Advancing AI in Auto Racing for Safer Driverless Cars on the Road

The thrill of auto racing arises from split-second choices and bold passes by fearless drivers. Picture that sight, but minus the driver – the car alone, guided by the unseen hand of artificial intelligence. Can the excitement of racing unfold without a driver at the helm? It appears that it can.

Introducing self-governing racing, a domain that isn’t just about high-speed competition but also about pushing the limits of what autonomous vehicles can accomplish and enhancing their safety.

Over a century ago, at the emergence of automobiles, as society transitioned from horse-drawn to motorized vehicles, there was public uncertainty about the safety and reliability of the new technology. Motorsport racing was organized to exhibit the technological performance and safety of these horseless carriages. Similarly, self-governing racing is the modern arena to establish the dependability of autonomous vehicle technology as driverless cars begin to hit the streets.

The high-speed trials of self-governing racing mirror the real-world challenges that autonomous vehicles encounter on streets: adapting to unforeseen changes and responding in split seconds. Mastering these challenges on the track, where speeds are higher and reaction times are shorter, leads to safer autonomous vehicles on the road.

Autonomous race cars overtake others on the Las Vegas Motor Speedway track.

I am a professor of computer science who studies artificial intelligence, robotics and autonomous vehicles, and I lead the Cavalier Autonomous Racing team at the University of Virginia. The team competes in the Indy Autonomous Challenge, a global contest where universities pit fully autonomous Indy race cars against each other. Since its 2021 inception, the event has drawn top international teams to prestigious circuits like the Indianapolis Motor Speedway. The field, marked by both rivalry and teamwork, shows that collective problem-solving drives advances in autonomous vehicle safety.

At the Indy Autonomous Challenge overtaking competition held at the 2024 Consumer Electronics Show in Las Vegas in January 2024, our Cavalier team secured second place and reached speeds of 143 mph (230 kilometers per hour) while autonomously passing another race car, affirming its status as a leading American team. TUM Autonomous Motorsport from the Technical University of Munich won the event.

Modest beginnings

The realm of self-governing racing didn’t commence with race cars on professional race tracks but with miniature cars at robotics conferences. In 2015, my colleagues and I engineered a 1/10 scale self-governing race car. We transformed a remote-controlled car into a small but potent research and educational tool, which I christened F1tenth, a play on the name of the traditional Formula One, or F1, race car. The F1tenth platform is now utilized by over 70 institutions worldwide to construct their miniaturized autonomous racers.

The F1tenth Autonomous Racing Grand Prix is now a significant event at robotics conferences where teams from across the globe congregate, each wielding vehicles that are identical in hardware and sensors, to engage in what is essentially an intense “battle of algorithms.” Victory on the track is clinched not by raw power but by the sophisticated AI algorithms’ command of the cars.

These race cars are diminutive, but the obstacles to autonomous driving are substantial.

F1tenth has also emerged as an appealing and accessible gateway for students to delve into robotics research. Over the years, I’ve reached thousands of students via my courses and online lecture series, which expounds on the process of how to build, drive and autonomously race these vehicles.

Becoming real

Today, the scope of our research has expanded significantly, advancing from small-scale models to actual autonomous Indy cars that compete at speeds of upward of 150 mph (241 kph), executing complex passing maneuvers with other autonomous vehicles on the racetrack. The cars are constructed on a modified version of the Indy NXT chassis and are equipped with sensors and controllers to enable autonomous driving. Indy NXT race cars are used in professional racing and are slightly smaller versions of the Indy cars made famous by the Indianapolis 500.

13 people stand beside a race car in a large empty racing stadium
The Cavalier Autonomous Racing team stands behind their driverless race car.
Cavalier Autonomous Racing, University of Virginia, CC BY-ND

The rigorous reality of racing these advanced machines on actual racetracks pushes the limits of what autonomous vehicles can accomplish. Autonomous racing takes the challenges of robotics and AI to new levels, necessitating researchers to refine our understanding of how machines perceive their environment, make safe decisions and control complex maneuvers at high speeds where traditional methods begin to waver.

Precision is crucial, and the margin for error in steering and acceleration is extremely small, requiring a sophisticated grasp and precise mathematical depiction of the car’s movement, aerodynamics and drivetrain system. Additionally, autonomous racing researchers develop algorithms that utilize data from cameras, radar and lidar, which is similar to radar but with lasers instead of radio waves, to maneuver around competitors and safely navigate the high-speed and unpredictable racing environment.

My team has published the world’s first open dataset for autonomous racing, inviting researchers everywhere to participate in refining the algorithms that could help shape the future of autonomous vehicles.

The data from the competitions is available for other researchers to use.

Crucible for autonomous vehicles

More than just a technological exhibition, autonomous racing is a crucial research frontier. When autonomous systems can function reliably in these extreme conditions, they inherently possess a buffer when operating in the ordinary conditions of street traffic.

Autonomous racing is a testing ground where competition drives innovation, collaboration fosters development, and AI-controlled cars racing to the finish line set a course toward safer autonomous vehicles.

Leave a Reply

Your email address will not be published. Required fields are marked *