12.5 C
New York
Thursday, July 2, 2020
Home News This Google robot taught itself to walk, with no help whatsoever, in...

This Google robot taught itself to walk, with no help whatsoever, in two hours

Do you remember that scene in Walt Disney’s Bambi where the titular fawn learns to stand up and walk under its own power? It’s a charming vignette in the movie, showcasing a skill that plenty of baby animals — from pigs to giraffe to, yes, deer — pick up within minutes of their birth. Over the first few hours of life, these animals rapidly refine their motor skills until they have full control over their own locomotion. Humans, who learn to stand holding onto things at around seven months and who begin walking at 15 months, are hopelessly sluggish by comparison.

Guess what the latest task that robots have beaten us at? In a new study carried out by researchers at Google, engineers have taught a quadruped Minitaur robot to walk by, well, not really having to teach it much at all. Rather, they’ve used a a type of goal-oriented artificial intelligence to make a four-legged robot learn how to walk forward, backward, and turn left and right entirely on its own. It was able to successfully teach itself to do this on three different terrains, including flat ground, a soft mattress, and a doormat with crevices.

“Legged robots can have great mobility because legs are essential to navigate unpaved roads and places designed for humans,” Jie Tan, principle investigator on the project and Google’s head of locomotion efforts, told Digital Trends. “We are interested in enabling legged robots to navigate our diverse and complex real-world environments, but it is difficult to manually engineer robotic controllers that can handle such diversity and complexity. Therefore it is important that robots be able to learn by themselves. This work is exciting because this is an early demonstration that, with our system, a legged robot can successfully learn to walk on its own.”

Positive reinforcement

The technology at the root of this particular project is something called deep reinforcement learning, a specific approach to deep learning that’s inspired by behaviorist psychology and trial and error learning. Told to maximize a certain reward, software agents learn to take actions in an environment that will achieve those results in the most precise, efficient way possible. The power of reinforcement learning was famously demonstrated in 2013 when Google’s DeepMind released a paper showing how it had trained an A.I. to play classic Atari video games. This was achieved with no instruction other than the on-screen score and the approximately 30,000 pixels that made up each frame of the video games it was playing.

Video games, or at least simulations, are frequently used by robotics researchers, too. A simulation makes perfect sense in theory, since it allows roboticists to train their machine in a virtual world before going out into the real one. That saves robots from the inevitable pratfalls and wear-and-tear that it would undergo as it learns to carry out a specific task. As an analogy, imagine if all of your driving lessons were carried out using a driving simulator. The argument could be made that you would learn more quickly because you wouldn’t have to be so cautious about risking your physical safety or damaging your car (or someone else’s). You could also train more rapidly without having to wait for allocated lessons or for a licensed driver to be willing to take you out.

The problem with this is that, as anyone who has ever played a driving video game will know, it’s pretty darn hard to model the real world in a way that feels like, well, the real world. Instead, Google’s researchers began developing improved algorithms that allows their robot to learn more rapidly with fewer trials involved. Building on a previous piece of Google research published in 2018, their robot was able to learn to walk in just a couple of hours in this latest demonstration.

It’s also able to do this while emphasizing a more cautious, safer approach to learning, involving fewer falls. As a result, it minimizes the number of human interventions that need to be made to pick the robot up and dust it off every time it takes a tumble.

Building better robots

Learning to walk in two hours may not be quite deer levels of learning-to-walk efficiency, but it’s a far cry from engineers having to explicitly program how a robot is usually taught to maneuver. (And, as noted, it’s a whole lot better than human infants can manage in that kind of time frame!)

“Although many unsupervised learning or reinforcement learning algorithms have been demonstrated in simulation, applying them on real, legged robots turns out to be incredibly difficult,” Tan explained. “First, reinforcement learning is data-hungry, and collecting robot data is expensive. Our previous work has addressed this challenge. Second, training requires someone to spend a lot of time supervising the robot. If we need a person to monitor the robot and manually reset it every time it stumbles — hundreds or thousands of times — it’s going to take a lot of effort and a very long time to train the robot. The longer it takes, the more difficult it is to scale up the learning to many robots in many different environments.”

One day this research could help create more agile robots that are more rapidly able to adapt to a variety of terrains. “The potential applications are numerous,” Tan said. However, Tan stressed that this is “still early days, and there are many challenges that we still need to overcome.”

In keeping with the reinforcement learning theme, it’s certainly a reward that’s worth maximizing, though!

Latest

Nixplay Smart Photo Frame review

The Nixplay Smart Photo Frame, available in a variety of sizes, is a Wi-Fi digital picture frame that displays your favorite images. Similar to traditional picture frames you can hang it on a wall or prop it up on a table. Unlike the one on your grandmother’s wall, it can cycle through more than 2,000 pictures.This is the sort of product you’d gift to parents and grandparents as you can send photos or playlists directly to them. Additionally, it might be a good product for new parents, newlyweds, or college students who might want to keep an eye on things back home. It works just as well to give one of these to someone as it would be to receive on.There are a different sizes and finishes available so it ought to be no problem finding the right fit for your home. And because of its flexibility, you can move it to different rooms or environments without hassle.The 10.1-inch version features a 1280 x 800 HD image that’s bright, easy to see from a variety of angles, and works in both landscape and portrait orientation. As one might expect from a device like this in 2020, there is support for Google Assistant and Amazon Alexa.The built-in motion sensor is able to identify whether there are people in the room which means it automatically turns itself off.Configuration and SetupSetting up the Nixplay Frame includes creating an account, pairing your frame to it, and adding photos. Using the mobile app you can manually add photos, but we found it easier to manage it from the website.Once logged in, you can pair your social media accounts with their respective library or albums. That includes Google Photos, Facebook, Instagram, Dropbox, Flickr, and Verizon Cloud.It’s also in this dashboard where you can set up timers to turn on and off the frame. Additionally, you can shuffle the playlist, opt to display a clock, adjust the transitions between photos, and more.If you’re purchasing one of these for a family member or friend, you’ll be able to set it all up and essentially make it a turn-key gift. All you’ll have to do is set it on the right Wi-Fi network.We appreciate that you can make as many adjustments that you can, especially to keep things updated. There’s no need to insert a microSD card or plug into the frame. Anything done in the cloud is automatically updated.As for the Google Assistant stuff, it’s more or less just being able to turn the frame on and off using your voice. It’s handy, but not necessary. Amazon Alexa appears to have a little deeper integration with options to pull up specific playlists. 1 of 4 The viewing angles on the frame are really good and we found it to provide sharp color and high contrast. Some of the transitions do feel a tad dated, however, they are quick. Fortunately, you can opt for longer delays between changing and decide which transition you want.Where to BuyYou can learn more about the Nixplay Smart Photo Frame at the company’s official website. There, you’ll find it available to purchase for about $180. A limited time discount sees the company taking $27 off, bringing the total to just $153.There are also other sizes to choose from, ranging from 9.7-inches up to 15.6-inches. From the looks of it, there are often chances to save on your frame. Be it centered around a holiday or just an instant discount, it pays to look.

The best options for when you want Fast Pair headphones

Fast Pair is a technology that lets you quickly pair your Bluetooth headphones to your Android phone without having to

Shine bright with these fireworks-filled wallpapers!

"Look at the fireworks, look at the fireworks light up the night sky!!"Fireworks add an extra pop of excitement to