TRI and Stanford working to combine vehicle automation with AI algorithms inspired by professional drift drivers
Researchers at Toyota Research Institute (TRI) are conducting research with Stanford’s Dynamic Design Lab into how to bring together the instincts of professional drift drivers and automated driving technology. Thee goal is to design a new level of active safety technology and share it broadly so that Toyota and other auto manufacturers can deploy it on the road.
Every day, there are deadly vehicle crashes that result from extreme situations where most drivers would need superhuman skills to avoid a collision. 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. This is the essence of the Toyota Guardian approach.—Gill Pratt, TRI CEO and Chief Scientist at Toyota Motor Corporation (TMC)
Every year, car crashes result in nearly 40,000 fatalities in the United States, and about 1.25 million fatalities worldwide. Toyota’s goal is to reduce that number to zero. While most crashes occur in mundane situations, in other situations drivers may need to make maneuvers that take their vehicle close to and, at times, exceed normal limits of handling. When faced with wet or slippery roads for instance, professional drivers may choose to drift the car through a turn.
Since 2008, our lab has taken inspiration from human race car drivers in designing algorithms that enable automated vehicles to handle the most challenging emergencies. Through this research, we have the opportunity to move these ideas much closer to saving lives on the road.—Professor Chris Gerdes of Stanford University’s Dynamic Design Laboratory
TRI has supported the Dynamic Design Lab’s research for many years. The current project draws upon Stanford’s published paper, “Opening New Dimensions: Vehicle Motion Planning and Control using Brakes while Drifting,” in which Stanford researchers demonstrated advanced drifting on MARTY, an electrified, automated DeLorean.
Autonomous vehicles should be able to maintain control in scenarios that push them beyond the limits of handling. In case of unintended rear tire force saturation while driving, the vehicle should be able to decelerate while ensuring the navigation of an obstacle free path. With that objective, this paper presents a novel architecture capable of controlling a rear-wheel drive vehicle in a drift using brakes in addition to steering and throttle. We demonstrate the existence of another dimension of drift equilibria which allow motion planning algorithms to prescribe vehicle states independently even while drifting. A tangent space analysis illustrates the transformation from an under-actuated to a fully-actuated system with the use of front-wheel braking. Minimal modifications to existing state of the art in drifting can exploit the additional actuation to significantly increase the set of feasible actions for the vehicle.—Goel et al.
MARTY, the Dynamic Design Lab’s electric DeLorean, dodges haybales as it autonomously drifts through a long and challenging obstacle course in 2019.
Stanford’s experimental results produced a proof-of-concept architecture capable of controlling a rear-wheel drive vehicle in a drift using brakes, steering and propulsion. TRI is now applying this architecture to vehicle platforms, including the GR Supra.
TRI is also engaging Toyota’s engineering expertise in motorsports and advanced development. Toyota Racing Development (TRD USA, Inc.) in the United States is providing valuable technical and experiential know-how in motorsports and drifting. Separately, TRI is also working with Toyota Motor Corporation’s Vehicle Dynamics Control Team—based in Japan—to apply the drifting architecture for future Toyota vehicles.
T. Goel, J. Y. Goh and J. C. Gerdes, “Opening New Dimensions: Vehicle Motion Planning and Control using Brakes while Drifting,” 2020 IEEE Intelligent Vehicles Symposium (IV), pp. 560-565, doi: 10.1109/IV47402.2020.9304728