Skip to main content
  1. Home
  2. Emerging Tech
  3. Features

The world's first poop scooping drone is a marvel of modern engineering, and also totally ridiculous

Add as a preferred source on Google

People in tech like to dream big. Steve Jobs wanted to take personal computers and transform them from geeky gadgets for a few hobbyists into beautiful consumer-friendly items found in every home. Google’s founders wish for a world in which they can make information universally accessible and useful.

Gerben Lievers wants to use drones and ground-based robots to clean up dog poop.

Recommended Videos

The 30-year old founder and strategy director of Tinki.nl, a Netherlands-based canine price comparison website (comparing accessory prices; not the dogs themselves), Lievers said that the one thing that upsets him about dog ownership is the 220 million pounds of dog droppings that are not properly disposed of in the Netherlands alone each year.

“We hear a lot of people complaining about dog poo,” he told Digital Trends. “One day I decided to try and think of a way to help solve the problem.”

“On paper it was perfect. Then we built a prototype, and it actually worked!”

While most of us would probably write an upset letter to the newspaper, or our local congressman, Lievers stumbled upon another possible solution.

“I was at an entrepreneur evening, and after the show I got talking to someone who was working in the drone business,” he continued. “We ended up talking about dog poo, and I asked him how he would consider solving it with drones. We agreed to meet up again, and to go to the drawing table to try and come up with a solution for this big problem. On paper it was perfect. Then we built a prototype, and it actually worked!”

The first prototype the pair — Lievers and the brains behind drone company Space53 — came up with represented a two-part attack on dog mess. The aerial component consists of a drone called Watchdog 1, which sports thermal imaging for spotting errant canine coils, based on their warm temperatures compared to the surrounding area. This data is then translated into GPS coordinates and transmitted to a ground-based robot called Patroldog 1, which trundles off to collect its foul-smelling prize.

“We tried [a version] that was more like a vacuum cleaner to suck it up, and one with arms that could [pick up the poo],” Lievers said. “In the end, the vacuum cleaner was better because of the different consistencies. That way the poo is also completely gone so the entire area is left clean.”

So engineering problem solved, right? Not quite. “The prototype we’re now working on deals with the problem that some dog poo is older and no longer warm,” he noted. “To get around this challenge, we use recognition software to determine that it’s dog poo.”

Image used with permission by copyright holder

The team is Developing these tools with some help from researchers at the nearby University of Twente. “When I first contacted them on the phone, they laughed, but then I explained how serious I was,” he said.

As far as recognition tasks go, Lievers said that dog deposits are just another object to detect. “It’s a bit like facial recognition,” he explained, making the faces/faeces comparison we never wanted to hear. “Every face looks different, but they’re recognized as faces. That’s the same with the technology we’re using here with poo. The form and shape may be different with each one, but when you have a database with enough training images it’s possible. There may be some false positives in it, but most will be recognized.”

“To get around this challenge, we use recognition software to determine that it’s dog poo.”

Improving the database of poop-related pictures, he said, could end up relying on crowdsourcing. “It may be that people will need to send us pictures of the poo of their dog in order to train our machines to be better,” he suggested.

So what’s next? “We hope to trial the prototypes in a few neighborhoods where the dog poo is really a big challenge as early as the end of this year, or the beginning of next year,” he explained. “A lot of this depends on how the technology can be developed, however, as well as how willing the government is to take part.”

Dogdrones from Tinki.nl put an end to the dog poo problem

Lievers’ hope is that local governments will provide funding for the project, with the idea that neighborhood volunteers can then be trained to fly the drones themselves, since they’re not yet autonomous. He also wants to expand Patroldog 1’s storage space, since currently it can only handle a “few handfuls of poo.”

Which leaves just one question: is this all a big joke? After all, when he’s not working at Tinki.nl, Lievers is also the owner of an award-winning digital marketing agency, Team Nijhuis.

“When change appears, people always think like this,” he said, bristling slightly at the suggestion. “We’ve had a lot of questions from people asking if this an April Fool’s joke. It’s not. I hadn’t even thought about that. Technology makes our lives better. This is an example of one way it can do it. When people tell me they think this is a joke I ask them why. I want people to shoot holes in the idea, because that way we can make it better.”

Just so long as you don’t shoot holes in it anywhere near our nice clean front yard!

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…
Yet another study says AI is bad for elections, and the rabbit hole gets worse
AI may be an election bomb waiting for someone to light the fuse
Voters cast their ballots on Election Day

Another election, another study has concluded that asking an AI chatbot for political guidance is a spectacularly bad idea. Research conducted during Hungary’s 2026 parliamentary election found that ChatGPT and Google Gemini offered not just inaccurate but also inconsistent and unreliable voting advice. The chatbots misclassified voter profiles, overlooked relevant parties, recommended parties absent from the ballot, and sometimes produced materially different answers when given the same information repeatedly.

AI keeps failing the voter test

Read more
Samsung’s humanoid robot ambitions are real, but factories come first
Samsung’s new robotics division has humanoids in its sights, although its immediate business is far more practical factory automation
Robot Touch Human Finger

Samsung wants a place in the humanoid race, but its new robotics push begins with machines built for factories rather than homes.

The CEO-led RX robotics division will initially focus on manufacturing robots. Samsung has separately identified humanoids as a priority, although it hasn’t announced a commercial model or explained where one fits into the division’s immediate plans.

Read more
The future of AI may depend on this one behind-the-scenes change
Running Claude on Android.

Whenever a new AI model arrives, it's easy to get caught up in the bells and whistles. We talk about how much smarter it is, how quickly it answers questions, or how realistic its images have become. But here's the thing: none of that matters much if the AI can't reliably work with the apps and services people use every day.

That's why an upcoming update to the Model Context Protocol (MCP) caught my attention. It isn't a new chatbot or a fancy AI model. In fact, most people will never even know it's happening. But it could quietly make the AI ecosystem a lot healthier. If you've never heard of MCP before, don't worry. Think of it as a shared language that lets AI assistants safely talk to apps like Gmail, Slack, calendars, databases, and countless other services. Instead of every company inventing its own way to make those connections, MCP gives everyone a common rulebook.

Read more