Toyota is teaching autonomous cars how to drift, hoping razor-sharp skills could help next-gen safety systems prevent fatal accidents.
The manufacturer’s research institute says the premise is simple:
“What if every driver who ran into trouble had the instinctive reflexes of a professional race car driver and the calculated foresight of a supercomputer to avoid a crash?”
Scientists at the Toyota Research Institute and Stanford University’s Dynamic Design Lab are working to teach self-driving cars and driver assistance systems how to handle slippery situations, including circumstances that may require the car to “exceed normal limits of handling” with a delicately balanced slide or “drift”.
Most emergency assistance features in new cars work by detecting a potential hazard and slamming on the brakes. A handful of advanced cars will help you steer around an accident.
Toyota’s research could help cars push through the regular limits of tyres and road surfaces to get out of harm’s way.
Gill Pratt, chief executive of the Toyota Research Institute, says fatal crashes occur in extreme situations every day.
“The reality is that every driver has vulnerabilities, and to avoid a crash, drivers often need to make manoeuvres that are beyond their abilities,” he says.
“Through this project, TRI will learn from some of the most skilled drivers in the world to develop sophisticated control algorithms that amplify human driving abilities and keep people safe.”
The test vehicle is a modified example of Toyota’s Supra sports car.
A powerful six-cylinder engine and rear-wheel-drive layout make the Supra ideal for experimenting with sideways action, something we experienced on a wet skidpan at Sydney Motorsport Park.
Toyota is not the first manufacturer to experiment with self-sliding cars.
But it is the first to claim that teaching autonomous vehicles to slip and slide could have real-world safety implications for future vehicles.