STMicroelectronics's first AI enhanced intelligent accelerometer

     STMicroelectronics has introduced three accelerometers with built-in advanced processing engines that improve the autonomous performance of the sensors, allowing the system to respond faster to external events while reducing power consumption.LIS2DUX12 and LIS2DUXS12 adopt the third-generation MEMS manufacturing process of Italian semiconductor, adding programmable features, including machine learning core (MLC), advanced finite state machine (FSM), and enhanced pedometer.

     Another entry-level accelerometer, the LIS2DU12, can be used in less demanding applications. All three products feature the latest industry standard I3C interface, universal digital capabilities for detecting events, and anti-aliasing filters with high accuracy at low sampling frequencies, enabling accurate gesture detection with negligible power consumption.

     LIS2DUX12 and LIS2DUXS12 integrate MLC to enable artificial intelligence (AI) algorithms to reliably detect human movements, while FSM further enhances activity recognition performance. The two functions complement each other, enabling the sensor to process data independently, reducing the interaction and data processing workload between the main processor and the sensor, significantly reducing power consumption, and improving the system response speed. In addition, by deploying the Adaptive Self-configuration (ASC) function, the accelerometer can independently adjust its own Settings, such as range and frequency, to further optimize measurement performance and take full advantage of every milliamperage of power consumption.

     LIS2DUXS12 also has unique Qvar induction channel, which can sense changes in the surrounding electrostatic environment and provide presence detection and proximity detection functions. This feature enables developers to increase the value of biometric sensing applications such as user interface controls, fluid detection, heart rate monitors, and more. In user interface applications, Qvar® is combined with acceleration signals to eliminate the potential for false detection in two-click and multiple-click events.

     The new smart accelerometer provides context-aware capabilities for advanced wearables, true wireless stereo (TWS) speakers and headsets, smartphones, hearing AIDS, game controllers, smartwatches, asset trackers, robots, and iot devices. These three products all adopt the latest ultra-low power architecture of STMicroelectronics. Combining the inherent ultra-low power technology with anti-aliasing filter, the application performance can be improved and the noise in the signal can be eliminated. Users can obtain ready-made MLC and FSM algorithms through STMicro's MEMS GitHub model library to realize complex gesture detection, asset tracking and other multi-use cases.

     With these enhancements, LIS2DUX12 and LIS2DUXS12 enable the next generation of "onlife" applications to intuitively and seamlessly support everyday activities, always on, always aware, and constantly in sync with user needs. The new products expand stmicroelectronics' family of AI-enhanced MEMS sensors, which include the Inertial Measurement Unit (IMU) launched in 2019.