Not all cars are made equal. And in Swedish carmaker Volvo's case, adjustments need to be made according to the local conditions of each country.
Turns out, its self-driving cars are unable to detect kangaroos, because of their unique "hop-to-hop" movements which are different from other large animals.
Volvo's system is able to identify other wild animals such as elk and moose correctly, but get "confused" when trying to detect kangaroos' hops.
"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," David Pickett, Volvo Australia's technical manager, told ABC Australia.
The car takes the ground as a reference point for detecting its distance from objects. Therefore, the jumpy animals' "usual" movement pattern makes it difficult to determine how far away they are.
However, it is more complicated than that.
"First we have to start identifying the roo," Pickett said. "We identify what a human looks like by how a human walks, because it's not only the one type of human — you've got short people, tall people, people wearing coats. The same applies to a roo."
"If you look at a roo sitting at the side of a road, standing at the side of a road, in motion, all these shapes are actually different," he added.
Kangaroos are responsible for nine out of ten road accidents involving animals in Australia, according to statistics released by the Australian Associated Motor Insurers Limited (AAMI) in 2016.
Volvo's research team is still trying to solve the inherently Australian problem.
The Swedish manufacturer is working on its self-driving cars with automotive safety systems company Autoliv and chipmaker Nvidia, and expects to have them on the road by 2021.
