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

Cute little MIT robot built to inspect for pipe leaks

Add as a preferred source on Google

It’s a fact — machines will take a whole lot of jobs in the next decade. They’re putting people out of work as this is being written. But let’s look on the bright side for a moment — machines will also do tasks that are too dangerous or even impossible for humans to perform, such as performing below-ground inspections to detect pipe leaks.

Researchers at the Massachusetts Institute of Technology (MIT) have developed a robotic system that swims through pipes to detect any problems before they burst. By detecting leaks early, the technology may help preserve precious water and the integrity of our cities’ infrastructure. The team, which has called itself PipeGuard, recently won $10,000 in a $100,000 MIT competition.

Recommended Videos

Current leak detection systems can be tedious and expensive, and are often not suited for the type of systems used in developing regions. The MIT approach instead was designed to be quick, affordable, and adaptable to pipes that are made of materials like wood, clay, or plastic.

MIT Leak Detection Robot for City Water Distribution Systems

But it has been no easy feat. It took the team nine years of research, development, and testing to create the oversized badminton birdie that is currently undergoing trials inside the 12-inch concrete pipes under Monterrey, Mexico.

The robot consists of a soft rubber housing with battery and storage, a flexible support that can measure the pipe’s change in size, and a membrane sensor that gets tugged by the outgoing water flow when it passes over a leak. If both the support and the membrane are flexed, than the robot can determine it has just passed over a bump rather than a crack in the pipe.

The robot was previously field tested in a rusty, mile-long section of pipe in Saudi Arabia, and it was able to detect leaks while ignoring false alarms.

“We put the robot in from one joint, and took it out from the other. We tried it 14 times over three days, and it completed the inspection every time,” You Wu, a graduate student working on the project, said in a statement. The robot also outperformed conventional detection methods, being up to ten times more sensitive, according to the researchers.

For its upcoming tests in Monterrey, Mexico, the team will attempt to develop a collapsible version of the robot that would be able to expand like an umbrella so it can fit in pipes of various sizes. Wu and his colleagues will describe the system in detail at the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) in September.

Dyllan Furness
Former Contributor
Dyllan Furness is a freelance writer from Florida. He covers strange science and emerging tech for Digital Trends, focusing…
Google Flow Music Spaces is becoming an all-in-one AI music studio
The latest update brings song editing, stem splitting, image generation, lyrics, and video creation into a single workspace.
Google Flow Music Featured

The company has announced a major update for Flow Music Spaces, bringing a suite of new AI-powered creative tools directly into collaborative workspaces. Instead of jumping between different apps or sessions, users can now generate and edit songs, split audio stems, create images, write lyrics, and even generate videos without leaving a Space.

What's new in Flow Music Spaces?

Read more
A Florida pastor asked ChatGPT if he was okay. It nearly got him killed.
When "just relax and recover" turns out to be the worst medical advice you could get.
ChatGPT on iPhone

Scott Winters, a pastor from Florida, is suing OpenAI after ChatGPT allegedly gave him what his lawsuit calls "extremely dangerous" medical advice, advice that nearly cost him his life.

What happened to the pastor?

Read more
Scientists made robots curious like toddlers, and it helped them learn language twice as fast
Give a robot curiosity, and it starts learning language (and misbehaving) just like a toddler.
robots and kids photo

Scientists have been trying to figure out how kids pick up language so fast for decades, and a new study out of the Okinawa Institute of Science and Technology (OIST) might have cracked part of the puzzle: curiosity.

Researchers built a virtual robot with a brain-inspired neural network and set it loose in a simulated 3D world full of shapes, colors, and simple commands like "push left magenta dumbbell." 

Read more