Skip to Content
Artificial intelligence

A robot dog has learned to run faster with machine learning

January 16, 2019

Reinforcement learning has helped a four-legged bot move a bit like a real animal, without having to be taught how to make each step.

The news: Roboticists want their creations to mimic animals because animals invariably move in the most energy-efficient way. But the eerily lifelike movement of robots like Boston Dynamics’ Spotmini is usually coded by hand. Now researchers have combined simulation with a technique called reinforcement learning to teach a dog-like robot called “ANYmal” to run faster and recover from falls. Crucially, it did so without any manual intervention. 

Train at super-speed: The simulation let the team run training sessions 1,000 faster than real time on more than 2,000 ANYmals simultaneously. After the simulated training was transferred to a real robot, it was able to exceed its previous top speed by 25% and flip over after falls, the EFH Zurich team explains in a new paper published in Science Robotics today. It’s still pretty limited (as you’ll see above), but it’s a step (ho ho) in the right direction.

Uses: Besides keeping Jeff Bezos company? To be honest, there aren’t that many compelling practical uses at the moment, but the researchers say these sorts of four-legged robots could one day be used to inspect underground tunnels or carry heavy loads on construction sites.

Deep Dive

Artificial intelligence

Yann LeCun
Yann LeCun

Yann LeCun has a bold new vision for the future of AI

One of the godfathers of deep learning pulls together old ideas to sketch out a fresh path for AI, but raises as many questions as he answers.

flower with textin multiple languages on the petals
flower with textin multiple languages on the petals

Inside a radical new project to democratize AI

A group of over 1,000 AI researchers has created a multilingual large language model bigger than GPT-3—and they’re giving it out for free.

screenshot from Gran Turismo
screenshot from Gran Turismo

Sony’s racing AI destroyed its human competitors by being nice (and fast)

What Gran Turismo Sophy learned on the racetrack could help shape the future of machines that can work alongside humans, or join us on the roads.

open source protein models concept
open source protein models concept

DeepMind has predicted the structure of almost every protein known to science

And it’s giving the data away for free, which could spur new scientific discoveries.

Stay connected

Illustration by Rose WongIllustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.