Tokyo Drift 2.0: AI masters art of drifting two GR Supra in tandem

Drifting is a high-octane ballet of man and machine. Competitors engage in a thrilling duel, where driver skill and vehicular prowess are tested to the limit in a head-to-head battle for supremacy.

The bond between driver and machine in drifting is a unique and intense partnership. However, AI has now emerged to help drifting bros in a much safer ‘man vs. man, machine vs. machine’ competition.

For the first time globally, Toyota Research Institute (TRI) and Stanford Engineering have autonomously drifting two GR Supra in tandem.

Toyota said that this AI-powered research aims to improve driving safety.

The experiment

For nearly seven years, the teams at TRI and Stanford have collaborated on research to make driving safer.

The experiments automate a motorsports maneuver called “drifting,” in which a driver precisely controls a vehicle’s direction after breaking traction by spinning the rear tires—a skill that can be transferred to recovering from a slide on snow or ice.

By adding a second car drifting in tandem, the teams have more closely simulated dynamic conditions in which cars must respond quickly to other vehicles, pedestrians, and cyclists.

“Our researchers came together with one goal in mind – how to make driving safer,” Avinash Balachandran, vice president of TRI’s Human Interactive Driving division, said.

“Now, utilizing the latest tools in AI, we can drift two cars in tandem autonomously. It is the most complex maneuver in motorsports, and reaching this milestone with autonomy means we can control cars dynamically at the extremes. This has far-reaching implications for building advanced safety systems into future automobiles.”

“The physics of drifting are actually similar to what a car might experience on snow or ice,” Chris Gerdes, professor of mechanical engineering and co-director of the Center for Automotive Research at Stanford (CARS), said.

“What we have learned from this autonomous drifting project has already led to new techniques for controlling automated vehicles safely on ice.”

In an autonomous tandem drifting sequence, two vehicles—a lead car and a chase car—navigate a course at times within inches of each other while operating at the edge of control.

The team used modern techniques to build the vehicle’s AI , including a neural network tire model that allowed it to learn from experience, much like an expert driver.

“The track conditions can change dramatically over a few minutes when the sun goes down,” said Gerdes. “The AI we developed for this project learns from every trip we have taken to the track to handle this variation.”

The tech

The experiments were conducted at Thunderhill Raceway Park in Willows, California, using two modified GR Supras. The algorithms on the lead car were developed at TRI, while Stanford engineers developed those on the chase car.

TRI focused on developing robust and stable control mechanisms for the lead car, allowing it to make repeatable, safe lead runs.

Stanford Engineering developed AI vehicle models and algorithms that enable the chase car to adapt dynamically to the motion of the lead car so that it can drift alongside without colliding.

GReddy and Toyota Racing Development (TRD) modified each car’s suspension, engine, transmission, and safety systems (e.g., roll cage, fire suppression).

Though subtly different from each other, the vehicles were built to the same specifications used in Formula Drift competitions, helping the teams collect data with expert drivers in a controlled environment.

Both are equipped with computers and sensors that allow them to control their steering, throttle, and brakes while also sensing their motion (e.g., position, velocity, and rotation rate).

Crucially, they share a dedicated WiFi network that allows them to communicate in real time and exchange information, such as their relative positions and planned trajectories.

To achieve autonomous tandem drifting, vehicles must continually plan their steering, throttle, and brake commands and the trajectory they intend to follow using a Nonlinear Model Predictive Control (NMPC) technique.

In NMPC, each vehicle starts with objectives, represented mathematically as rules or constraints that it must obey.

The lead vehicle’s objective is to sustain a drift along a desired path while remaining subject to the constraints of the laws of physics and hardware limits like maximum steering angle.

The chase vehicle aims to drift alongside the lead vehicle while proactively avoiding collisions.

Each vehicle then solves an optimization problem up to 50 times per second to decide what steering, throttle, and brake commands best meet its objectives while responding to rapidly changing conditions.

By constantly leveraging AI to train the neural network using data from previous tests, the vehicles improve from every trip to the track.