Korean Robotics Company Yujin Developing Food Delivery Robot
Food delivery robot created by South Korean robotics firm Yujin Robot.
Photo: Yujin Robot

Robots are good for all kinds of things, but almost all of those things (with a few exceptions) are not things that are intended to make the lives of lazy humans (on an individual basis) better. Like, immediately better. As in, "bring me a sandwich" better.

Yujin Robot, perhaps best known for (if you live in Asia) vacuums or (if you live in ROS) Turtlebot 2, is now testing out a food delivery robot that's safe enough, and affordable enough, to operate autonomously in care facilities.

Here's the rather unfulfilling video, at least for people who like seeing robots, you know, actually do stuff:

The GoCart system is clever enough to control a team of robots, autonomously sorting out which needs to go where, and when. It's probably most efficient, as the video points out, during fixed mealtimes where it can work out cooperative scheduling in advance, but by far the most exciting feature is the ability to order snacks on your smartphone. This is a unique capability that should really be added to the comparison chart below:

We're obviously missing a few details here, like detailed tech specs (although it looks like there's some sort of laser down there along with sonar and a Kinect-ish thing) as well as what's arguably most important, which is whether GoCart really is affordable for small facilities. The suggestion is that it solves the "robots are too expensive" problem, but calling something affordable without providing even a suggestion of a price never fails to make us suspicious. It's also not quite clear from the information available how much infrastructure is required to get one or more GoCarts up and running.

Now, while GoCart certainly isn't competition for Savioke's SaviOne/Botlr, it's cool to see that there are several of these relatively "affordable" delivery robots out on the market with the ability to wander around on their own in semi-structured environments amongst humans that may not be entirely comfortable with them. Technology has progressed far enough to make this possible, but more importantly, confidence in the technology has progressed far enough to make this possible, too.

GoCart will start testing this October in a retirement community somewhere in the northeastern United States, and a facility in southern Sweden.

[ Yujin GoCart ]

The Conversation (0)

How the U.S. Army Is Turning Robots Into Team Players

Engineers battle the limits of deep learning for battlefield bots

11 min read
Robot with threads near a fallen branch

RoMan, the Army Research Laboratory's robotic manipulator, considers the best way to grasp and move a tree branch at the Adelphi Laboratory Center, in Maryland.

Evan Ackerman

This article is part of our special report on AI, “The Great AI Reckoning.

"I should probably not be standing this close," I think to myself, as the robot slowly approaches a large tree branch on the floor in front of me. It's not the size of the branch that makes me nervous—it's that the robot is operating autonomously, and that while I know what it's supposed to do, I'm not entirely sure what it will do. If everything works the way the roboticists at the U.S. Army Research Laboratory (ARL) in Adelphi, Md., expect, the robot will identify the branch, grasp it, and drag it out of the way. These folks know what they're doing, but I've spent enough time around robots that I take a small step backwards anyway.

The robot, named RoMan, for Robotic Manipulator, is about the size of a large lawn mower, with a tracked base that helps it handle most kinds of terrain. At the front, it has a squat torso equipped with cameras and depth sensors, as well as a pair of arms that were harvested from a prototype disaster-response robot originally developed at NASA's Jet Propulsion Laboratory for a DARPA robotics competition. RoMan's job today is roadway clearing, a multistep task that ARL wants the robot to complete as autonomously as possible. Instead of instructing the robot to grasp specific objects in specific ways and move them to specific places, the operators tell RoMan to "go clear a path." It's then up to the robot to make all the decisions necessary to achieve that objective.

Keep Reading ↓ Show less