Skip to main content

Amazon worker’s A.I.-powered cat flap stops his pet from bringing in dead animals

How do you stop your beloved pet cat catching and murdering innocent wildlife, then bringing it into your home in the middle of the night and waking you up? There’s plenty of advice out there, ranging from getting sweet little Figaro a collar with a bell, to disincentivizing the act by quickly disposing of dead critters without making a fuss. Of course, if you’re a technically minded Amazon employee, there’s another option too: You rig up your cat flap to an A.I.-enabled camera and Arduino-powered smart locking system. You know, the good, old fashioned way.

That’s exactly what Amazon product manager Ben Hamm did recently, after reaching the end of his tether with cute-yet-murderous cat Metric. To create the door locking mechanism, Hamm affixed an Arduino to an electromagnetic bolt that he attached to the cat door. He also set up a camera using Amazon’s AWS DeepLens, a programmable video camera which can run deep learning models locally and take action according to what it sees. He then set about coding his solution using programming language Python and Amazon SageMaker, a managed cloud service that enables developers to build, train, and deploy machine learning models.

Cats, Rats, A.I., Oh My! - Ben Hamm

“The most important part of training machine learning software is getting your hands on enough data,” Hamm told Digital Trends. “First I programmed my camera just to capture images every time it detected movement, and then I spent months labeling over 23,000 images. As the most important data — Metric bringing in prey — happened unpredictably, this took time. If my camera failed when Metric brought in a rat, I would get disappointed. You start to get very greedy for quality data! Once I had the data nice and labeled, I fed it into Amazon SageMaker to create image classification models.”

The finished system means that, when Hamm’s camera detects Metric trying to bring in prey, it sends a USB signal that locks the door. (Because DeepLens does its processing locally, this will work even if Hamm’s internet goes down.) The cat flap remains locked for a quarter hour, and Hamm is sent a text message. He also set it up so that it sends a “blood money” donation to the National Audubon Society, which protects birds.

As to whether he plans to commercialize the technology, Hamm remains unsure. “The finished product is currently installed over the window of my cottage,” he said. “I was not planning on commercializing it, but the outpouring of desperate cat owners has definitely been interesting!”

Editors' Recommendations

Luke Dormehl
I'm a UK-based tech writer covering Cool Tech at Digital Trends. I've also written for Fast Company, Wired, the Guardian…
Meet the man fighting plastic pollution with a fleet of A.I.-powered camera drones
machine learning drone plastic problem beach feat 2

Vision From the Skies: The Plastic Tide Project

That plastic cup you’ve got sitting on your desk looks pretty harmless on its own. However, add it to the rest of the plastic that humanity throws away on a daily basis and you have the makings of the estimated 5 to 13 million metric tons of plastic trash which reportedly wind up in the world’s oceans every year. U.K.-based Plastic Tide founder Peter Kohler got a glimpse of the scale of this problem a decade ago -- and it changed the course of his life.

Read more
How A.I. and a prehistoric creature could help predict animal behavior
ai animal behavior hydra copy

Like the sentient toys in Toy Story, animals seem to lead exciting lives when humans aren't watching. Ancient creatures called Hydra, on the other hand, don't seem to do much at all. But that's what makes them so interesting.

In a recent study, researchers used a machine learning algorithm -- one that is usually used to filter spam email — to catalog Hydra behavior. With one of the simplest nervous system on Earth, Hydra give scientists a basic sample to study how neural activity relates to physical activity, potentially paving the way for future research into predicting animal behavior.

Read more
Poachers don’t stand a chance against these A.I.-powered camera drones
rhino horns 3d printing 65751733 l

Simon Eeman/123RF

The use of artificial intelligence to protect wildlife is something researchers have been working on for a while. However, computer scientists at the University of Southern California are taking it to the next level with the creation of a deep learning-based A.I. system that is able to spot poachers in near real-time, based on video shot from drones.

Read more