The radar 140GHz operates up to a range of 10m, with 15mm range resolution and 10GHz of RF bandwidth. Multiple antenna paths are incorporated to enable a complete (virtual) 1x4 MIMO configuration to achieve angular target separation. The transceiver chip features on-chip antennas, and are integrated in 28nm bulk CMOS technology, ensuring a low-cost solution at high volume production.
By adding machine learning capabilities, imec has also demonstrated the radar’s capability to detect and classify small motions based on Doppler information.
“This opens new opportunities, for example, enabling gesture recognition for intuitive man-machine interactions”, explains 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 touch screens.”
Being insensitive to lighting conditions and preserving privacy (a radar can so far not recognize humans), a radar solution has particular advantages over other types of motion sensors, for example time-of-flight-based infrared cameras. And, being extremely compact, the 140GHz radar system can be integrated invisibly in almost every device, such as laptops, smartphones or screen bezels.
Imec has developed a specific machine learning algorithm based on a multi-layer neural network including an LSTM layer and using supervised learning to train the inference model by using in-house labelled recordings of more than 25 people, including several captures for each of 7 different gestures. Against the experimental dataset, the model classifies the recorded 7 gestures and predicts the right gesture at least 94% of the time.