How will robots change the world? A frequently asked and as yet unanswered question. After all, we do not have a crystal ball. What we do know is that digitalization and automation have changed the world enormously in recent decades. At Eindhoven University of Technology (TU/e) in the Netherlands, the potential of smart machines in industry and daily life is being researched each and every day. Scientists immerse themselves in technology and student teams get to work on concrete solutions to social problems. This series will tell you about the latest robots, their background, and their future. Today, the third article in this series is all about autonomous racing cars.
The Transformer, that’s the name of the University Racing Eindhoven (URE) student team’s latest car. As the name suggests, the car can also change shape. The electric racing car from the University Racing Eindhoven (URE) is capable of driving with or without a driver. “The front and rear side wings of the car can be replaced by a number of sensors and an extra computer which allows the car to drive autonomously,” says Dennis Gubbels, URE team leader. The student team is competing in the international Formula Student competition with their racing car. There are three different classes: For internal combustion engines, electric drives and autonomous driving. The Eindhoven team is taking part in the competitions for electric and autonomous racing cars.
Brain versus system
The autonomous race is run slightly different to what motor racing is used to. “The autonomous cars are not all racing on the track at the same time. They drive around the track one by one. In the end, the lap times are compared and a winner emerges,” clarifies Gubbels. The students try to drive the car around the track as optimally as possible. Just like a driver, the car searches for the ideal line to complete a lap as quickly as possible.
“Lidar sensors and front-facing cameras work in tandem to determine the distance to the pylons along the road. This enables the car to make a map of the surroundings and calculate the optimal driving route,” the team leader explains.
In order to be able to make these calculations, the car has an extra computer at the back of the car. “This is where all the data from the sensors and cameras are received. The computer processes that data and then sends signals to set the speed and steering. That’s what normally happens in a driver’s brain,” he adds. “The goal is to make this system better than a regular racing driver. The team has incorporated a number of safety systems to keep it safe. “We have an emergency brake system. This ensures that the car brakes automatically if, for example, there’s an error or if the power fails,” Gubbels continues. “In addition, we can always brake remotely if we see that the car can’t handle it.”
The upcoming months will be all about testing for the students. “Due to the corona crisis, we have been on hold for a while this past academic year. This meant that the car is not completely finished yet,” Gubbels states. The team normally makes a new car each academic year. Things will be different this year. “We are now continuing on with last year’s car. That also has its advantages. Now we can thoroughly test and optimize it, both mechanically and in terms of software.”
The team is preparing for next year as well. “The competition is going to change. Next year, there will be a class where the car has to be able to drive with a driver one moment and autonomously the next,” he notes. “Then we need to integrate the autonomous systems into the car even more effectively.” At the moment, the students still have to slightly adjust their car in order to make the switch to autonomous driving. “If everything really is part of one car, this affects almost all other aspects of the car. With extra sensors and computers, we need to think carefully about how it will all fit neatly inside the car. We also need to explore the influence of all the sensors on aerodynamics,” Gubbels says.
From the racetrack to the open road
Autonomous driving is becoming more prevalent in the world of racing. “I expect that in a few years’ time, in addition to Formula 1 and Formula E, there will also be a major competition for autonomous racing,” says Gubbels. “Perhaps initially on a smaller scale or even digitally – based on simulations – and later on with actual cars.” The technological development that is taking place in the racing world can also be useful outside the racetrack. “Our car’s sensors detect pylons, but they can also detect people, cyclists, zebra crossings or road signs. In both scenarios, a computer must then be able to calculate an optimal route without hitting anything else.”
Although there are other things on public roads that need to be taken into account, according to the student. ” Lots of people walk and cycle in the vicinity of public roads. Of course, that’s not the case on the racetrack,” Gubbels adds. “The car needs to be able to see which way someone is walking, cycling or driving. Then it has to calculate how long it takes before somebody is near the car. On that basis, the car can then assess whether it can keep on going or should stop.”
“Systems will therefore be designed for self-driving passenger cars so that they can communicate with each other,” he goes on to say. “This will increase safety levels because cars will subsequently know what the other cars are going to do. In a race, you don’t want to let your opponent know what you’re about to do, that’s how you can defend your position or come up with a plan to overtake another car.”
Gubbels thinks that autonomous cars are safer than human drivers. “A person can only look ahead, or left or right, while a computer system can do it all at the same time,” he says. ” Moreover, people sometimes act emotionally, even in traffic. A system doesn’t do that and therefore always makes well-informed decisions.”