When a car drifts sideways, it looks dramatic but in reality, the car is actually ‘out of control’ as its tyres have lost their grip, just like skidding. However, skilled drivers can control the drift through steering control and application of power, avoiding going off the road or track.
Drifting is useful for researchers developing autonomous vehicles as the action of the car sliding sideways provides a scenario for which they need to ‘teach’ the computers to handle. As autonomous vehicle control systems need to be programmed for all sorts of situations, drifting is one more simulated dynamic condition to learn.
Two years ago, researchers at the Toyota Research Institute (TRI) in America were able to successfully get a Supra – with no driver at the wheel – to drift around a closed circuit. By programming skills comparable to an expert driver, the autonomous system can more effectively respond to dangerous and extreme situations, helping keep people safe on the road.
Now they have gone further by adding a second car drifting in tandem, simulating situations where cars must respond quickly to other vehicles, pedestrians, and cyclists. Even if the vehicle is being driven by a human, the more intelligent programming will allow better responses with the Advanced Drive Assistance Systems (ADAS).
“Utilizing the latest tools in AI, we can drift two cars in tandem autonomously. It is the most complex manoeuvre 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,” said Avinash Balachandran, Vice-President of TRI’s Human Interactive Driving division.
In an autonomous tandem drifting sequence, two vehicles—a lead car and a chase car—navigate a course at times within centimetres 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 tyre model that allowed it to learn from experience, much like an expert driver.
“The physics of drifting are actually similar to what a car might experience on snow or ice,” explained Chris Gerdes, professor of Mechanical Engineering and Co-director of the Centre for Automotive Research at Stanford. “What we have learned from this autonomous drifting project has already led to new techniques for controlling automated vehicles safely on ice.”
“The track conditions can change dramatically over a few minutes when the sun goes down,” added Gerdes. “The AI we developed for this project learns from every trip we have taken to the track to handle the variations.”
Car crashes result in more than 40,000 fatalities in America and about 1.35 million fatalities worldwide every year. Many of these incidents are due to a loss of vehicle control in sudden, dynamic situations. Autonomy holds tremendous promise for assisting drivers to react correctly.
“When your car begins to skid or slide, you rely solely on your driving skills to avoid colliding with another vehicle, tree, or obstacle. An average driver struggles to manage these extreme circumstances, and a split second can mean the difference between life and death,” said Balachandran. “This new technology can kick in precisely in time to safeguard a driver and manage a loss of control, just as an expert drifter would.”