Toyota Research Institute has been re-creating the circumstances surrounding an unfortunate (albeit decidedly less tragic) event -- a three-vehicle highway crash involving a Toyota test car -- and figured out a way that the car could automatically intervene to make sure the collision never happened in the first place.
Here's how it works: As a secondary track to its autonomous driving research, Toyota Research Institute has been developing something it calls "Toyota Guardian" -- a passive safety system that augments human control of a vehicle and can intervene to avoid collisions.
Within the last year, Toyota developed a concept for its Guardian system borrowed from fighter jets that it calls "blended envelope control." Much like a fighter jet's fly-by-wire control system translates a pilot's inputs into the micro-adjustments necessary to fly a plane, the blended envelope control concept translates the driver's intent into the operation of a car.
And Toyota is willing to share the technology with other automakers.
“We were thinking about what would be good for society,” Toyota Research Institute CEO Gill Pratt said at a press conference at the trade show formerly known as the Consumer Electronics Show, which has become a showcase for driverless cars. “We will not keep it proprietary to ourselves only. But we will offer it in some way to others, whether that’s through licensing or actual whole systems.”
To show how it works on Monday at CES in Las Vegas, Pratt used a re-creation of a three-vehicle noninjury crash that occurred on a California interstate and involved one of Toyota's autonomous test vehicles.
"Our test vehicle was traveling at freeway speed in manual mode with its autonomy mode disabled as it gathered data at the many tunnels and bridges in the San Francisco Bay Area," Pratt explained in a written release. "After we downloaded data from the incident, we asked ourselves: Could this crash have been mitigated, or avoided altogether by a future Toyota Guardian automated safety system? We believe the answer is yes."
Toyota Research Institute used the data its vehicle had gathered in the crash to build an accurate simulation, then re-created the crash on its test track as a learning tool for the car to figure out its options. Toyota, and the car, discovered that in the case of the accident, the vehicle's "best option was to quickly accelerate safely away from encroaching vehicles," thereby avoiding the crash.
"We humans have an inherent need for autonomy, which is much stronger than our desire for autonomous cars," Pratt said in a written statement. "It's about the sheer delight of mobility when a child first learns to stand up and make its way across a room without the help of Mom or Dad. And it is the joy of just going for a drive, behind the wheel of a car that can accelerate, brake and turn as if it is an extension of your body."
Toyota says augmented driving systems, such as Toyota Guardian, are important alternatives to the as-yet-unfulfilled desire of some for a fully autonomous transportation system, allowing humans to continue to experience the joy of driving with the added safety benefit of as-needed technological intervention.
"We think the most important benefit of automated driving is not about the autonomy of cars," Pratt said in the statement, "but about the autonomy of people."
Bloomberg contributed to this report.