TDK Launches SmartEdgeML™ to Run Ultra-Low Power Machine Learning Models on a 6-Axis IMU

时间： 2024-01-16 来源：TDK InvenSense News

技术问答

The SmartEdgeML solution allows users to build, test, tune, and deploy ML models at the sensor chip level
SmartEdgeML includes: SmartMotion™ ICM-45686-S 6-axis motion sensor, SmartBug 2.0 evaluation kit, and Sensor Inference Framework software(SIF software), now available for download
SmartBug 2.0 (MD-45688-ML) will be available on February 1 to evaluate SIF with ICM-45686-S

TDK Corporation announces the InvenSense SmartEdgeML^™, 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 2.5 x 3mm 6-axis motion sensor IMU at<30µA.

“TDK’s SmartEdgeML is a paradigm shift in edge machine learning, as it will allow developers, ODMs, and OEMs to implement ML-optimized motion sensor algorithms on an IMU sensor chip. This reduces the amount of raw data going to edge processors, which significantly improves device battery life, data privacy, and system latency,” said Sahil Choudhary, Director Motion Sensors and Software at InvenSense, a TDK Group company.

TDK also announces the availability of the InvenSense SmartBug 2.0 (MD-45686-ML), a multi-sensor wireless module consisting of the InvenSense ICM-45686-S IMU. This module works as the perfect evaluation system for users to get started with the InvenSense SIF and the ICM-45686-S IMU. The SIF is now available for download, while the MD-45686-ML and ICM-45686-S will be available at distributors by February 1, 2024.

There are three components of SmartEdgeML, which include:

SIF (sensor inference framework): SIF, the software component of SmartEdgeML, is a complete machine learning framework by TDK, 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 2.5x3mm IMU from the TDK BalancedGyro™ family that enables ML decision tree models to be run on-chip at the lowest current consumption (<30µA). This new 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.

Main applications

TWS, Hearables
Wearables
AR Glasses
IoT

Main features and benefits

Customization: Users can define and customize their use case and build a motion sensor algorithm with SIF in less than five minutes (with AUTO mode). Users can also configure their custom sensor settings, filters, and features based on their sensor algorithm requirements.
Ownership: Users can own the data and test the ML model with their dataset rather than depending on the sensor vendor for data collection.
Time to market: SIF AUTO mode allows an ML beginner to build an ML model in five 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.
Ultra-Low Power: The SmartEdgeML 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.

发送到邮箱 |
+1 赞 0
收藏
评论 0
| 转发至：

本文由玄子转载自TDK InvenSense News，原文标题为:TDK launches SmartEdgeML™ to run ultra-low power machine learning models on a 6-axis IMU，本站所有转载文章系出于传递更多信息之目的，且明确注明来源，不希望被转载的媒体或个人可与我们联系，我们将立即进行删除处理。

全部评论（0）

暂无评论

GreenWaves Technologies Announced Availability of GAP8 Software Development Kit and GAPuino Development Board

GreenWaves’ pioneering GAP8 IoT Application Processor enables high-performing evaluation board and development kit.Grenoble, France and Santa Clara, Calif., May 22, 2018 – GreenWaves Technologies, a fabless semiconductor startup designing disruptive ultra-low power embedded solutions for image, sound and vibration AI processing in sensing devices, today announced the availability of its GAP8 Software Development Kit (SDK) and GAPuino Development Board. The GAPuino Boards are available for purchase here and the GAP8 SDK can be downloaded via GitHub.

产品发布时间 : 2024-08-20

GreenWaves Technologies Unveils GAP8 IoT Application Processor, Enabling Groundbreaking Embedded Artificial Intelligence at the Very Edge

GreenWaves Technologies Unveils GAP8 The Industry’s Lowest Power IoT Application Processor, Enabling Groundbreaking Embedded Artificial Intelligence at the Very Edge.

产品发布时间 : 2024-08-15

【产品】TDK提供SmartIndustrial™ 6轴IMU模块，为工业应用提供精确运动和倾角测量

TDK的SmartIndustrial™ 6轴IMU模块产品系列，即IIM-46234和IIM-46230，提供工业应用所需的精确运动和倾角测量。这些模块能够在恶劣环境（如振动、剧烈温度变化等）下进行精准测量，为各种工业导航、工业稳定性和监测应用赋能。

产品发布时间 : 2023-06-19

EPSON(爱普生) 晶体器件选型指南

描述- 爱普生通过原创的“省、小、精技术”和“数字技术”，致力于共同创建一个将人、物与信息互联的可持续发展的社会，让世界变得更加和谐美好。在办公和家庭打印、商业和工业打印、制造、视觉、生活方式等领域持续创新。

