Autonomous boats might soon do a favor for people who have no intention of charting a course. Researchers at MIT and AMS Institute have developed a new version of their 'Roboat' that can identify and latch on to fellow robots to form different structures, whether it's a foot bridge, a garbage collector or a stage for a concert. The boats use cameras, lidar and computer vision algorithms to look for fellow bots with QR-like tags (to help determine their relative position), and then position themselves for docking on command. They also know to try again if there's a botched attempt.
The docking mechanism itself is a ball-and-socket system that uses a laser to tell when the ball is inside, locking the arriving robot into place. The socket, meanwhile, is a funnel that gives the boats leeway to bounce around in the water.
There's no guarantee you'll see production versions of this tech. Roboat has been in development for several years. However, there's a clear roadmap for the future. A new funnel could give the bots more control for towing other objects through canals, while the tags themselves could be displayed on an LCD to issue instructions to multiple boats from one lead automaton. And like you'd guess, the basic principles involved aren't limited to the water -- this could help with everything from docking spacecraft to recharging your robot vacuum.