Toyota Research Institute tests cars to drift autonomously pushes vehicles’ advanced safety capabilities.
LOS ALTOS, Calif., Feb. 2, 2022 – Toyota Research Institute (TRI) highlighted a new research milestone in autonomy today, offering a glimpse into the future of safer mobility for everyone.
As revealed in this video, In a world first, TRI researchers programmed a car to autonomously drift around obstacles on a closed track. TRI’s Nonlinear Model Predictive Control (NMPC) technique expands the vehicle’s operational domain to the very boundaries of its performance by combining a thorough understanding of both vehicle dynamics and control architecture. The goal of this study is to use controlled, autonomous drifting to avoid accidents by navigating unexpected barriers or dangerous 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.”
Every year, car crashes result in nearly 40,000 fatalities in the United States and about 1.35 million fatalities worldwide. While most crashes occur in mundane situations, in some extreme situations, drivers may need to make maneuvers that take their vehicle close to and, at times, beyond normal limits of handling.
TRI and Stanford University’s Dynamic Design Lab set out a year ago to create a new level of active safety to assist avert crashes and preventing injuries and fatalities. Today’s accomplishment is another step in that quest, thanks to the help of automotive performance specialist GReddy and drift icon Ken Gushi. This technology can enhance and augment a typical driver’s ability to adapt to dangerous and extreme situations by developing skills equivalent to those of an experienced driver, helping to 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,” said Jonathan Goh, TRI research scientist. “That’s why TRI is programming vehicles that can identify obstacles and autonomously drift around obstacles on a closed track.”
This accomplishment takes TRI researchers closer to a complete understanding of vehicle performance. The software advancements presented today to calculate a whole new trajectory every 20th of a second to keep the car balanced while it circles the circuit smoothly.
Toyota will continue to push the limits of vehicle safety technology by researching ever more effective ways for emerging safety technologies to amplify human capabilities on the road, it said in a press release.
Technical Details
- This technology uses Nonlinear Model Predictive Control (NMPC).
- Combining the vehicle dynamics and control design insights from drifting-specific approaches with the generalized framework of NMPC yields a control scheme that extends the vehicle’s operational domain beyond the point of tire saturation. This allows the vehicle to drive beyond the notions of traditional open loop stability to where the vehicle is skidding but still controllable due to closed loop driving control.
- Recently, Toyota Research Institute has developed a step toward such a unified approach and experimentally demonstrated an NMPC controller that can smoothly transition from dynamic, non-equilibrium drifting to grip driving, while accounting for multiple objectives including road bounds.
- This approach was tested on a Toyota Supra that has been specially customized for autonomous driving research. It is equipped with 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 250Hz, and the NMPC controller runs on an x86 computer.
- For the purposes of data collection with expert drivers in a controlled environment, the suspension, engine, transmission, chassis and safety systems (e.g., roll cage, fire suppression) have been modified to be similar to that used in Formula Drift competitions.
- Experiments were conducted at Thunderhill Raceway, on the 2-mile ‘West’ track.
Toyota Research Institute (TRI) conducts research to advance robotics, energy and materials, machine learning, and human-centric artificial intelligence. Led by Dr. Gill Pratt, TRI’s team of researchers are developing technologies to amplify human ability, focused on making our lives safer and more sustainable. Established in 2015, TRI has offices in Los Altos, California; Cambridge, Massachusetts; and Ann Arbor, Michigan. For more information about TRI, please visit http://tri.global.
SOURCE Toyota Research Institute