型号- X1B000142000400,X1G005461XXXX00,RA8804CE,X1G006041XXXX14,SG2016VHN,TG2016SMN,X1B000471000815,VG3225EFN122.880000MHZCJGHBA,X1G004171XXXX00,X2A000311XXXX00,SG-210 STF,RX8900CE UC,SG2016EGN,SG-WRITERII,RX8900CE UB,RX8900CE UA,X1B000292000300,RX8130CE,X1B000301000100,X2A000351XXXX00,TG2520SMN,X1G004541XXXX00,SG5032VEN,X1G005941XXXX15,X1G005901XXXX15,SG-8200,SG2520EHN,SG-8201,X1G0052010001,SG2016EHN,Q4140455100020041,FC-12M32.768000KHZ12.5+20.0-20.0,X1G005531XXXX00,SG2016CAA,SG2520VHN,X1B000142000300,X1G0053210001,X1B000471000715,RA8804CE XA,TG5032SGN,TG7050CKN30.720000MHZCAHHGA,RA8804CE XB,X1G006191XXXX16,X1G005311XXXX00,X1G005351XXXX00,X1G006111XXXX15,X1A000121XXXX00,Q41457152000100,X2A000201XXXX00,Q4180255100020040,SG-8201 SERIES,SG2520EGN,X1B000182000300,X1G005981XXXX16,RA8000CE YB B8,SG2016CAN,X1G005421XXXX27,RX-8803LC AA,VG7050CDN,X1G005571XXXX00,X1B000491A01915,FA-12824.000000MHZ12.0+10.0-10.0,X1B000292000200,X1G004561XXXX0096,SG-8101CGA170.000000MHZTCHPA,Q418564C2000100,SG2016VGN,SG2520VGN,RA8000CE YB C0,TG5032SFN,Q41802552000100,X1A000161XXXX16,M-G552 SERIES,X1G0055710001,SG5032EEN,TG5032CGN,X1G005011XXXX00,SG5032CAN,X1G004801XXXX00,TG2016SMN26.000000MHZECGNNM,X1B000202000100,X1B000421000215,X1B000142000200,TG5032SMN,XV7081BB,X1G006221XXXX15,RA8900CE,SG2520CAA,RX4111CE,SG-9101,X1B000172000200,RX8900SA,VG7050EFN,SG-8018,X1G005601XXXX00,X2A000171XXXX00,SG2016CAN25.000000MHZTJHA,TG3541CEA,SG-8018CG25.000000MHZTJHPA,X2F000011000100,X1A000201XXXX18,SG-8506 SERIES,MG7050,X1B000271A00500,FA2016AA24.000000MHZ12.0+10.0-10.0,SG-8000,X1B000401A00116,FC-135R,TG5032CMN,SG5032CCN,RX-8803SA AA,X1B000202000200,X1B000421000115,X1G005541XXXX00,X1B000142000100,TG2016SKA,RX-8564LC,TG5032SKN,M-A352AD10,XV4001BC,VG7050VFN,XV4001BD,RX-8035LC B,X1G005951XXXX16,FA1210AN,X1B000131XXXX00,X1B000172000100,XV4001B*,Q13FC1350XXXX00,TG5032CFN30.720000MHZCAGNDA,X1B000501A01015,X1G004281XXXX00,RX-4045SA AC,X1B000311000100,TG2016SLA26.000000MHZECGNNM,TG2016SLA,TG2016SLN,X1B000271A00400,SG-8503 SERIES,SG-8101,SG-8018 SERIES,SG-9101CB,TG5032CKN,SG-9101CA,SG2520HHN,X2G000191000100,RX-4035SA B,SG-9101CE,Q41404552000100,RX-4045SA AA,SG-9101CG,TG3225CEN39.000000MHZKFGNNM,X1G0052110001,SG3225EEN156.250000MHZCDGA,XV4001BX,X1G006031XXXX14,TG5032CGN30.720000MHZCAGHDA,X1G005491XXXX00,X1B000072000100,SG-WRITER II,X1G005881XXXX15,TG-5006CE,X1E000021XXXX17,TG-3541CEA XA,TG-5006CG,SG-8503CA156MHZ625MHZAPRLZ,X1A000021XXXX00,TG-3541CEA XB,SG3225EEN,X1B000471000415,SG3225CAN,SG2520HGN,FA-238,X1A000061XXXX00,X1B000391000116,X1B000202000300,SG3225VEN,X1E000411XXXX26,X1E000451XXXX26,RX4901CE