Engineering news

System aims to limit self-driving crash injuries without ‘complex ethical questions’

Professional Engineering

Stock image (Credit: Shutterstock)
Stock image (Credit: Shutterstock)

A new decision-making and motion-planning technology could limit injuries and damage in “unavoidable” crashes involving self-driving cars.

Professors of mechanical engineering and mechatronics at the University of Waterloo in Canada developed the system, which is mainly based on pre-defined mathematical calculations considering the severity of damage and crash injuries.

“The popular idea that autonomous vehicles of the future will completely eliminate crashes is a myth,” said the research announcement. “Although safety should improve dramatically… there are just too many uncertainties for self-driving vehicles to handle them all without some mishaps.”

The first rule for the crash-mitigation technology is avoiding collisions with pedestrians. From there, it considers 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 a particular direction.

The system considers the whole ‘traffic environment’ perceived by the autonomous vehicle, including all the other vehicles and obstacles. After recognising that a collision of some kind is inevitable, it analyses all available options and chooses the course of action with the ‘least serious’ outcome.

Safety should improve “dramatically” with widespread introduction of self-driving cars, said Amir Khajepour, director of the Mechatronic Vehicle Systems Lab. However, he added, “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".

Autonomous vehicles 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, routinely making tens and even hundreds of decisions per second based on that information. The new system is based primarily on pre-defined mathematical calculations considering the severity of crash injuries and damage.

Researchers did not attempt to factor in extremely complex ethical questions, such as whether a car should put the safety of its own occupants first or weigh the wellbeing of all people in a crash equally. However the system is designed to integrate ethical rules once they have been decided by carmakers and regulators, said Khajepour.

A recent IMechE report called for more testing of self-driving vehicles to improve public confidence in the technology.

The new research was published in IEEE Transactions on Intelligent Transportation Systems.


Content published by Professional Engineering does not necessarily represent the views of the Institution of Mechanical Engineers.
Share:

Read more related articles

Professional Engineering magazine

Professional Engineering app

  • Industry features and content
  • Engineering and Institution news
  • News and features exclusive to app users

Download the Professional Engineering app

Professional Engineering newsletter

A weekly round-up of the most popular and topical stories featured on our website, so you won't miss anything

Subscribe to the Professional Engineering newsletter

Opt into your industry sector newsletter

Related articles