The Future is Closer Than We May Think
For those of you old enough to remember Hanna Barbera’s classic cartoon The Jetsons, how many times have you wished you had a “Rosie” to cook your dinner or clean your dishes? “She” would have made this past Thanksgiving much more effortless!
The future envisioned by the creators of The Jetsons certainly had a lot more fiction to it than we’ll ever realize. But, for the idea of the “personal robot” represented by Rosie, the future is closer than we may think, and its name is “Ellie” (or EL-E to be exact).
A team of researchers -- Charles Kemp, Travis Deyle and Hai Nguyen from Georgia Tech and Matthew S. Reynolds from Duke University -- is focused on applying personal robotics within healthcare and has developed several prototypes. The challenge of personal robotics is how to make the machine perceive, manipulate and understand the world around it so it can interact with humans and objects to perform specific tasks – like loading a dishwasher or delivering medicine.
Enter passive UHF RFID. Humans and/or objects can be tagged with passive UHF RFID labels, providing the interface through which a personal robot can interact to carry out its tasks. As the Georgia Tech/Duke team explains on its research page:
Passive Ultra-High Frequency (UHF) RFID tags are well matched to robots' needs. Unlike low-frequency (LF) and high-frequency (HF) RFID tags, passive UHF RFID tags are readable from across a room, enabling a mobile robot to efficiently discover and locate them. Because they don't have onboard batteries to wear out, their lifetime is virtually unlimited. And unlike bar codes and other visual tags, RFID tags are readable when they're visually occluded. For less than $0.25 per tag, users can apply self-adhesive UHF RFID tags throughout their home.
EL-E, one of the prototypes built by the research team, uses ThingMagic M5e UHF RFID reader modules to form the core of the robot’s RFID sensors. The Mercury M5e is embedded in two ‘antennas’ on the robot – one for reading tags up to approximately 6 meters and other for reading the same tags within 30 centimeters of the robot’s hand. The image above illustrates this.
The read range and reliability delivered by the ThingMagic M5e is important for this particular application. The robot needs to be able to have as long a range as possible to detect a label from across a large room, but the finger-mounted short-range antenna is just as important to manipulate a tagged object, such as handing a bottle of medicine to a patient.
While it may be difficult to envision seeing a machine like the prototype illustrated above in your hospital room or home, one way to do so is to consider how the Georgia Tech research team partnered with Willow Garage, a California company that builds robots for research. Specifically, the team built the EL-E RFID application using Willow Garage’s PR2 robot as the “infrastructure”. The partnership was featured this past October on CNN’s The Big I show. The video here shows Charles Kemp and Travis Deyle from the research team demonstrating it for CNN’s Ali Velshi.
When you watch the PR2 in action with the Georgia Tech/Duke team’s application driving it, you can start to think about eventually having your own “Rosie” to make your lives easier. Now all this robot needs is a New Jersey accent.