Hitachi's EMIEW Robot Learns to Navigate Around the Office

The little robot that could, now smarter and safer

2 min read
Hitachi's EMIEW Robot Learns to Navigate Around the Office
Photo: Hitachi

First unveiled in 2007, Hitachi's adorable little service robot EMIEW 2 has been gradually improving over the years. Standing 80 centimeters tall and weighing 14 kilograms, the robot is rather unusual in that it moves on a combination of legs and wheels, a system that works a bit like roller skates. Recently Hitachi announced that the robot's software is able to understand its environment better than before, allowing it to mingle more harmoniously among workers in busy settings like offices and hospitals.

Photo: Hitachi
Hitachi researchers Junichi Tamamoto (left) and Ryosuke Nakamura, who worked on the team that developed EMIEW.

Previously, EMIEW 2 (Excellent Mobility and Interactive Existence as Workmate) used digital maps pre-stored in its memory to drive around rooms, corridors, and other spaces. And to avoid collisions, it relied on its sensors to detect people and obstacles in real-time, automatically changing direction and reducing its speed (from a maximum of 6 km/h). But Hitachi engineers felt that, even with its cameras and a laser range finder, the robot needed to be more aware of its environment in order to prevent accidents.

Now EMIEW 2 still relies on maps of its surroundings, but its navigation software has a new feature: It uses designated zones that make the robot change its speed and direction. For example, if people frequently pop out of a corner unexpectedly, the robot knows it should slow down and alter its path upon approach (pictured below). Or if a door is never opened, the robot knows it can speed on by. And if necessary, the robot can avoid high traffic areas altogether, preventing it from becoming a nuisance to workers. The software identifies potential "hotspots" based on previously recorded activity between the robot and its environment and updates itself automatically, learning where it needs to make adjustments to its normal navigation paths.

Photo: Hitachi
Clockwise from top left: EMIEW 2 automatically adjusts its path as it approaches a corner, ensuring it won't bump on anyone walking by.

Besides delivering refreshments or locating and fetching objects for busy office workers, Hitachi suggests the robot's new mapping feature could expand its repertoire to guided tours or guard duty. The company hasn't said when it plans to make EMIEW commercially available, but if it needs to do some more tests in a different setting, IEEE Spectrum editors would welcome the cool little robot as a coworker anytime.

[ Hitachi ] via [ Asahi ]

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
LightGreen

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