Kangaroos are confusing self-driving cars
Kangaroos are involved in 20,000 car accidents every year in Australia Image: REUTERS/Fabrizio Bensch
Manufacturers of driverless cars promise that collisions will become a thing of the past.
Self-driving cars will be safer, they claim. With super sensors, laser and camera technology, they will be able to spot another car approaching, or a pedestrian in the road, and react far faster than a human driver could.
But when it comes to preventing collisions with kangaroos, engineers at Volvo have hit a stumbling block.
Crashes involving an animal cause the deaths of around 200 people a year in the United States. And about 20 times a day, a driver somewhere in Sweden crashes a car into a moose. Indeed, these types of collisions are the reason the Swedish carmaker has made large animal detection systems part of the design for its driverless cars.
Designed for a moose
The software, however, was designed with the prospect of a large animal such as a moose wandering into the road. So when the technology was tested in Australia it struggled to detect kangaroos.
If you drive on Australian roads, chances are, sooner or later, you will come across a kangaroo. And if you’re unlucky, you might be in one of the 20,000 accidents every year involving the marsupials.
In 2015, a team of Volvo Cars safety experts travelled to the Australian Capital Territory – a kangaroo collision hotspot – to film and study the roadside behaviour of kangaroos in their natural habitat. The data Volvo Cars collected was to be used to develop the first ever kangaroo detection and collision avoidance system.
“In Sweden we have done research involving larger, slower moving animals like moose, reindeer and cows, which are a serious threat on our roads. Kangaroos are smaller than these animals and their behaviour is more erratic. This is why it’s important that we test and calibrate our technology on real kangaroos in their natural environment,” Volvo said in a press release at the time.
Volvo Cars is developing a system that uses radar and camera technology to detect kangaroos and automatically apply the brakes if an accident is imminent.
However, the carmaker told Australia’s ABC News that after 18 months of studying kangaroos at the Tidbinbilla Nature Reserve in Canberra, it still hasn't been able to develop a reliable way to detect kangaroos on the road.
"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 said.
There could be a simpler solution, though.
Fraser Shilling, Director of the California Roadkill Observation System, a program that tracks roadkill, locates collision hotspots and aims to reduce wildlife mortality on roadways, told Smithsonian magazine that fencing along major roadways coupled with green overpasses or tunnels could all but eliminate car-animal collisions in some places.
Noting that some US counties can spend up to $2 million per year picking up and disposing of wildlife carcasses, he adds: “I think it is worth investigating the smart vehicle, but it kind of avoids the question of why we aren’t going with the other option of just building the crossings and fencing when it’s so cost effective.”
In the meantime, if you come across a kangaroo while driving in Australia, the advice from Australia’s National Roads and Motorists' Association is as follows:
“Kangaroos are most active around sunrise and sunset when they are foraging and this is when they are most likely to venture onto roads, so we encourage drivers to slow down during twilight hours.
“If you see an animal on or near the road, you should try and brake, but not swerve to avoid a collision. Reduce your speed inside signposted wildlife areas. Stay alert.”
Don't miss any update on this topic
Create a free account and access your personalized content collection with our latest publications and analyses.
License and Republishing
World Economic Forum articles may be republished in accordance with the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International Public License, and in accordance with our Terms of Use.
The views expressed in this article are those of the author alone and not the World Economic Forum.
Stay up to date:
Mobility
The Agenda Weekly
A weekly update of the most important issues driving the global agenda
You can unsubscribe at any time using the link in our emails. For more details, review our privacy policy.