Waterloo University engineers have developed a new decision-making and motion-planning technology for self-driving vehicles.
The new system helps limit injuries and damage caused by self-driving vehicles involved in crashes.
It works by analyzing all available options and chooses the right course of action with the least serious outcome after recognizing that a collision of some kind is inevitable.
According to professor Amir Khajepour – who heads Waterloo’s Mechatronic Vehicle Systems Lab, the goal of this research was to minimize the consequences of autonomous vehicle crashes.
The first rule governing the new autonomous vehicle (AV) crash-mitigation technology is to avoid collisions with pedestrians.
From there, it weighs factors such as relative speeds, angles of collision and differences in mass and vehicle type to determine the best possible manoeuvre, such as braking or steering in one direction or another.
Khajepour contends that there is a necessity for such systems because the popular idea that AVs of the future will completely eliminate crashes is a myth.
Although safety should improve dramatically, Khajepour asserts that there are just too many uncertainties for self-driving vehicles to handle them all without some mishaps:
“There are hundreds, thousands, of variables we have no control over. We are driving and all of a sudden there is black ice, for instance, or a boulder rolls down a mountain onto the road.”
AVs are capable of limiting damage when a crash is unavoidable because they always know what is happening around them via sensors, cameras and other sources.
They routinely make tens and even hundreds of decisions per second based on that information.
Waterloo’s new system decides how an AV should respond in emergency situations based primarily on pre-defined mathematical calculations considering the severity of crash injuries and damage.
The engineers haven’t factored in extremely complex ethical questions such as: 1) whether an AV should put the safety of its own occupants first, 2) or weigh the well-being of all people in a crash equally.
Khajepour is hopeful that once carmakers and regulators standardize the ethical rules for self-driving vehicles, the new system can be designed to integrate them wisely.
Image and content: IEEE VTS/University of Waterloo via Eurekalert