Robot vision – and comprehension of what the robot sees – is one of the major sticking points when it comes to household helper robots. But robots don’t have to be subject to the limitations of human senses – particularly if they can tap into technologies such as NFC and RFID.
The latter has been implemented by researchers at the Georgia Institute of Technology to help robots locate objects. To be more precise, they have used small ultra-high frequency RFID tags, stuck onto objects, which robots can then track in a room – even when the tag is hidden out of sight.
RFID alone, however, is not sufficient for item location.
“RFID doesn’t tell the robot where it is,” said biomedical engineering associate professor Charlie Kemp. “To actually find the object and get close to it, the robot has to be more clever.”
Kemp’s team fitted one of the Georgia Tech’s PR2 robots with articulated, directionally sensitive antennae (although not as cool as Robby‘s), and developed a search algorithm that improves the robot’s ability to locate and navigate towards tagged objects, differentiating each tag’s signature to avoid confusion.
The antennae work to engage the robot in a sort of “hotter or colder” style search. They receive a stronger RFID signal when they are pointed in the direction of an RFID tag, and also when they are closer to it; by navigating around a room and constantly moving its antennae, the robot is able to extrapolate when a signal is getting stronger and move towards it. And, because it is not locating the object in 3D space, the algorithm can remain relatively simple.
“The robot can use its mobility and our special behaviours to get close to a tag and oriented toward it,” said study co-author Travis Deyle, former Georgia Tech student, who worked on the project in Kemp’s laboratory as part of his doctoral degree.
“This could allow a robot to search for, grasp and deliver the right medication to the right person at the right time. RFID provides precise identification, so the risk of delivering the wrong medication is dramatically reduced. Creating a system that allows robots to accurately locate the correct tag is an important first step.”
The robot’s object-locating abilities were tested on several household objects: a medication bottle, a hair brush, a TV remote and a cell phone. Potentially, though, the robot could use unique RFID tags to correctly identify billions of individual objects without hitting a false positive.
“With a little modification of the objects in your home, a robot could quickly take inventory of your possessions and navigate to an object of your choosing,” Kemp said. “Are you looking for something? The robot will show you where it is.”
University of Washington professor Matt Reynolds also contributed to the project. You can read the full paper online on the Georgia Tech website (PDF).