IMUs supported include the recently launched LSM6DSO and LSM6DSOX 6-axis modules.
FSM logic allows the running of gesture and motion-recognition algorithms directly in the sensor. MLC implements machine-learning classifiers for real-time always-on motion and vibration pattern recognition.
Unico GUI (STSW-MKI109L for Linux, STSW-MKI109M for Mac OSX, and STSW-MKI109W for Windows) allows configuration of the module’s internal registers and embedded FSM and MLC logic. This configuration simplifies the creation of motion-recognition algorithms. The GUI also makes it easier to combine the module’s accelerometer and gyroscope data with inputs from external sensors for more sophisticated context-sensing capabilities.
The FSM and MLC act as an embedded, low-power engine for gesture and motion recognition — allowing user-interface functions and context-aware apps to continue running while the main processor sleeps. LSM6DSO offers logic for up to 16 independent state machines, each generating a hardware interrupt activated by a specific motion pattern, while the LSM6DSOX also contains the logic to implement multiple-stage decision trees for machine-learning classification.