The video below shows (among other things) a humanoid robot called Atlas stumbling its way through a patch of forest. It’s caused quite a stir online, but there’s no need to panic.
Truth be told, the clip is a bit eerie. But it’s primarily a great example of the potential value of dynamic balance—that is, keeping oneself balanced through motion—for allowing legged robots to cover all sorts of terrain.
The video was presented earlier this month by the company’s founder, Marc Raibert, at a conference called Fab 11, held in Cambridge, Massachusetts, and Boston. I spoke briefly to Raibert about the video, and he explained that it was actually shot over a year ago using a previous version of Atlas. The latest version carries a battery on its back, so it does not require a power cable.
Several Atlas robots also took part in a contest held in June by the Defense Advanced Research Projects Agency (DARPA), where they had to navigate a complex obstacle course involving opening doors, operating power tools, and climbing over rubble (see “A Transformer Wins DARPA’s $2 Million Robotics Challenge”).
It’s also noticeable how different the motion of the Atlas is in the woodland clip to the ones involved in the DARPA challenge. That’s because those robots used much more conservative control software to avoid falling over and damaging themselves (see “Why Humans and Robots Struggled with DARPA’s Challenge”). As the clip of Atlas shows, when you throw caution to the wind, robots are already capable of joining us for a walk in the woods.
Meta has built a massive new language AI—and it’s giving it away for free
Facebook’s parent company is inviting researchers to pore over and pick apart the flaws in its version of GPT-3
The gene-edited pig heart given to a dying patient was infected with a pig virus
The first transplant of a genetically-modified pig heart into a human may have ended prematurely because of a well-known—and avoidable—risk.
Saudi Arabia plans to spend $1 billion a year discovering treatments to slow aging
The oil kingdom fears that its population is aging at an accelerated rate and hopes to test drugs to reverse the problem. First up might be the diabetes drug metformin.
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.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.