The kangaroos in Austaraila are confounding self-driving tech in Volvos. Volvo has been testing self-driving City Safety tech in the down under since October 2015.
Kangaroos throwing off the “Large Animal Detection” becasue of the way the move.
“We’ve noticed with the kangaroo being in mid-flight … when it’s in the air it actually looks like it’s further away, then it lands and it looks closer,” Volvo Australia’s technical manager David Pickett told the Australian Broadcasting Corp.
Volvo Cars started developing kangaroo detection technology to solve one of the most costly causes of traffic collisions in Australia.
A team of Volvo Cars safety experts travelled to the Australian Capital Territory to film and study the roadside behaviour of kangaroos in their natural habitat. The data Volvo Cars collected will be used to develop the first ever kangaroo detection and collision avoidance system.
According to the National Roads & Motorists’ Association (NRMA) there are over 20,000 kangaroo strikes on Australian roads each year costing over AU $75 million in insurance claims. The human cost of serious injuries and fatalities from animal collisions is incalculable.
Too help address this Volvo Cars is developing a unique system that uses radar and camera technology to detect kangaroos and automatically apply the brakes if an accident is imminent.
The technology behind this research into kangaroo detection is an evolution of City Safety which detects cars, cyclists and pedestrians both during the day and night.
A radar sensor in the grill scans the road ahead to detect moving objects like animals, cars, cyclists and pedestrians. A very advanced light-sensitive, high-resolution camera in the windscreen works in parallel with the radar to detect which way the object is moving and help the computer decide what action to take, if any.
When the object is detected, it takes 0.05 seconds for the computer system to react on the situation. This should be compared with the human reaction time of about 1.2 seconds. The only problem is the