The FSM logic lets users run gesture and motion-recognition algorithms directly in the sensor for always-on convenience and low power consumption. The MLC implements machine-learning classifiers for real-time always-on motion and vibration pattern recognition.

With Unico GUI (STSW-MKI109L for Linux, STSW-MKI109M for Mac OSX, and STSW-MKI109W for Windows machines) to configure the module’s internal registers and embedded FSM and MLC logic, users can quickly and easily create their own motion-recognition algorithms. The GUI also makes light work of combining the module’s accelerometer and gyroscope data with inputs from additional external sensors, such as a magnetometer, for even more sophisticated context-sensing capabilities.

When used in smartphones, wearables, or industrial devices, the FSM and MLC -- as an embedded, low-power engine for gesture and motion recognition -- allow user-interface functions and context-aware apps to continue running while the main processor sleeps to maximize battery runtime.

The LSM6DSO contains logic for up to 16 independent state machines, each generating a hardware interrupt activated by a specific motion pattern, while the LSM6DSOX contains also the logic to implement multiple-stage decision trees for machine-learning classification.