Collin Arocho
14 May

Imec has added machine learning capabilities to its family of radar technology. The research institution from Leuven is using this week’s Future Summits 2019 event to demonstrate its compact and highly sensitive 140 GHz MIMO (multiple-input, multiple-output) radar system. It’s set up for gesture recognition, supporting a more intuitive man-machine interaction.

One of the keys for this radar-on-chip prototype system is its compact size. It’s small enough it could easily be integrated invisibly on just about any device, from smartwatches to smartphones or laptops. Another distinguishing factor is its high radar performance – in terms of resolution and motion sensitivity. The system operates with a range of up to 10 meters, with 15 mm range resolution and 10 GHz of RF bandwidth. Multiple antenna paths are incorporated to enable a complete (virtual) 1×4 MIMO configuration to achieve angular target separation. The transceiver chip features on-chip antennas, integrated in 28nm bulk CMOS technology, ensuring a low-cost solution at high volume production.

Credit: Imec

With the added machine learning capabilities, the radar is able to detect and classify small motions based on Doppler information. “This opens new opportunities, for example, enabling gesture recognition for intuitive man-machine interactions,” says Barend van Liempd, R&D manager at Imec. “Think about the AR/VR space, where the new radar can support intuitive interaction with virtual objects. Gesture recognition can potentially also enable intuitive device control – complementary to existing interfaces such as voice control or smart touchscreens.”

Aside from gesture recognition, Imec sees several other applications in the fields of medicine and safety. The ultra-fine resolution and high radio frequency allow the detection of micro-skin movements. This means that measurements of vital signs can be done with high precision. Additionally, these features make the device an excellent candidate for in-car vital sign monitoring systems, enabling non-contact tracking of the driver’s state, ie detection of falling asleep or abnormal stress levels, or possibly to prevent accidents due to acute health hazards, like heart or epilepsy attacks.