Skip to main content

MIT’s new robot can play everyone’s favorite block-stacking game, Jenga

MIT Robot Learns How to Play Jenga

Not content with getting freakishly good at cerebral games like chess and Go, it seems that artificial intelligence is now coming for the kind of fun games we played as kids (and childish adults). With that in mind, researchers from the Massachusetts Institute of Technology (MIT) have developed a robot which uses the latest machine learning computer vision to play everyone’s favorite tower-toppling game Jenga.

If it’s been a while since you played Jenga, the game revolves around a wooden tower constructed from 54 blocks. Players take it in turns to remove one block from the tower and place it on top of the stack. Over time, the tower gets taller and, crucially, more unstable. The result is a game of impressive physical skill for humans — and, now, for robots as well.

MIT’s Jenga-playing bot is equipped with a soft-pronged gripper, force-sensing wrist cuff, and external camera, which it uses to perceive the block-based tower in front of it. When it pushes against a block, the robot takes visual and tactile feedback data from the camera and cuff, and weighs these up against its previous experiences playing the game. Over time, it figures out when to keep pushing and when to try a new block in order to stop the Jenga tower from falling.

“Playing the game of Jenga … requires mastery of physical skills such as probing, pushing, pulling, placing, and aligning pieces,” Alberto Rodriguez, assistant professor in the Department of Mechanical Engineering at MIT, said in a statement. “It requires interactive perception and manipulation, where you have to go and touch the tower to learn how and when to move blocks. This is very difficult to simulate, so the robot has to learn in the real world, by interacting with the real Jenga tower. The key challenge is to learn from a relatively small number of experiments by exploiting common sense about objects and physics.”

On face value, the idea of a robot whose only mission is to play Jenga doesn’t sound like it has much real-world applicability. But the concept of a robot that can learn about the physical world, both from visual cues and tactile interactions, has immense applicability. Who knew a Jenga-playing robot could be so versatile?

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…
Scientists are using A.I. to create artificial human genetic code
profile of head on computer chip artificial intelligence

Since at least 1950, when Alan Turing’s famous “Computing Machinery and Intelligence” paper was first published in the journal Mind, computer scientists interested in artificial intelligence have been fascinated by the notion of coding the mind. The mind, so the theory goes, is substrate independent, meaning that its processing ability does not, by necessity, have to be attached to the wetware of the brain. We could upload minds to computers or, conceivably, build entirely new ones wholly in the world of software.

This is all familiar stuff. While we have yet to build or re-create a mind in software, outside of the lowest-resolution abstractions that are modern neural networks, there are no shortage of computer scientists working on this effort right this moment.

Read more
Inside the rapidly escalating war between deepfakes and deepfake detectors
Facebook Deepfake Challenge

Imagine a twisty-turny movie about a master criminal locked in a war of wits with the world’s greatest detective.

The criminal seeks to pull off a massive confidence trick, using expert sleight of hand and an uncanny ability to disguise himself as virtually anyone on the planet. He’s so good at what he does that he can make people believe they saw things that never actually happened.

Read more
The BigSleep A.I. is like Google Image Search for pictures that don’t exist yet

In case you’re wondering, the picture above is "an intricate drawing of eternity." But it’s not the work of a human artist; it’s the creation of BigSleep, the latest amazing example of generative artificial intelligence (A.I.) in action.

A bit like a visual version of text-generating A.I. model GPT-3, BigSleep is capable of taking any text prompt and visualizing an image to fit the words. That could be something esoteric like eternity, or it could be a bowl of cherries, or a beautiful house (the latter of which can be seen below.) Think of it like a Google Images search -- only for pictures that have never previously existed.
How BigSleep works
“At a high level, BigSleep works by combining two neural networks: BigGAN and CLIP,” Ryan Murdock, BigSleep’s 23-year-old creator, a student studying cognitive neuroscience at the University of Utah, told Digital Trends.

Read more