Toyota plans to test drifting autonomous vehicle (AV) technology from Stanford’s Dynamic Design Lab in vehicles such as its GR Supra sporty car.
Photo courtesy of Toyota

Jerking the steering wheel sharply to send a car into a controlled skid, also known as drifting, may look cool in movies but it’s not the safest driving maneuver. A controlled skid is still a skid, and drivers have much better control of vehicles when wheels spin in the direction the vehicle is moving.

Researchers from the Toyota Research institute (TRI) and Stanford University’s Dynamic Design Lab, however, think there’s a lot to learn from traction-free, wheel-spinning, drifting cars on racetracks. Researchers say learning how professional drivers push vehicles far past intended use parameters can help in programming autonomous vehicles (AVs) that might have to react to emergency situations.

“We’re trying to develop AVs that can handle emergency maneuvers on slippery surfaces like ice or snow,” says Chris Gerdes, a mechanical engineering professor at Stanford and director of the Center for Automotive Research at Stanford (CARS). “We’d like to develop automated vehicles that can use all of the friction between the tire and the road to get the car out of harm’s way. We want the car to be able to avoid any accident that’s avoidable within the laws of physics.”

Gerdes has been studying drifting for several years and in 2015 worked with students to design Multiple Actuator Research Test bed for Yaw control (MARTY), a self-driving, drifting DeLorean.

TRI has funded some of Stanford’s automotive research and is partnering with the university to learn how to adapt extreme emergency driving maneuvers into future AVs. Automakers liken it to putting an experienced race car driver in charge of a passenger car in case of emergency.

“Every day, there are deadly vehicle crashes that result from extreme situations where most drivers would need superhuman skills to avoid a collision,” Toyota chief scientist and TRI CEO Gill Pratt says. “The reality is that every driver has vulnerabilities, and to avoid a crash, drivers often need to make maneuvers that are beyond their abilities. Through this project, TRI will learn from some of the most skilled drivers in the world to develop sophisticated control algorithms that amplify human driving abilities and keep people safe.”

Gerdes says Stanford researchers have been studying professional driver reflexes and how they control cars for more than a decade. That informed MARTY, the vehicle that proved computers could control a vehicle as it drifted using brakes, steering, and propulsion (MARTY has an electric powertrain).

An early step of the partnership is applying MARTY’s algorithms and architecture to production vehicles such as Toyota’s GR Supra sporty car.

Stanford University Dynamic Design Lab https://dynamicdesignlab.

Toyota Research Institute (TRI)