United States. The Instituto de Investigación de Toyota (TRI) and Stanford Engineering have announced a groundbreaking milestone in automotive research: the world's first fully autonomous tandem drift sequence.
Over seven years of intensive collaboration, the teams have used artificial intelligence to master a high-risk motorsports technique , known as skidding, where two automated vehicles precisely monitor the loss of traction of their rear tires. This advancement not only simulates extreme driving conditions, such as snow or ice, but also sets new standards in automotive safety.
"Our researchers came together with one goal in mind: how to make driving safer," said Avinash Balachandran, vice president of TRI's Human Interactive Driving division.
The project, carried out at Thunderhill Raceway Park, California, used two Toyota GR Supras modified with systems developed by TRI and Stanford. Equipped with predictive control algorithms and neural networks for continuous learning, these vehicles are designed to adapt and respond in real-time to changing conditions.
"The physics of the skid are actually similar to what a car might experience on snow or ice," said Chris Gerdes, a professor of mechanical engineering and co-director of the Stanford Center for Automotive Research (CARS). "What we have learned from this autonomous drifting project has already led to new techniques for controlling automated vehicles safely on ice."
With more than one billion deaths annually worldwide due to road accidents, this breakthrough offers tangible promise to drastically reduce the risks associated with loss of vehicle control.
This achievement not only highlights the potential of AI to revolutionize road safety, but also positions Toyota and Stanford at the forefront of global automotive innovation.
