MEMS accelerometers come with AI built-in

MEMS accelerometers come with AI built-in

New Products |
By Peter Clarke

STMicroelectronics is offering three tri-axis accelerometers with processing engines built-in to extend sensor autonomy. These include a machine learning core.

The addition of a finite-state-machine and software programmability enables systems to respond more quickly to external events while lowering power consumption.

The LIS2DUX12 and LIS2DUXS12 are digital, 3-axis linear accelerometers with features such as always-on anti-aliasing filtering, a finite state machine (FSM) and machine learning core (MLC) with adaptive self-configuration (ASC). The S12 includes and analog hub and variable current (Qvar) sensing channel.

Up to 16g

The parts come with I3C slave interface and embedded 128-level FIFO buffer complete and user-selectable full scales of ±2g/±4g/±8g/±16g They are capable of measuring accelerations with output data rates from 1.6Hz to 800Hz.

The accelerometers provide a dedicated internal engine to process motion and acceleration detection including free-fall, wake-up, single/double/triple-tap recognition, activity/inactivity, and 6D/4D orientation.

The Qvar channel can be used to detect changes in the ambient electrostatic environment to provide presence and proximity detection. This capability lets developers address user-interface control, liquid detection, and biometric sensing applications, such as heart-rate monitors. In user-interface applications, Qvar combined with an acceleration signal removes potential false positive detection in two-tap and multi-tap events.

The machine-learning core in the LIS2DUX12 and LIS2DUXS12 enables artificial-intelligence (AI) algorithms to perform reliable activity detection and the FSM enhances movement recognition. Together, they provide autonomous processing in the sensor, which offloads host interaction and processing, significantly lowering power consumption and enables faster system responses. In addition, by deploying an adaptive self-configuration (ASC) capability, the accelerometers adjust their own settings – such as measurement range and frequency – independently to further optimize performance.

Powerful and saving power

These smart accelerometers provide context sensing for wearables devices such as earbuds, smartphones, hearing aids, game controllers, smart watches, asset trackers, robotic appliances, and IoT devices.

Ready-to-use machine learning and finite-state machine algorithms are available through ST’s MEMS GitHub model zoo, which facilitates complex gestures, asset tracking, and many other use cases.

These smart MEMS accelerometers extend ST’s family of MEMS sensors enhanced with AI. The company introduced inertial measurement units (IMUs) with AI in 2019.

The LIS2DUX12 and LIS2DUXS12 are available in a 2mm by 2mm by 0.74mm 12-lead LGA package. Pricing is from $1.38 for the LIS2DUX12 and $1.43 for the LIS2DUXS12, for orders of 1000 pieces. The LIS2DU12, in the same package type, is available for $1.20.

Related links and articles:

News articles:

Bosch IMU enhanced for consumer applications

Sensirion buys AI predictive maintenance firm

MEMS vibration sensor cancels road noise

Bosch leads vendor ranking in strong MEMS market

MEMS bone-conduction microphone provides wake-on-voice for wearables

MEMS vibration sensor for industrial monitoring


Linked Articles