XS A0,TG-5006CJ,SG-8018CA,SG-8018CB,TSX-3225,X1A000171XXXX18,RX-4045SA,VG7050CDN122.880000MHZCJGHBA,SG-8201CJ,FA-128,SG-8018CG,SG-8201CG,SG-8018CE,X1G0051810001,SG-8506CA156.2MHZ0X37APRLZ,RX4901CE XS B0,SG-8200 SERIES,X1G005341XXXX00,SG-9101 SERIES,X1G006141XXXX15,RX-4035SA,X1G004251XXXX00,X1B000471000315,X1G005561XXXX00,X1G004291XXXX00,RX8111CE,TG-5510CB-***38.880000MHZ,X2F000021000100,VG5032EFN,RX4901CE XS C0,SG-9101CGA170.000000MHZC20PJAAA,X1G005931XXXX15,FC1610BN32.768000KHZ12.5+20.0-20.0,X1B000501A00915,RX4901CE XS D0,SG-8200CG,SG-8200CJ,XV-3510CB*********KHZ,X1G005161XXXXXX,RA8900CE UA,X1E000341XXXX00,RA8900CE UB,RX-8803SA,RX-8025NB,SG2016HGN100.000000MHZCDHPZA,X1B00023200010039,X1B000471000615,X1G0050311001,MG7050HAN,SG3225EAN,X2A000121XXXXXX,X1B000192000200,SG2016EGN156.250000MHZCDHPZA,X1B000182000200,X1G006201XXXX16,FC2012SN,X1B000242000100,M-G370PD,FA2016ASA38.400000MHZ7.0+10.0-10.0,X1G0055810001,RX-4571SA,X1B000292000100,SG-8201CJ170.000000MHZTDJPA,SG3225VAN,FC1610AN32.768000KHZ12.5+20.0-20.0,X1G005721XXXX16,X1B000361A00100,RX-8025SA AC,FC2012SN32.768000KHZ12.5+20.0-20.0,RX-8025SA AA,RX8900SA UB,RX8900SA UC,RX-8803LC,RX8900SA UA,TG5032CKN38.880000MHZCAHHGA,SG-8504 SERIES,VG5032EDN,RX-8035LC,SG-8201CJA170.000000MHZTDJPA,RX-8035LC AC,RX-8035LC AA,XG-2121CA,X1G005221XXXX00,FC-12M TYPE,X1B000351000200,VG5032VFN,XC1011SD,X1B000301000300,SG-8504CA156.2MHZNNNNAPRLZ,RA4000CE,X1G005441XXXX25,X1G005551XXXX00,TG3225CEN,X1G005501XXXX00,X1B000471000515,X1G005991XXXX16,XV4001K*,RX-8035SA AA,X1G005331XXXX00,RX-8035SA AC,Q14FC1350XXXX00,X1B000192000300,RX8804CE,TG-5510CA-***30.720000MHZ,X1B000182000100,SG2016HGN,X1G004241XXXX00,SG-8101 SERIES,X1B000301000200,RX-8571LC,FA-20HS,FC-135 TYPE,X1B000361A00200,TG-3541CE,X1A000181XXXX18,SG2016HHN,X1B000351000100,RX-8035SA B,X1G005101XXXXXX,FA2016ASA,VG5032VDN,X1B000491A00915,FC-12M,X1G006061XXXX14,SR3225SAA,X1B000122XXXX00,X1G005481XXXX00,X1G005891XXXX15,Q22FA23V0XXXX17,SG-850XCA,SG2016CAA25.000000MHZTJHA,SG-8018CGA,X1B000481000415,X1E000401XXXX18,SG-210STF,TG7050XKN,MG7050VAN,Q414571C2000100,TG2016SLN26.000000MHZEWHSNM,XV4001KD,TG-5510CA,X2E0000210002XX,XV4001KC,RX-8025SA,SG3225EAN156.250000MHZKJGA,X1G005921XXXX15,TG-5510CB,X1G004451XXXX00,SG-8201CJA,SG3225HBN,FC-135R32.768000KHZ12.5+20.0-20.0,X1G006021XXXX14,Q91PR10W00018,SG-8200CJ170.000000MHZTJJPA,RX-8803SA UB,RX-8803SA UA,RX-8803SA UC,TG1612SLN26.000000MHZEWHSNM,SG-8101CE,SG-810

选型指南 - EPSON - 2024/4/5 PDF 英文下载