AI Device Triggers Alarm When Kids Are Left Alone in Cars

Summer in Australia is almost here, which for many people means beach time, backyard BBQs and lounging contentedly with a poolside drink.

But it’s also a time when cars heat up exponentially, increasing the risk of inhabitants that are left in them for any length of time. With kids and pets most vulnerable, scientists have now developed a sensor that could save lives.

The small, inexpensive sensor, prototyped by researchers at the University of Waterloo in Canada, combines radar technology with artificial intelligence (AI) to detect when there’s unattended children or animals in a car.

At just three centimetres in diameter, the wireless, disc-shaped sensor would be attached to a vehicle’s rear-view mirror or mounted on the ceiling. It sends out radar signals that are reflected back by people, animals and objects in the vehicle. Built-in AI then analyses the reflected signals.

“It addresses a serious, world-wide problem. And it’s so affordable it could become standard equipment in all vehicles.”

The system, whch is believed to have 100 per cent accuracy, would prevent vehicle doors from locking and sound an alarm to alert the driver, passengers and other people in the area that there is a problem.

“It addresses a serious, world-wide problem,” said George Shaker, an engineering professor at Waterloo. “And it’s so affordable it could become standard equipment in all vehicles.”

Shaker adds: “Unlike cameras, this device preserves privacy and it doesn’t have any blind spots because radar can penetrate seats, for instance, to determine if there is an infant in a rear-facing car seat.”

The low-power device, which runs on a vehicle’s battery, distinguishes between living beings and inanimate objects by detecting subtle breathing movements.

Researchers are now exploring whether the device could be adapted to monitor the vital signs of drivers for indications of fatigue, distraction, impairment, illness or other issues.

The device is funded in part by a major automotive parts manufacturer that is aiming to bring it to market by the end of 2020.

A paper on their project, Low-cost low-power in-vehicle occupant detection with mm-wave FMCW radar, was recently presented at an international conference in Montreal.

Image: Graduate students Mostafa Alizadeh, left, and Hajar Abedi position a doll, modified to simulate breathing, in a minivan during testing of a new sensor.