Roborace completes first fully autonomous racecar hill climb
Autonomous Vehicle Technology announces 2019 ACES Award Winner in Autonomy | Motorsports
Roborace completed the first official autonomous hill climb at Goodwood by a racecar. The Robocar successfully navigated the 1.16-mi (1.8-km) course using artificial intelligence (AI). The run, reportedly the first ever to take place at Goodwood Festival of Speed by a vehicle without a human driver, is an impressive achievement for a racecar to complete its very first run of the hill using only artificial intelligence.
The car uses a variety of sensors to give it 360-degree vision of its environment and the ability to localize its position on the hill and detect drivable surfaces and objects using deep neural networks. Roborace also gave event attendees a chance to experience the run from the perspective of the car in a fully immersive VR simulator in Goodwood’s Future Lab, in conjunction with HTC VIVE and D-BOX. Robocar was designed by Daniel Simon, the automotive futurist known for his work in films such as Oblivion and Tron: Legacy . It weighs 1350 kg (2976 lb) and is powered by four 135-kW electric motors used to drive each wheel.
An Nvidia Drive PX2 computer processes the car’s data, which include inputs from the LiDAR, radar, GPS, ultrasonic, and camera sensors. Roborace provides the car with an application programming interface as a platform for teams who then add their AI driver algorithm to the vehicle. Development of the automated driving system for the Robocar at Goodwood was led by Arrival.
Click to view AVT’s 2019 ACES Award Winners best in class of