the Japanese Super Formula Championship are identical in construction and the teams are not allowed to change a single component.

This includes the sensor array, which consists of seven cameras, four radar sensors, three lidar sensors and, on top of that, GPS, all of which are used to perceive the world around you. As I strolled around the pits and chatted with the various teams, I learned that not everyone is making full use of the 15 terabytes of data that each car absorbs every single lap.

Some teams, like Indianapolis-based Team Code19, began working on the monumental project of developing a self-driving car just a few months ago. “There are four rookie teams here,” said Code19 co-founder Oliver Wells. “Everyone else takes part in such competitions, some for up to seven years.”

It’s all about the code

Munich-based TUM and Milan-based Polimove have extensive experience running and winning both the Roborace and the Indy Autonomous Challenge. This experience transfers just like the source code.

“On the one hand, the code is constantly being developed and improved anyway,” says Simon Hoffmann, team leader at TUM. The team made adjustments to adapt cornering behavior to the sharper curves of the road and also to adjust overtaking aggression. “But in general I would say we use the same basic software,” he said.

During the numerous qualifying rounds over the weekend, the teams with the most experience dominated the timesheets. TUM and Polimove were the only two teams to complete lap times under two minutes. However, Code19’s fastest lap was just over three minutes; The other new teams were far slower.

This has created a level of competition that rarely exists in software development. While there have been competitive coding challenges like TopCoder or Google Kick Start before, this is a completely different matter. Improvements in the code mean faster lap times – and fewer crashes.

Kenna Edwards is a Code19 assistant race engineer and a student at Indiana University. She had some experience in app development, but had to learn C++ to write the team’s anti-lock system. “It saved us from crashing at least a couple of times,” she said.

Unlike traditional coding problems, which may require debuggers or other tools to monitor, improved algorithms here produce tangible results. “It was cool to see how the flat spots on the tire improved over the next session. Either they have decreased in size or frequency,” Edwards said.

This implementation of the theory not only provides exciting technical challenges, but also opens up viable career paths. After previous internships at Chip Ganassi Racing and General Motors and thanks to her experience with Code19, Edwards will begin working full-time at GM Motorsports this summer.

A look into the future

This type of development is a big part of what A2RL is about. In addition to the main action on the track, there is a second series of competitions for younger students and youth groups around the world. Before the A2RL main event, these groups competed against each other with autonomous 1:8 scale model cars.

“The goal is that next year we will keep the smaller model cars for the schools, for the universities we might keep it with go-karts, a little bigger, they can play with the autonomous go-karts. And then “If you want to be in the big league, you start racing these cars,” Faisal Al Bannai, the secretary general of the Abu Dhabi Advanced Technology Research Council, told the ATRC. “I think if they recognize that path, I think you’ll encourage more people to get into research and into science.”

It is Al Bannais ATRC that foots the bill for the A2RL, covering everything from the cars to the hotels for the numerous teams, some of which have been testing in Abu Dhabi for months. They also threw a world-class party for the main event, complete with concerts, drone racing, and ridiculous fireworks displays.

The action on the track was a little less spectacular. The first attempt at a four-car autonomous race was aborted after one car spun and blocked the following cars. However, the second race was far more exciting and included a lead at the front when the University of Modena’s Unimore team car went wide. It was TUM that made it through the race and took home the lion’s share of the $2.25 million prize money.

As for the battle between man and machine, Daniil Kvyat made quick work of the autonomous car, overtaking it not once but twice to great cheers from the gathered crowd of more than 10,000 spectators who took advantage of the free tickets to watch a little history – – plus around 600,000 more streaming the event.

The technical glitches were unfortunate. Still, it was a remarkable event to witness, illustrating just how far autonomy has come – and, of course, how much more progress still needs to be made. The fastest car was still more than 10 seconds behind Kvyat’s time. However, it ran smooth, clean laps at an impressive speed. This is in stark contrast to the first DARPA Grand Challenge in 2004, where every single participant either crashed into a barrier or went on an unplanned sojourn into the desert.

For A2RL, the real test will be whether it can develop into a financially viable series. Advertising drives most motorsports, but here there is the added benefit of developing algorithms and technologies that manufacturers could reasonably apply to their cars.

ATRC’s Al Bannai told me that while the series organizers own the cars, the teams own the code and are free to license it: “What they’re competing with at the moment is the algorithm, the AI ​​algorithm, who makes this car do what it does.” That belongs to each of the teams. It doesn’t belong to us.

So the real racing may not be on the race track, but in securing partnerships with manufacturers. After all, what better way to inspire confidence in your autonomous technology than by showing it can handle 160 mph track traffic?