RFID tags help robots locate and grab moving objects in milliseconds

[The AchieVer]

RFID tags help robots locate and grab moving objects in milliseconds

MIT Media Lab researchers are using RFID tags to make it easier to locate objects.

 

 

A group of researchers at the Massachusetts Institute of Technology (MIT) have developed a system that uses radio-frequency identification (RFID) tags to locate moving, tagged objects within milliseconds. 

The system, called TurboTrack, could improve the efficiency of robots working on manufacturing, as well as carrying out drone search-and-rescue missions, with the the system being able to locate objects within 7.5 milliseconds on average and with errors of less than 1 centimetre. 

TurboTrack uses a reader to send wireless signals to RFID tags that can be applied to any object, which is then rebounded back to the reader. The system uses a "space-time super-resolution" algorithm, MIT says, which sifts through the reflected signals to locate the RFID tag's response.

"As the tag moves, its signal angle slightly alters -- a change that also corresponds to a certain location ... by constantly comparing that changing distance measurement to all other distance measurements from other signals, it can find the tag in a three-dimensional space. This all happens in a fraction of a second," MIT said. 

 

According to MIT researchers, the RFID system is better suited than computer vision technologies for performing robotic tasks within cluttered environments or where vision is limited, such as carrying out drone search-and-rescue missions. This is because radio frequency signals can identify targets without visualisation, as well as through clutter and walls. 

"Nanodrones currently use computer vision and methods to stitch together captured images for localisation purposes. These drones often get confused in chaotic areas, lose each other behind walls, and can't uniquely identify each other. This all limits their ability to, say, spread out over an area and collaborate to search for a missing person." 

 

During tests of the system, the researchers tracked RFID-equipped nanodrones during docking, maneuvering, and flying. They also performed a separate test where they attached one RFID tag to a cap and another to a bottle. A robotic arm then located the cap and placed it onto the bottle, which was held by another robotic arm. For both tests, TurboTrack was either on par with or faster than traditional computer vision systems, or able to work in situations where computer vision had failed, according to MIT. 
 
The development of RFID tag technology has been appealing for developers due to it being cheap, battery-free, and washable, with TurboTrack RFID tags costing only 3 cents to make, MIT Media Lab assistant professor Fadel Adib said.  

 

MIT has also explored the use of RFID tags in other applications, developing a low-cost sensor in June that can monitor and improve human health. 

 

In a paper describing the research [PDF], the team suggested that RFID tagging could become the base of vast, sensor-driven networks, taught to detect not only health-related changes in a body, but also chemicals such as carbon monoxide or ammonia.

Meanwhile, researchers at Carnegie Mellon University have figured out how RFID tags can be used for things such as controlling virtual avatars or reminding slouching users to sit up straight.

 

"By attaching these paper-like RFID tags to clothing, we were able to demonstrate millimeter accuracy in skeletal tracking," said Haojian Jin, a PhD student in CMU's Human-Computer Interaction Institute (HCII).

 

 

Source