STMicroelectronics’ ASM330LHHX inertial measurement unit (IMU) moves smart driving another step closer to high levels of automation with its machine-learning (ML) core. The ML core enables fast real-time response and sophisticated functions with low system-power demand.
Leveraging ST’s micro-electro-mechanical systems (MEMS) technology, the automotive-qualified ASM330LHHX houses a 3-axis accelerometer and 3-axis gyroscope in a 2.5 x 3 x 0.83mm outline. The 6-axis module provides movement and attitude sensing for functions including vehicle positioning and digital stabilization.
The ML core, a hardwired processing engine, runs AI algorithms directly on the sensor, ensuring extremely low latency between sensing an event and the vehicle’s response. This enables sophisticated real-time performance that demands far lower system energy and computing power than a solution embedded on an application processor or cloud-based AI.
Demonstration boards and free software example libraries are available to simplify application development. Functions available include vehicle-stationary detection, attitude and heading reference, altitude estimation, car-tow detection, and crash detection.
The ASM330LHHX has two operating modes including low-power mode for running always-on applications like telematics, anti-theft systems, motion-activated functions, and vibration monitoring and compensation. When operated in low-power mode, the current is less than 800µA with both the accelerometer and gyroscope running.
There’s also a high-performance mode for applications that demand the highest accuracy and lowest latency, including precise positioning, vehicle-to-everything (V2X) communication, and impact detection and crash reconstruction.
ST’s proven MEMS fabrication processes ensure excellent sensor stability and low noise, seen in low measured Allan variance (AVAR) for both the gyroscope and accelerometer. The module maintains consistent high accuracy over the extended operating temperature range, -40° to 105° C.
Filed Under: Automotive, Components, Machine Learning, News