Skip to main content
  1. Home
  2. Emerging Tech
  3. Legacy Archives

MIT designs autonomous robot that assembles IKEA furniture

Add as a preferred source on Google

IkeaBotWe’ve already got robots for some of life’s most tedious tasks – there’s the Roomba for vacuuming, the Looj for cleaning the gutters, and Siri for writing our texts when we’re too drunk to use our thumbs. In the utopian future, we’ll have a robot for every stupid chore we hate doing ourselves, and thanks to the wizards at MIT, we can finally cross one more of these tasks off the list: assembling IKEA furniture. Thats’s right, MIT researchers have actually developed a robot that will assemble flat-pack furniture on it’s own, with minimal direction.

This revolutionary contraption was unveiled earlier this week at the IEEE International Conference on Robotics and Automation (ICRA) by a team from MIT’s Distributed Robotics Laboratory. But before you crap yourself from being so impressed, you should know that the IKEAbot isn’t just one robot – it’s actually a pair of them. Just like with humans, it takes two to assemble a Borgsjö TV stand. Going it alone will only lead to frustration, rage, and involuntary enrollment in an anger management program. So, in an effort to avoid any outbursts of hellish robotic fury, the team from MIT wisely built the IkeaBot from a pair of KUKA  YouBots, each of which have been retrofitted with special arms for screwing things in. Not only is this a wildly innovative idea, it also finally gives us an answer to the age old question of “how many robots does it take to screw in a table leg?”

Recommended Videos

Words don’t really do it justice, so check out the video below to get an idea of how it works. Skip to somewhere around the two minute mark to see it in action.

The hardware is pretty impressive, but in all honesty the software is where the magic happens. To begin, the only thing the bots are given is a set of CAD files that describe the furniture in terms of geometry, number of parts, screw holes locations. From there, they use a custom object-oriented symbolic planning system to figure out how the pieces fit together – without actually knowing what the finished furniture will look like. Aside from the CAD files, all the bots know is that every screw hole should be used and that no parts should be left over. Amazingly, even with such simple rules, the bots almost always end up with the right configuration . 

Unfortunately, the project is far from being commercially available, but let’s not kid ourselves here – if you’re buying furniture at IKEA, chances are you can’t afford a pair of 20,000-dollar autonomous robots to assemble it for you. For now, you’ll have to build stuff the old fashioned way: on your knees, with the instructions in the wastebasket. But if you’re patient, I’m sure we’ll have these badboys at our disposal in just a couple years.

Drew Prindle
Former Senior Editor, Features
Drew Prindle is an award-winning writer, editor, and storyteller who currently serves as Senior Features Editor for Digital…
Meta goes toe-to-toe with the big boys as it launches Muse Wonder AI models
Illustration of Meta Muse Wonder AI model.

It's raining frontier AI models. Soon after Anthropic set alarm bells ringing with its Claude Fable model at the summit of AI peformance, OpenAI answered with GPT-6 Astra. Not one to be left behind, Google released Gemini 4 Argon. The race is now getting hotter as Meta enters the fray with two new AI models in the Muse series: Wonder and Wonder Full. Cheesy naming aside, these Meta AI models mean business, or at least that's what the benchmark figures suggest. More importantly, these AI models are already making their way to Muse users.

https://twitter.com/DigitalTrends/status/2109699549375988120

Read more
AI can’t tell if you’re gay or straight, but it thinks it knows what both look like
AI knows it shouldn't judge a face, but apparently, drawing one is a different story.
Emilia Clarke AI generated stock image. Gemini / Nano Banana is on the left

We've all been told not to judge a book by its cover, and you'd think AI would follow that rule, too. Ask an AI chatbot to guess someone's sexual orientation just by looking at their face, and it'll likely tell you that there's no reliable way to know. But what happens when you ask that same model to change someone's appearance to match a particular sexual orientation? Well, that's where things get uncomfortable.

A new study, accepted for presentation at the 2026 Conference on Empirical Methods in Natural Language Processing, found that AI models from OpenAI and Google can be inconsistent when handling sensitive personal characteristics. They might refuse to make assumptions about someone based on their appearance, but when asked to generate those same assumptions visually, the results tell a very different story.

Read more
A clinical study with Google’s special chatbot shows a strong future for AI in healthcare
Google’s medical AI could give doctors a useful second set of eyes
Google Articulate Medical Intelligence Explorer chatbot

AI is a useful tool for handling many tasks in private as well as professional settings, but medical advice, especially diagnosis, is one area where I generally draw the line. General-purpose chatbots tend to sound confident and convincing while giving medical advice, even when they are wrong, as studies have previously found.

That being said, Google's new research points to a much more convincing use for AI in healthcare. Its Articulate Medical Intelligence Explorer chatbot, or AMIE for short, could help prepare both sides before the appointment even begins.

Read more