Innovative MEMS Sensor IMUs for Consumer, Industrial Applications

Two high-performance InvenSense motion sensors, the InvenSense SmartMotion ICM-42370-P and the InvenSense SmartIndustrial IIM-42653, as well as the InvenSense SmartEdgeML and the InvenSense SmartBug 2.0 (MD-45686-ML), were launched at CES 2024.

InvenSense SmartMotion ICM-42370-P is a premium 3-axis accelerometer for consumer applications that require low noise and high sensitivity.

Ideal for IoT applications, the ICM-42370-P accelerometer offers low-noise performance and up to ±16 g of measurement range. It features 16-bit ADC for high accelerometer sensitivity and supports a wide range of on-chip motion event/activity detection based on interrupt or register access, without additional user programming.

These features make it ideal for use cases such as home/industrial appliances, security cameras, and consumer or medical wearables.

The InvenSense SmartIndustrial IIM-42653 is a high-FSR 6-axis IMU (3-axis gyroscope + 3-axis accelerometer) that can achieve a gyro-programmable digital output of ±4,000 dps and an accelerometer-programmable output of ±32 g, while achieving an ultra-low gyro noise. These technical features make the IIM-42653 ideal for applications that need robust, fast, and accurate performance, such as industrial or high-end grade AGV, AMR, and drones.

The InvenSense SmartEdgeML is an advanced edge ML solution enabling new possibilities for wearables, hearables, AR glasses, IoT, and other products that benefit from machine learning (ML) at the sensor chip level.

SmartEdgeML is the first solution to generate and run machine learning models on a 0.1 x 0.1 in. (2.5 x 3 mm) 6-axis motion sensor IMU at <30 µA. 

It will allow developers, ODMs, and OEMs to implement ML-optimized motion sensor algorithms on an IMU sensor chip to reduce the amount of raw data going to edge processors, improving battery life, data privacy, and system latency.

The InvenSense SmartBug 2.0 (MD-45686-ML), a multi-sensor wireless module consisting of the InvenSense ICM-45686-S IMU, works as an evaluation system for users to get started with the InvenSense SIF and the ICM-45686-S IMU.

There are 3 components of SmartEdgeML: 

• SIF (Sensor Inference Framework)
  • SIF, the software component of SmartEdgeML, is a complete machine learning framework, providing a one-stop-shop for users to collect IMU sensor data, select custom features, build ML models, test ML performance, deploy, and run those models on the ICM-45686-S IMU through the SmartBug 2.0. Tested examples include algorithms such as exercise classification (squats, jumping jacks, lateral raises, or push-ups) and wrist gesture classification (fight, turn, shake, or still). 
• ICM-45686-S IMU
  • This is the hardware component of SmartEdgeML. The SmartMotion ICM-45686-S is a 0.1 x 0.1 in. (2.5 x 3 mm) IMU from the TDK BalancedGyro family that enables ML decision tree models to be run on-chip at the lowest current consumption (<30 µA). This IMU provides premium temperature stability and vibration rejection, making it optimal for applications such as AR glasses, VR, OIS, drones, TWS, and robotics that need a combination of high-performance and ultra-low-power machine learning algorithms.  
• SmartBug 2.0 (ML version)
  • MD-45686-ML is an all-in-one multi-sensor wireless module that comes with the ICM-45686-S 6-axis motion sensor and is compatible with the SIF. The small form factor and BLE + USB interface of SmartBug 2.0 allow users to get started quickly with SIF so they can move easily from data collection to building ML models, to deploying on the ICM-45686-S IMU. This is the go-to device for getting started with SmartEdgeML.

The SmartMotion ICM-42370-P will be available on February 1, 2024, from distributors and through the InvenSense website at invensense.tdk.com/smartmotion.

The SmartIndustrial IIM-42653 is now available across distribution channels, with more information at invensense.tdk.com/smartindustrial or by emailing InvenSense Sales at [email protected].

The SIF is available for download, while the MD-45686-ML and ICM-45686-S will be available at distributors by February 1, 2024. For more information about SmartEdgeML including the SmartBug 2.0, and to download the SIF software, visit invensense.tdk.com/smartedgeml or contact InvenSense Sales at [email protected].

Features:

SmartMotion:

• 3-axis accelerometer with wide full-scale range up to ±16 g
• Low noise performance of 100 μg/√Hz under Low Noise (LN) mode
• 16-bit ADC up to 2.25 kB FIFO for high-resolution sensor data output
• On-chip motion functions for easy motive detection: pedometer, tilt detection, low-g detection, freefall detection, wake on motion, significant motion detection
• Supports latest host interface including 12.5 MHz I3CSM, 1 MHz I2C, 24 MHz SPI
• Drop-in to 6-axis footprint for easy transition between 3 and 6-axis based on requirements
• Dimensions: 0.1 x 0.1 x 0.03 in. (2.5 x 3 x 0.76 mm) (14-pin LGA)

Industries/Applications:

• Home/Industrial Applications
• Security Cameras/Dashcams
• Consumer and Medical Wearables (IoT)

SmartIndustrial:

• Precise measurements enabled by highly accurate and ultra-low noise sensors
• Support for extended temperature range -40 to 221°F (-40 to 105°C)
• ±4,000 dps and ±32 g, gyro and accelerometer outputs enable fast, accurate motion sensing
• Support for highly accurate external clock input that reduces system-level sensitivity error, improves orientation measurement from gyroscope data, and reduces ODR sensitivity to temperature and device-to-device variation
• Comprehensive development and evaluation platform along with software for quick-to-market development of customer systems
• Available in a small 0.1 x 0.1 x 0.035 in. (2.5 x 3 x 0.91 mm) 14-pin LGA package

Industries/Applications:

• Drones
• Navigation Modules
• AGV and AMR Systems

SmartEdgeML

• Users can define and customize their use case and build a motion sensor algorithm with SIF in less than 5 minutes (with AUTO mode). Users can also configure their custom sensor settings, filters, and features based on their sensor algorithm requirements.
• Users can own the data and test the ML model with their dataset rather than depending on the sensor vendor for data collection.
• SIF AUTO mode allows an ML beginner to build an ML model in 5 minutes. After the user collects data, the SIF takes care of the rest. Once the model/algorithm is ready and meets the performance criteria, TDK provides an integration guide to run the final algorithm on ICM-45686-S IMU on the user's system. This end-to-end ML solution on an IMU saves multiple months of algorithm effort.
• Solutions can run as low as <30 µA. This low power allows the edge processor device to sleep longer and process only smart data coming from the sensors, reducing battery drainage and MIPS cycles.

Industries/Applications:

• TWS, Hearables
• Wearables
• AR Glasses
• IoT

InvenSense | TDK Corp.
invensense.tdk.com
(408) 501-2200