Toyota develops autonomous drifting technology in the name of safety – demonstrated with a GR Supra

Researchers at the Toyota Research Institute (TRI) have successfully programmed a GR Supra to autonomously drift around obstacles at the Thunderhill Raceway – a world first – all in the interest of making mobility safer in the future.

According to the institute, the idea behind this research is to utilise controlled, autonomous drifting to avoid accidents by navigating sudden obstacles or hazardous road conditions like black ice. This uses TRI’s Nonlinear Model Predictive Control (NMPC) approach that extends the vehicle’s operational domain to the very limits of its performance.

“At TRI, our goal is to use advanced technologies that augment and amplify humans, not replace them. Through this project, we are expanding the region in which a car is controllable, with the goal of giving regular drivers the instinctual reflexes of a professional race car driver to be able to handle the most challenging emergencies and keep people safer on the road,” commented Avinash Balachandran, senior manager of TRI’s Human Centric Driving Research.

In the United States, car crashes result in nearly 40,000 fatalities yearly, with about 1.35 million fatalities recorded worldwide. While most crashes happen in mundane situations, in some extreme situations, drivers may need to make advanced manoeuvres that take their vehicle close to and, at times, beyond normal limits of handling.

With that in mind, TRI and the Dynamic Design Lab at Stanford University paired up to design a new level of active safety to help avoid crashes, bringing in the support of GReddy and drift star Ken Gushi. By building skills comparable to an expert driver, the technology developed can amplify and augment a regular driver’s ability to respond to dangerous and extreme situations, helping keep people safe on the road.

“When faced with wet or slippery roads, professional drivers may choose to drift the car through a turn, but most of us are not professional drivers. That’s why TRI is programming vehicles that can identify obstacles and autonomously drift around obstacles on a closed track,” said Jonathan Goh, TRI research scientist.

The GR Supra used was specially customised for autonomous driving research and is equipped with computer-controlled steering, throttle, clutch displacement, sequential transmission and individual wheel braking. Additionally, vehicle state information is obtained from a dual-antenna RTK-GNSS-aided INS system at a rate of 250 Hz, and the NMPC controller runs on an x86 computer.

Other modifications involve the car’s suspension, engine, transmission, chassis and safety systems, which were made to be similar to those used in Formula Drift for the purposes of data collection with expert drivers in a controlled environment.

Looking to sell your car? Sell it with Carro.