February 2, 2022
The Toyota Research Institute (TRI) has announced a new research milestone in autonomy, which the company said provides a glimpse into the future of safer mobility for everyone.
In a demonstration, TRI researchers successfully programmed a vehicle to autonomously drift around obstacles on a closed track. By combining a deep knowledge of vehicle dynamics and control design, TRI’s Nonlinear Model Predictive Control (NMPC) approach extends the vehicle’s operational domain to the limits of its performance. The idea behind the research, TRI said, is to utilize controlled, autonomous drifting to avoid accidents by navigating sudden obstacles or hazardous road conditions like black ice.
“At TRI, our goal is to use advanced technologies that augment and amplify humans, not replace them,” said Avinash Balachandran, senior manager of TRI’s Human Centric Driving Research. “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.”
Toyota cited statistics about car crashes that result in almost 40,000 fatalities per year in the U.S., and about 1.35 million worldwide. While most crashes happen in mundane situations, TRI said in some extreme situations, “drivers may need to make maneuvers that take their vehicle close to and, at times, beyond normal limits of handling.”
To address this, TRI and the Dynamic Design Lab at Stanford University aimed to design a new level of active safety to help avoid crashes and prevent injuries and fatalities. With the support of GReddy and drift legend Ken Ghusi, the technology built skills comparable to an expert driver to amplify and augment a regular driver’s ability to respond to dangerous and extreme situations.
The approach was tested on a Toyota Supra that was specially customized for autonomous driving research. The vehicle includes computer-controlled steering, throttle, clutch displacement, sequential transmission and individual wheel braking. 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. For the purposes of data collection, the suspension, engine, transmission, chassis and safety systems (roll cage, fire suppression), was modified to be similar to Formula Drift competitions.
“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,” said Jonathan Goh, a TRI research scientist. “That’s why TRI is programming vehicles that can identify obstacles and autonomously drift around obstacles on a closed track.”
TRI said the achievement brings researchers closer to understanding the full spectrum of vehicle performance. The software calculates a whole new trajectory every 20th of a second to balance the car as it goes around the track, TRI said.
Toyota said it will “continue to push the limits of vehicle safety technology” by researching additional effective ways for emerging safety technologies to help amplify human capabilities on the road.