The development uses RFID tags to enable robots to focus in on targets, based on localization technology. Radio-frequency identification (RFID) uses electromagnetic fields to automatically identify and track tags attached to objects.
The RIFD method developed is called TurboTrack, and it is seen as a superior process to computer vision, which is typically used to help robots to assess their nearby environment. The system mixes a standard RFID reader with an additional “helper” component, which is used to localize radio frequency signals. The helper signal generates a wideband signal comprising multiple frequencies, building on a modulation scheme used in wireless communication. This is termed orthogonal frequency-division multiplexing, a method of encoding digital data on multiple carrier frequencies.
The use of RIFD enables robots to engage in collaborative activities and to achieve new levels of precision. An example of collaborative is with robots working on packaging and assembly.
As well as assisting retail, especially the e-commerce, the technology could assist with robotic manufacturing (socially the development of autonomous cars); collaborative drones, as well as other applications. With the drone application, the technology could allow swarms of drones to carry out search-and-rescue missions. This type of drone application often uses nanodrones, and a weakness with current drone technology is that such drones can become confused in bust or built-up areas. The technology should be able to reduce this confusion and enable a more coordinated drone response.
With precision, tests revealed that robots equipped with the RIFD technology are capable of locating tagged objects within 7.5 milliseconds, on average. This was with an error of less than a centimeter.
According to lead researcher, Fadel Adib: “If you use RF signals for tasks typically done using computer vision, not only do you enable robots to do human things, but you can also enable them to do superhuman thing.”
He adds: “And you can do it in a scalable way, because these RFID tags are only 3 cents each.”
The technology has been presented to the USENIX Symposium on Networked Systems Design and Implementation, which took place in Boston, U.S., between February 26–28, 2019.
