Self-learning AI smart sensor for fitness tracking

24-05-2022 | Mouser Electronics | Test & Measurement

Mouser now stocks the BHI260AP self-learning AI smart sensor from Bosch. Coined as the world's first self-learning AI sensor for wearables and hearables, the device incorporates a six-axis IMU, a 32-bit customer-programmable microcontroller, and software functionalities in a SiP solution.

The self-learning AI smart sensor offers embedded edge AI with self-learning AI software and includes fitness tracking, navigation (pedestrian dead reckoning), machine learning analytics, and relative and absolute orientation estimation. The integrated sensor on the BHI260AP is a 6DoF IMU that includes a 16-bit, three-axis accelerometer and 16-bit, three-axis gyroscope. The host interface is configurable as SPI or I²C, with two master interfaces (one selectable SPI/I²C and one I²C) and up to 12 GPIOs.

The unique self-learning and personalisation elements of the device allow users to train devices with customised fitness activities effortlessly. The sensor comprises more than 15 pre-learned fitness activities, so no training is needed before use. As well as the included activities, the device also delivers the ability to learn, personalise, auto-track and enhance the user experience. Users can also enhance or add new fitness activities without modifying the software or needing an original dataset. Since the AI is running on the sensor itself, connecting to the cloud or a smartphone is not needed. This innovative edge AI functionality helps lower latency, minimise power consumption and improve end-user privacy.

The sensor is an all-in-one solution for always-on sensor applications, perfect for wrist wearables, hearables, smartphones, AR/VR headsets, and controller devices. For evaluation and development, Mouser also offers the BHI260AP Shuttle Board 3.0, currently available to order.

By Natasha Shek