A drone dropped a “rescue pod” into waters south of Brisbane, saving two swimmers in distress.
From NYTimes by Isabella Kwai
A practice session for Australian lifeguards who were testing a new drone turned into a real rescue when the drone helped save two swimmers at a beach in New South Wales.
On Thursday morning, Jai Sheridan, a lifeguard supervisor who was operating the drone, was alerted to two young men caught in turbulent surf with 10-foot swells.
Mr. Sheridan then steered the drone toward the swimmers.
In video of the incident taken from the drone, it can be seen releasing a yellow “rescue pod” that inflates in the water.
The two swimmers grabbed the pod, and with its support they made their way to shore.
They were fatigued, but not hurt, Surf Life Saving New South Wales, a volunteer organization, said in a statement.
The rescue took just 70 seconds. “On a normal day that would have taken our lifeguards a few minutes longer,” Mr. Sheridan said.
Little Ripper Lifesaver drones use world first algorithm technology to spot sharks for public safety at beaches.
Fitted with onboard sirens and voice messages in multiple languages they also warn people of any danger.
The lifesaving drones have multiple deployable automatically inflating rescue tubes capable of supporting up to 4 people in a rescue situation.
The drone used for the rescue, known as a Little Ripper unmanned aerial vehicle, is also part of a shark-spotting program being rolled out across Australian beaches this summer.
It uses an algorithm to automatically recognize sharks.
“The applications in the water are just phenomenal,” said Michael Blumenstein, a professor at the University of Technology Sydney who oversaw the team that developed the shark-spotting software. “The amount of payload that these drones carry enable them to be really be versatile.”
Drones and AI Take On Killer Sharks Down Under in Australia.
Whether or not shark attacks are a major problem in Australia, the Australian government has devoted an enormous amount of resources into trying to mitigate the risk of sharks near popular beaches.
They've tried nets to keep the sharks out, they've tried electronic gadgets to dissuade them, and they've tried lots of different ways of killing them, without much in the way of evidence that any of it is particularly effective.
After six months of trials, the latest and most robot-y idea is about to be implemented: drones will start patrolling some Australian beaches next month, using cameras and some AI-backed image analysis software to spot lurking sharks much better than humans can.
Humans aren't particularly good at identifying sharks on aerial imagery.
We can manage a 20-30 percent accuracy rate, which means both identifying other things as sharks (kinda bad) and misidentifying sharks as other things (way worse).
As with many tasks of this kind, a machine learning system does much better: once it's been trained on labeled aerial videos of sharks, whales, dolphins, surfers, swimmers, boats, and whatever else, the software is 90 percent accurate at telling humans to panic because there's a shark somewhere.
And when implemented on a drone, the system really does tell people to panic, using a loudspeaker to warn them that there's a shark in the water.
The drones come from an Australian company called Westpac Little Ripper, which modifies a few different kinds of commercial drones for tasks like shark spotting as well as general life-saving operations, such as dropping beacons and even rafts.
The larger Little Ripper drones are gas powered and can fly for hours, which is nice, but they somehow cost up to US $250,000 each.
In cases involving rough surf, remote locations or natural disasters, where conditions may be hazardous and time is a factor, Professor Blumenstein said, drones are able to help operators assess a situation without endangering human lives.
Farmers have also found practical applications for drones, using them to efficiently assess the health of their crops, for example.
But in crowded urban areas, Professor Blumenstein said, security concerns may still be an issue. “People are still, I think, wary of low-hanging hovering objects, and rightfully so,” he said.
A lifesaving example of the power of AI in edge devices is demonstrated using a UAV (unmanned aerial vehicle) and the Intel® Movidius™ Neural Compute Stick.
The Little Ripper Lifesaver UAV is currently using cloud-based AI to monitor the Australian coastline.
n Intel proof-of-concept using Intel Movidius technology shows that AI processing could be done directly on the device, allowing for more immediate danger detection and response time.
In December, the state government of New South Wales announced that it would invest 430,000 Australian dollars, or $345,000, into drone technology as part of a trial on the state’s North Coast.
John Barilaro, deputy premier of New South Wales, said after Thursday’s rescue that the investment had already paid off.
“Never before has a drone, fitted with a flotation device, been used to rescue swimmers like this,” Mr. Barilaro said.
The software developed by Professor Blumenstein’s team could soon become a vital tool for lifeguards.
“There’s no reason why we couldn’t use it to automatically detect people in the water,” he said.
- YouTube : Drones detect Sharks at Lighthouse Beach, Ballina / Shark-spotting drones on patrol at Australian beaches
- Sydney Morning Herald : Drone used to save two swimmers caught in rough surf at Lennox Head
- ABC : Drone helps rescue teens just hours after being unveiled for trial at Lennox Head
- BBC : Caister lifeboat crew trials drones for rescues