The LSM6DSOX from STMicroelectronics is an Inertial Measurement Unit (IMU) which features a three-axis digital accelerometer and a three-axis digital gyroscope. It offers always-on low-power features for use in small, battery-powered activity trackers.
Building on the high-performance platform of the earlier LSM6DSO, the LSM6DSOX adds a machine learning core, enabling developers to implement software through which the device can classify motion data based on known patterns.
The machine learning processing capability allows the designer to implement motion-detection algorithms for functions such as fitness logging, wellness monitoring, personal navigation and fall detection on the sensor rather than on an application processor.
This reduces power consumption and latency in motion-based applications.
The machine learning processing capability uses decision-tree logic. The LSM6DSOX can be configured to run up to eight decision trees simultaneously and independently.
The machine-learning core works in conjunction with the integrated finite-state machine logic to perform recognition of motion patterns or to detect vibration. Designers creating activity-tracking products with the LSM6DSOX can train the core for classification using Weka, an open-source PC-based application, or other tools. They can generate settings and limits from sample data such as acceleration, speed and magnetic angle that characterize the types of movements to be detected.
The auxiliary output interface and configuration options also simplify use in optical image stabilisation and when closing fast control loops.
The LSM6DSOX is pin-compatible with other devices in ST’s six-axis IMU family, such as the LSM6DSO, LSM6DSL and LSM6DSR.
Features
| Applications
|
