Trådløs multisensor udvides med maskinlærings faciliteter
TDK lancerede med stor succes tilbage i 2019 det såkaldte SmartBug trådløse sensormodul, der nu lanceres i kraftigt opdateret SmartBug 2.0 version (in english).
TDK Corporation announces the InvenSense SmartBug 2.0 with various new and exciting features for consumer and IoT applications as a smart remote data-collection module for IoT after the success of the original SmartBug in 2019.
- SmartBug 2.0 will take digital transformation to the next level by not only being a trusted source of smart sensor data, but by providing the ability to create efficient machine learning models on a 2.5 x 3 mm sensor, explains Sahil Choudhary, Product Marketing Director, at InvenSense, a TDK Group company.
SmartBug 2.0 features:
ICM-45686-S IMU: The SmartBug 2.0 replaces the ICM-42688-P IMU with the latest BalancedGyro IMU, ICM-456xy, the world’s lowest power IMU (220 µA @ 50 Hz 6-Axis) from TDK. This allows developers to collect high quality IMU data for a much longer time, due to the larger battery life (3x better).
This new IMU also provides premium temperature stability and vibration rejection, making SmartBug 2.0 useful for products such as AR glasses, VR, OIS, drones, MR, TWS, and robotics for prototyping, data collection, and Machine Learning-based algorithm development.
Machine Learning: SmartBug 2.0’s key feature is the introduction of machine learning (ML). Developers, ODMs, OEMs, and product developers can now use SmartBug 2.0 along with the sensor inference framework (SIF) by TDK to build machine learning solutions for the ICM-45686-S IMU. SIF is an all-in-one comprehensive software by TDK that enables users to collect IMU sensor data, select custom features, build ML models, test performance, deploy, and run those models on the ICM-456xy IMU through the SmartBug 2.0.
This end-to-end solution allows ML enthusiasts to develop custom motion classification algorithms and run them on a 2.5*3 mm IMU at a current consumption as low as 30 µA. A few examples include algorithms such as exercise classification (squats, jumping jacks, lateral raises, or push-ups) and wrist gesture classification (fight, clench, shake, or still mode).
Furthermore, the small and wireless factor of the SmartBug 2.0 enables engineers to test these ML models in real use-cases and tune the ML parameters accordingly, to create robust ML models at the lowest power.
Head Tracking solution: SmartBug 2.0 added TDK’s head tracking solution (VibeSense360) for TWS and AR applications. This will help TWS and audio companies collect raw sensor and head orientation data at the lowest power (280 µA at 50 Hz) from a TDK solution and learn unique signatures about enabling spatial audio. Please contact TDK sales support for more information on TDK’s VibeSense360 solution for TWS applications.
Air Motion solution: SmartBug 2.0 enhances TDK’s Air Motion solution by adding swipe gestures, remote orientation gestures, and accurate cursor tracking for smart TV remotes.
Data Collection Improvements: Based on user feedback, SmartBug 2.0 has also updated streaming and logging parameters in SmartBug to enable longer duration streaming and logging of multi-sensor and algorithm data.
Lastly, SmartBug 2.0 retains the user interface, BLE, WIFI, USB, and SD card logging and previous applications such as asset monitoring, smart door lock, and sensor fusion, keeping the original SmartBug experience alive.