03-07-2025 | Bosch | Semiconductors
Wearables and hearables have transformed how we track and monitor our movements, particularly in how we can analyse sport and exercise. For the most dynamic activities, Bosch's latest BHI385 sensor delivers accurate acceleration measurement up to ±28g – allowing it to capture peak movement, such as a golf swing or tennis smash, and deliver the most precise insights.
With a measurement range of up to ±28g, the sensor enables precise motion analysis for high-impact events across various sports, fitness activities, and gaming. The sensor combines a gyroscope and accelerometer with embedded AI software and an integrated 32-bit MPU, creating a complete programmable system based on the company's field-proven IMU platform.
The device builds on the successful BHI360 sensor generation and adds advanced programmability and self-learning AI, making it excellent for applications such as personalised coaching, sport-specific feedback or gesture-controlled interfaces.
"With BHI385, we enable wearables to go beyond basic motion tracking – by understanding intensity, repetition quality and user-specific movement patterns, directly on-device," says Dr Stefan Finkbeiner, CEO at Bosch Sensortec.
The device's embedded AI supports key motion functions, including 6DoF/9DoF sensor fusion, step counting, activity recognition, and gesture detection (single, double and triple tap). Self-learning cyclic gesture recognition enables it to detect repeated motion patterns and adapt them to the individual, not only recognising what is being done, but also how well it is being performed. This enables advanced use cases, such as evaluating the quality of movement in sports or rehabilitation training.
All processing runs on the integrated low-power processor, avoiding wake-up calls to the host CPU. Typical current consumption is less than 500µA at 50Hz for sensor fusion, and under 50µA for simpler accelerometer-based algorithms.
The device is offered in a compact 20-pin LGA package measuring 2.5mm x 3mm x 0.95mm³. Its low power consumption and embedded intelligence make it a perfect fit for wearables, hearables, and edge AI systems. To support fast time-to-market, the company provides developers with Motion AI Studio and an Open SDK for custom ML model integration.
The BHI385 is ideal for applications such as sport activity tracking, detailed movement evaluation, including technique analysis, and embedded ML processing for wearables. Its high acceleration range and smart algorithms also make it excellent for impact and collision detection, as well as an intuitive HMI via motion control.
Target devices include smartwatches and fitness bands, specialised sports wearables, including smart clothing, head-mounted devices for AR/VR and audio use, and connected fitness or gaming equipment. These devices benefit from the BHI385's compact design, embedded intelligence, and advanced motion tracking capabilities.