Imec has combined advanced machine learning algorithms and innovations in chip design to extend its secure proximity portfolio with next-generation high-precision and low-power ultra wideband technology.
Ultra wideband technology is perfectly suited to support a variety of high accuracy and secure wireless ranging use-cases.
“Using machine learning, we created smart anchor selection algorithms that detect the (non) line-of-sight between UWB anchors and the mobile devices that are being tracked. Building on that knowledge, the ranging quality is estimated, and ranging errors are corrected. Since our approach also comes with machine learning enabled features that enable adaptive tuning of the network’s physical layer parameters, the right steps can then be initiated to mitigate those ranging errors – for instance by tuning the anchors’ radios,” explained Professor Eli De Poorter from IDLab.
Think of the ‘smart lock’ solutions commonly used in automotive – automatically unlocking a car’s doors as its owner approaches, while locking the car when the owner moves away.
While UWB is inherently more difficult to compromise than some alternatives, its potential has largely remained untapped because of its higher power consumption and larger footprint.
The innovations imec introduces today mark an important step to unlocking the technology’s full potential.
More details below from the press release.