What’s new: Google DeepMind has trained a robot to play table tennis at the equivalent of amateur-level competitive performance, the company has announced. It claims it’s the first time a robot has been taught to play a sport with humans at a human level.
How good is it? The system is far from perfect. Although the table tennis bot was able to beat all beginner-level human opponents it faced and 55% of those playing at amateur level, it lost all the games against advanced players. Still, it’s an impressive advance.
Why it matters: The research represents a step towards creating robots that can perform useful tasks skillfully and safely in real environments like homes and warehouses, which is a long-standing goal of the robotics community. Read the full story.
—Rhiannon Williams
This futuristic space habitat is designed to self-assemble in orbit
More people are traveling to space, but the International Space Station can only hold 11 people at a time. The Aurelia Institute, a nonprofit space architecture lab based in Cambridge, MA, has an approach that may help: a habitat that can be launched in compact stacks of flat tiles and self-assemble in orbit.
Building large space habitats is difficult, and dangerous. But the Aurelia Institute’s TESSERAE space habitat, which resembles a futuristic, one-story-tall soccer ball, could make it much easier. Read the full story.
—Sarah Ward