Robots can walk, talk, run a hotel … and are entirely stumped by a doorknob. Or a mailbox. Or a dirty bathtub—zzzzt, dead. Sure, the SpotMini, a doglike domestic helper from Boston Dynamics, can climb stairs, but it struggles to reliably hand over a can of soda. That’s why some roboticists think the field needs to flip its perspective. “There are two approaches to building robots,” says Maya Cakmak, a researcher at the University of Washington. “Make the robot more humanlike to handle the environment, or design the environment to make it a better fit for the robot.” Cakmak pursues the latter, and to do that, she studies so-called universal design—the ways in which buildings and products are constructed for older people or those with disabilities. Robot can’t handle the twisting staircase? Put in a ramp. As for that pesky doorknob? Make entryways motion-activated. If you want droids at your beck and call someday, start thinking about robo-fitting your digs now.

1. Wide-Open Floor Plan Any serious sans-­human housekeeping needs a wheeled robotic butler with arms, Cakmak says. That means fewer steps, plus hallways wide enough for U-turns. Oh, and hardwood floors. Thick carpeting slows a bot’s roll.

2. Visual Waypoints Factory robots work so fast in part because their world is highly structured—conveyor belt here, truck over there. So for your robo-home, create landmarks that anchor the bots in space—a promi­nent light fixture, say, that tells them, “You’re in the dining room.” (RFID tags will help bots locate smaller objects, like cleaning supplies.)

Now you can have items delivered to you wherever you are.

Microsoft today is unveiling new artificial intelligence technology that’s something of an artist – a “drawing bot.” The bot is capable of creating images from text descriptions of an object, but it also adds details to those images that weren’t included the text, indicating that the AI has a little imagination of its own, says Microsoft.

“If you go to Bing and you search for a bird, you get a bird picture. But here, the pictures are created by the computer, pixel by pixel, from scratch,” explained Xiaodong He, a principal researcher and research manager in the Deep Learning Technology Center at Microsoft’s research lab in Redmond, Washington, in Microsoft’s announcement. “These birds may not exist in the real world — they are just an aspect of our computer’s imagination of birds.”

The bot is able to generate a variety of images, researchers say, including everything from “ordinary pastoral scenes,” like those with grazing livestock, to the absurd – like “a floating double-decker bus.”