First autonomous car race: Like Formula 1, only without a driver

business Indy Autonomous Challenge

Like Formula 1, only without a driver – this is how the world’s first autonomous race went

The fastest algorithm comes from Milan and Alabama

In the race against the clock in October 2021, the German team TUM from the Technical University of Munich had the lead. This time the Bolide of the Italian-American team Polimove was the fastest.

There has never been anything like it: near the city of Las Vegas, Formula 1 racing cars raced over a racetrack at 270 km / h – controlled by clever algorithms. In the final, a German team competed against an Italian-American team.

UAt 3:46 p.m., the engineers of the Italian-American team Polimove wrote history in the desert of the US state of Nevada: At that moment, their bolide started to overtake at the Las Vegas Motor Speedway and passed its opponent, the white and blue car of the Teams TUM from Munich. With this, Polimove won the Indy Autonomous Challenge, or IAC for short, on Friday – the first race in the world in which only autonomous cars competed.

Nine teams, all from universities, competed against each other on the oval 30 kilometers northeast of the famous Las Vegas Strip. Their cars did not drive in a field, as we know it from Formula 1, that would be too difficult for the algorithms. Instead, they fought duels. The robot cars fought one on one – like Polimove and TUM, which were in the final of the competition.

The Polimove bolide pulls past the car of the German team TUM from Munich (front)

The Polimove bolide pulls past the car of the German team TUM from Munich (front)

There was everything that one is used to from racing: spins, crashes, engine damage. The vehicles look confusingly similar to Formula 1 cars and also have roaring engines. Nevertheless, it seemed strange how the cars without a pilot – without helmets protruding from the cockpits – raced over the track at 270 kilometers per hour. So much power in the hands of an artificial intelligence, it seemed almost threatening.

It all depends on the algorithms

The race took place on the fringes of CES, the largest tech trade show in the world. All teams drove the same model: the AV-21 from the Italian manufacturer Dallara. The engine of the bolide is old school, it is a four-cylinder. But the cockpit is crammed with modern autonomous technology.

also read

E-car Mercedes December 7th, 2021.  Game changer or disappointment - the Mercedes EQS in the test Summary: With the EQS, the electrified S-Class, Mercedes has made an enormous promise of charging and, above all, range.  The luxury-class Limousibe is supposed to travel as much as 700 kilometers.  Can it really be?  If so, then Mercedes has achieved a kind of electric revolution.  WELT-AM-SONNTAG has tested the car in everyday life and knows the answer. Department: Economy

Where the driver sits in Formula 1, there are radar, lidar (laser radar), cameras and a computer brain at the IAC. The focus is on this technology, the other factors such as aerodynamics and tires are identical for all vehicles. It all depends on who has the smartest, fastest algorithms.

“Autonomous driving is difficult even at low speeds,” said Florian Sauerbeck from the TUM team, which consists of doctoral students from the Technical University of Munich, before the competition in the pit lane. Because artificial intelligence has to coordinate a great many different sensors. “And on a racetrack, at 270 km / h,” explained Sauerbeck, “the challenge is infinitely greater.” The slightest overcorrection or the slightest brake could lead to disaster.

“Easily cope with normal traffic”

Determining your position using GPS is particularly tricky at such high speeds. And something else made life difficult for the IAC teams in Nevada: The curves of the Las Vegas Motor Speedway are inclined by 20 degrees. This can confuse the vehicles’ cameras and algorithms. “But that’s exactly what we want critical situations,” said Sauerbeck. “The idea is: if our car masters the exceptions, it will easily cope with normal traffic.”

At the time trial in Indianapolis, their artificial intelligence was still ahead: the German team TUM and their car

At the time trial in Indianapolis, their artificial intelligence was still ahead: the German team TUM and their car

According to Paul Mitchell, the competition’s chief organizer, that’s the goal. “Our aim is not to establish a new racing series,” he explained, “but to accelerate the development of autonomous vehicles.” Many innovations in the car industry have their origins in racing. “I hope,” said Mitchell, “that this event will bring us a little closer to the robotic car for everyone.”

The nine teams had already started on a track in the city of Indianapolis in October. However, it was not a head-to-head race, like now in Las Vegas, but a time trial. So the autonomous cars were only fighting against the clock. Winner back then: the team from Munich.

Here you can listen to our WELT podcasts

We use the player from the provider Podigee for our WELT podcasts. We need your consent so that you can see the podcast player and interact with or display content from Podigee and other social networks.

“Everything on stocks” is the daily stock market shot from the WELT business editorial team. Every morning from 7 a.m. with the financial journalists from WELT. For stock market experts and newcomers. Subscribe to the podcast at Spotify, Apple Podcast, Amazon Music and Deezer. Or directly via RSS-Feed.

.

Leave a Comment

This site uses Akismet to reduce spam. Learn how your comment data is processed.