Ambarella’s centralized 4D imaging radar with Oculii technology provides a flexible and high-performance perception architecture that enables system integrators to future-proof their radar designs.
Ambarella’s centrally processed 4D imaging radar architecture will improve the safety and driving flexibility of autonomous vehicles. This is the world’s first centralized 4D imaging radar architecture, which allows for central processing of raw radar data and deep, low-level integration with other sensor inputs—including cameras, lidar and ultrasonic. This architecture enables higher performance imaging radar systems and new ADAS/AD features while simultaneously optimizing the cost of radar sense. The 4D imaging radar architecture is suitable for use in level 2+ to level 5 autonomous vehicles, as well as autonomous mobile robots (AMRs) and automated guided vehicle (AGV) robots.
“No other semiconductor and software company has advanced in-house capabilities for radar and camera technologies, as well as AI processing,” said Fermi Wang, President and CEO of Ambarella. “This expertise has allowed us to create an unprecedented centralized architecture that combines our unique Oculii radar algorithms with CV3’s industry-leading domain control performance per watt to effectively new levels of AI vision, sensor integration and path planning will be available to help realize the full potential of ADAS, autonomous driving and robotics.
The data sets of other competing 4D imaging radar technologies are too large to be transported and processed centrally. They produce several terabits per second of data per module while consuming more than 20 watts of power per radar module, due to the thousands of MIMO antennas used in each module to provide the high angular resolution required for 4D imaging radar. . That’s multiplied by the six or more radar modules needed to cover a car, making central processing impractical for other radar technologies, which must process radar data in the thousands. antennas.
Oculii technology reduces the antenna array for each processor-less MMIC radar head in this new architecture to 6 transmit x 8 receive. They achieved this by applying AI software to dynamically adapt radar waveforms generated using existing monolithic microwave integrated circuit (MMIC) devices, and using AI sparsification to create virtual antennas. Target applications for the new centralized radar architecture include ADAS and level 2+ to level 5 autonomous vehicles, as well as autonomous mobile robots (AMRs) and automated guided vehicle (AGV) robots.