STMicroelectronics — LIS2DUX12 and LIS2DUXS12 Accelerometers

Two new accelerometers from STMicroelectronics feature advanced processing engines which extend the sensor’s autonomy, enabling the host system to respond more quickly to external events while lowering power consumption. 

The LIS2DUX12 and LIS2DUXS12 offer new programmable capabilities including a machine-learning core (MLC), advanced finite state machine (FSM), and an enhanced pedometer. An anti-aliasing filter for high accuracy at low sampling frequencies improves the performance of applications such as gesture detection while having a negligible effect on power consumption. 

The integrated MLC in the LIS2DUX12 and LIS2DUXS12 enables artificial intelligence (AI) algorithms to perform reliable activity detection, while the FSM enhances movement recognition. Together, they enable autonomous processing in the sensor, offloading the burden of data processing from the host. This has the effect of lowering power consumption and producing faster system responses.  

In addition, by deploying an adaptive self-configuration capability, the accelerometers adjust their own settings, such as measurement range and frequency, autonomously to improve performance. 

The LIS2DUXS12 features ST’s Qvar® channel, which makes the sensor aware of changes in the ambient electrostatic environment. This capability lets developers add value to applications such as user-interface control and liquid detection. In user-interface applications, the Qvar channel combined with an acceleration signal removes the potential for false positive detection in two-tap and multi-tap events. 

The new accelerometers are supported by the ST MEMS GitHub model zoo, which facilitates the deployment of code for recognizing complex gestures, asset tracking, and many other use cases. 

A third, entry-level new accelerometer, the LIS2DU12, is also available for less demanding applications.