Racing robot aims to accelerate autonomous technology – The Irish Times

The tarmac road that winds in front of and past the stately Goodwood House is deceptively tricky. The great and good of motor racing gather here every summer for the Goodwood Festival of Speed, and the competitive element of the weekend is finding the fastest driver and car combination to cover the 1.8-mile course. Cars old and new, drivers young and experienced. Racing royalty versus novices, classic sports cars versus crazy new supercars, and everything in between.

Tricky? Oh yes. It may be just a hill 362 days a year, but over the three days of the festival it’s as tough a racetrack as you’d imagine. The track is narrow and often slippery, especially under the overhanging trees. There’s the dangerous Flint Wall, which the fastest drivers will miss by millimetres, and the unassuming-looking Molecomb, whose banked turns have caused some of the best and most famous racing drivers trouble amidst the hay bales. It’s no walk in the park.

That’s why the Indy Autonomous Challenge, backed by tyre giant Bridgestone, has brought its robot race car to the 2024 Festival of Speed. If the Goodwood hill climb is difficult and deceptive for the world’s most experienced racing drivers, how difficult would it be for a robot car that sees its world through a combination of Light Detection and Ranging (Lidar) scanners and cameras?

How would an autonomous car be perceived at an event packed with traditionalists that included the likes of Mika Hakkinen, Max Verstappen and NASCAR legend Richard The King Petty?

The Indy Autonomous Challenge (IAC) is, as its name suggests, a competition to build the fastest, most capable autonomous race car possible, based on a Dallara chassis and Honda engine from the Indy Lights car – a preparation program for the famous Indycar racing series, the centerpiece of which is the epic Indianapolis 500.

Each car is managed by a university or group of universities. The car is equipped with state-of-the-art sensors and software to support autonomous driving.

Racing traditionalists can give up now — the idea behind IAC isn’t to create a robot race driver to replace humans, but simply to use the white-hot cauldron of motorsport to accelerate the development of autonomous driving technology on the road.

“We saw a gap in the autonomous and self-driving markets, particularly in relation to testing and developing high-speed autonomy,” Marc Ferlet, IAC’s chief marketing officer, told The Irish Times. “We saw that the large companies in the ecosystem, most of which are based on the west coast of America, were focused on urban and suburban robo-taxi applications.”

IAC got the idea that humans can usually drive easily at 30 mph on city streets, but driving at very high speeds—highway style—is much more difficult and requires much greater skill. IAC’s idea is that it’s better to get a robot to do something humans aren’t very good at than something we do mostly well. Similarly, it’s much easier to teach a robot to drive on a large, multi-lane road—or a racetrack—than on a crowded, chaotic city street.

There’s an old and generally correct saying that racing improves the breed, and that definitely applies to cars. According to Ferlet, the IAC isn’t trying to make the breed improve racing. “We never set out to create an autonomous racing series,” Ferlet said. “The original plan was that the race we had between cars in October 2021 was going to be a ‘one-off’ event. But then we got involved with companies and universities coming to us, ‘wow, this is the best platform, can I use it to test these different propositions or research goals,’ and so on.”

Still, Ferlet smiled when I told him that bringing the car to Goodwood was a move designed to pit the AI ​​against a human rally driver — or rather, the greatest human rally drivers of all time.

“That’s not the goal,” Ferlet insists. “It wasn’t to say we’re going to replace race drivers. Nobody wants that. But maybe it’s interesting to see that this car can be driven autonomously, safely, at very high speeds. So we bring the car to Goodwood, we bring the car to the Indianapolis Motor Speedway, and then people can see them being driven safely by software at very high speeds, 170 mph, and not crashing. So then the prospect of a computer driving at 80 mph on the freeway becomes much more acceptable.”

But there’s more to the trip to Goodwood than just showing off. The route, as mentioned, is tough, and the grounds are notoriously poor for mobile phone and GPS reception, so the IAC car’s software has had to rely much more on cameras, on-board sensors and, especially, Lidar.

The IAC car, supplied by Luminar, has four Lidar sensors, one for each corner, which is about twice the number of sensors used in road cars. Ferlet noted that the car’s software chose to rely primarily on Lidar rather than cameras as it learned the Goodwood approach, ultimately setting the fastest time of 66.96 seconds, with a top speed of 162.8 km/h. By comparison, the fastest time of the weekend was set by racing driver Romain Dumas, in a stunning 2000bhp electric Ford Supervan. Dumas and the Supervan completed the climb in just 43.98 seconds. It’s clear that the AI ​​has a long way to go before it’s as fast as Dumas.

But again, that’s not the point. Tyres were a big part of the Goodwood drive for the IAC team. IAC is heavily backed by Bridgestone, and the cars were tested at Bridgestone’s extensive proving ground near Rome. It wasn’t the first time Goodwood had provided a severe test of variable grip uphill (not least because it rained for most of Saturday). Human drivers, good ones at least, have a sixth sense for how much grip the tyres are actually providing, but the computer can’t. What’s more, the IAC car had to be running on cold tyres because the AI ​​currently can’t be set up to do a smoky start-line burnout to warm up those tyres.

“Grip, when you’re a racing driver, you just understand it. With an autonomous vehicle, it’s much more complicated. You have to fully model the performance of the tires and understand how the track works,” Ferlet said.

This is the kind of engineering expertise that could be key to future robotic cars, and it’s a key reason Bridgestone is supporting IAC. “Motorsports are part of Bridgestone’s DNA, always have been and always will be. And what really matters is that we learn from these experiences and apply them to the sustainable mobility solutions we develop for society and our customers,” said Sara Correa, chief marketing officer at Bridgestone.

Despite all the protestations about not wanting to create a robot racing series and that IAC is just a rolling laboratory for self-driving technology — which is true, to be fair — Ferlet admitted that the software can be programmed to be more or less “aggressive” in the way it drives. “You have to set thresholds for the car and tell it if something’s going to happen, if it’s going to stop or not. When you have multi-car events, the teams have to decide at what point the car is going to give way and at what point it’s not. Some teams are going to be more aggressive than others, and I think it’s fair to say that the personality of the teams, and maybe even the nationality of the teams, shines through that. And I’ll tell you, their egos aren’t one inch smaller than the egos of the best racing drivers.”

Suddenly the idea of ​​a robot racing series doesn’t seem so bad. Program one car to drive like Alain Prost, one to drive like Ayrton Senna, and one to drive like Nigel Mansell and let’s recreate the 80s.