AI-Driven Innovation Aims to Enhance Driving Safety
In a groundbreaking development, Toyota Research Institute (TRI) and Stanford Engineering have successfully achieved the world’s first fully autonomous tandem drift sequence, marking a significant milestone in driving research. This achievement, the result of nearly seven years of collaboration, showcases the ability of two cars to autonomously drift in tandem, a motorsport maneuver that involves precise control of a vehicle’s direction after breaking traction by spinning the rear tires.
“Our researchers came together with one goal in mind – how to make driving safer,” said Avinash Balachandran, vice president of TRI’s Human Interactive Driving division. “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.”
Drifting is not only a popular motorsport technique but also a critical skill for recovering from a slide on snow or ice. The autonomous tandem drift sequence involves a lead car and a chase car navigating a course while operating at the edge of control. The experiment’s success demonstrates how AI can control vehicles dynamically, simulating conditions where quick responses are necessary to avoid collisions with other vehicles, pedestrians, or obstacles.
“The physics of drifting are actually similar to what a car might experience on snow or ice,” said Chris Gerdes, professor of mechanical engineering and co-director of the Center for Automotive Research at Stanford (CARS). “What we have learned from this autonomous drifting project has already led to new techniques for controlling automated vehicles safely on ice.”
The team utilized advanced AI techniques, including a neural network tire model that allows the vehicles to learn from experience, much like an expert driver. This technology enables the vehicles to adapt to changing track conditions and improve from every trip to the track.
Car accidents result in over 40,000 fatalities annually in the US and approximately 1.35 million worldwide. Many of these incidents are due to a loss of vehicle control in sudden, dynamic situations. Autonomy offers significant potential for assisting drivers in reacting correctly in these scenarios.
“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,” added 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.”
Gerdes emphasized the groundbreaking nature of this achievement, stating, “Doing what has never been done before truly shows what is possible. If we can do this, just imagine what we can do to make cars safer.”
Technical Details
The experiments were conducted at Thunderhill Raceway Park in Willows, California, using two modified GR Supras. TRI developed algorithms for the lead car, while Stanford engineers focused on the chase car. Both vehicles were equipped with AI, sensors, and communication systems to perform the tandem drift sequence.
Key aspects of the project include:
- Development of robust control mechanisms for the lead car to ensure safe and repeatable lead runs.
- AI vehicle models and algorithms enabling the chase car to adapt dynamically to the lead car’s motion.
- Modifications by GReddy and Toyota Racing Development (TRD) to each car’s suspension, engine, transmission, and safety systems.
- Use of Nonlinear Model Predictive Control (NMPC) to continually plan and adjust steering, throttle, and brake commands.
- A dedicated WiFi network for real-time communication between the vehicles.
This autonomous tandem drift achievement not only represents a significant technical milestone but also underscores the potential of AI-driven safety systems to prevent accidents and save lives.