Menu
Meet 'Galileo,' a new AI system from MIT that could help robots help us during disasters

Meet 'Galileo,' a new AI system from MIT that could help robots help us during disasters

Deep learning helps the system predict how physical objects will collide and interact

Computers can be taught to understand many things about the world, but when it comes to predicting what will happen when two objects collide, there's just nothing like real-world experience.

That's where Galileo comes in. Developed by MIT's Computer Science and Artificial Intelligence Lab (CSAIL), the new computational model has proven to be just as accurate as humans are at predicting how real-world objects move and interact.

Ultimately, it could help robots predict events in disaster situations and help humans avoid harm.

Humans learn from their earliest days -- often through bumps, bruises and painful experience -- how physical objects interact. Computers, however, don't have the benefit of that early training.

To make up for that lack, CSAIL researchers created Galileo, a system that can train itself using a combination of real-world videos and a 3D physics engine to infer the physical properties of objects and predict the outcome of a variety of physical events.

To train Galileo, the researchers used a set of 150 videos depicting physical events involving objects made from 15 different materials, including cardboard, foam, metal and rubber. Equipped with that training, the model could generate a data set of objects and their various physical properties.

They then fed the model information from Bullet, a 3D physics engine often used to create special effects for movies and video games. By taking the key elements of a given scene and then physically simulating it forward in time, Bullet served as a "reality check" against Galileo’s hypotheses, MIT said.

Finally, the team developed deep-learning algorithms that allow the model to teach itself to further improve its predictions.

To test Galileo’s predictive powers, the team pitted it against human subjects to predict a series of simulations, one of which can be seen in an online demo.

In one simulation, for example, users first see a collision involving a 20-degree inclined ramp; they're then shown the first frame of a video with a 10-degree ramp and asked to predict whether the object will slide down the surface.

"Interestingly, both the computer model and human subjects perform this task at chance and have a bias at saying that the object will move,” said Ilker Yildirim, who was lead author alongside CSAIL PhD student Jiajun Wu on a paper describing the research. "This suggests not only that humans and computers make similar errors, but provides further evidence that human scene understanding can be best described as probabilistic simulation.”

The paper was presented last month at the Conference on Neural Information Processing Systems in Montreal, MIT announced on Monday.

Eventually, the researchers hope to extend the work to more complex scenarios, with an eye toward applications in robotics and artificial intelligence.

“Imagine a robot that can readily adapt to an extreme physical event like a tornado or an earthquake,” said coauthor Joseph Lim. “Ultimately, our goal is to create flexible models that can assist humans in settings like that, where there is significant uncertainty.”

Follow Us

Join the New Zealand Reseller News newsletter!

Error: Please check your email address.

Featured

Slideshows

Educating from the epicentre - Why distributors are the pulse checkers of the channel

Educating from the epicentre - Why distributors are the pulse checkers of the channel

​As the channel changes and industry voices deepen, the need for clarity and insight heightens. Market misconceptions talk of an “under pressure” distribution space, with competitors in that fateful “race for relevance” across New Zealand. Amidst the cliched assumptions however, distribution is once again showing its strength, as a force to be listened to, rather than questioned. Traditionally, the role was born out of a need for vendors and resellers to find one another, acting as a bridge between the testing lab and the marketplace. Yet despite new technologies and business approaches shaking the channel to its very core, distributors remain tied to the epicentre - providing the voice of reason amidst a seismic industry shift. In looking across both sides of the vendor and partner fences, the middle concept of the three-tier chain remains centrally placed to understand the metrics of two differing worlds, as the continual pulse checkers of the local channel. This exclusive Reseller News Roundtable, in association with Dicker Data and rhipe, examined the pivotal role of distribution in understanding the health of the channel, educating from the epicentre as the market transforms at a rapid rate.

Educating from the epicentre - Why distributors are the pulse checkers of the channel
Kiwi channel reunites as After Hours kicks off 2017

Kiwi channel reunites as After Hours kicks off 2017

After Hours made a welcome return to the channel social calendar last night, with a bumper crowd of distributors, vendors and resellers descending on The Jefferson in Auckland to kickstart 2017. Photos by Maria Stefina.

Kiwi channel reunites as After Hours kicks off 2017
Arrow exclusively introduces Tenable Network Security to A/NZ channel

Arrow exclusively introduces Tenable Network Security to A/NZ channel

Arrow Electronics introduced Tenable Network Security to local resellers in Sydney last week, officially launching the distributor's latest security partnership across Australia and New Zealand. Representing the first direct distribution agreement locally for Tenable specifically, the deal sees Arrow deliver security solutions directly to mid-market and enterprise channel partners on both sides of the Tasman.

Arrow exclusively introduces Tenable Network Security to A/NZ channel
Show Comments