NXP Semiconductors has unveiled its third-generation S32R47 imaging radar processor in 16nm FinFET technology, delivering up to 2x processing performance in the radar MPU, in a 38% smaller IC footprint than its previous generation. It also includes AI/ML support for features like enhanced direction of arrival (DoA) processing and object classification.
In combination with NXP’s mmWave radar transceivers, power management and in-vehicle networking solutions, the S32R47 family meets functional safety ASIL ISO 26262 ASIL B(D) requirements.
Imaging radar leverages richer point cloud data for more detailed modeling of the environment. This is a key enabler for AI-based perception systems that allow for assisted and autonomous driving.
The S32R47 integrates a high-performance multicore radar processing system, allowing denser point cloud output and enhanced algorithms that enable next-generation ADAS systems. This aims to better separate objects, improve detection reliability and accurately classify objects such as vulnerable road users or lost cargo.
According to Yole Intelligence’s Status of the Radar Industry 2024 report, by 2029 approximately 40% of vehicles entering the road will be passenger cars with driving automation Level 2+ (L2+)/Level 3 (L3), with an increasing number of vehicles with Level 4 (L4).
“The S32R47 can efficiently process three times, or more, antenna channels in real time than today’s production solutions,” said Meindert van den Beld, senior vice president and general manager for radar and ADAS at NXP. “It enables improved imaging radar resolution, sensitivity and dynamic range – required by demanding autonomous driving use cases – while still meeting the stringent power and system cost targets set by OEMs for volume production.”