SimpleLink™ SDK Edge AI Plugin 1.10.00.00 Release Notes
Table of Contents
Introduction
The SimpleLink™ SDK EdgeAI Plugin (EDGEAI) from Texas Instruments is a plugin for enabling EdgeAI development on TI’s Wireless MCUs leveraging the TI’s Edge AIs Studio.
Documentation
The following documentation is provided with this release.
What’s New
With this release of the plugin, new examples have been added for the following devices, and previously supported examples now include support for additional devices.
- Smart PIR Motion Detection
- CC1312PSIP
- CC1312R1
- CC1312R7
- CC1314R10
- Fan Blade Fault Detection
- CC2755R10
- CC2755P10
- CC2745R10-Q1
- CC3551E
- CC1312R1
- CC1312R7
- CC1312PSIP
- CC1352R1
- CC1352P1
- CC1352P7
- CC1314R10
- CC1354P10
NOTE: The Fan blade fault detection example enabled in the plugin allows the user to evaluate the Fan Imbalance Classification and Motor Bearing Fault Classification Edge AI Projects within EDGE-AI-STUDIO-MCU.
The plug-in contains the following features that have been developed:
- Device Agent Protocol (DAP).
- Feature Extraction Library.
- Support for Neural Processing Unit - Custom Datapath Extension (CDE) on CC27XX and CC35XX devices.
- Smart PIR Motion Detection example.
- Fan Blade Fault Detection example.
Fixed Issues
No bug fixes or known issues addressed in this release.
Known Issues and Limitations
- Users training Edge AI ML tasks for the CC2745R10-Q1, CC2755P10, or CC3551E devices may encounter a compilation failure when using the Edge AI Studio MCU 1.7.0 Desktop application, which prevents the creation of ai trained artifacts. To ensure successful training and artifact generation, please use the Edge AI Studio MCU 1.7.0 Cloud version.
- Launchpad auto-detection feature for Edge AI Studio MCU 1.7.0 Desktop results in a data capture / Live Preview failure for LP-EM-CC2745R10-Q1. User(s) are recommended to manually change the Device Selection to CC2755.
- Compiler support is currently limited to TI Clang.
- The examples and the pre-trained model in TI’s Edge AIs Studio expects a specific matrix of features as input. Therefore, the supported Feature Extraction library is not configurable in terms of features and their parameters. This will be modified in the future to enable flexibility while doing Model Training.
- The PIR sensor example and the pre-trained PIR-net model in TI’s Edge AIs Studio supports sampling frequencies between 25 and 50 Hz.
- The PIR sensor example and the pre-trained PIR-net model in TI’s Edge AIs Studio supports a fixed buffer of 125 bytes as input.
- The Fan Blade Fault Detection example operates at a fixed sampling frequency of 4000 Hz. Modifying the sampling frequency requires retraining the model.
- The pre-trained Fan Blade Fault Detection model classifies faults into exactly 4 output classes: BladeDamage, BladeImbalance, BladeObstruction, and Normal. The model output shape is fixed at (1, 4) and cannot be extended without retraining.
- For the following devices, a manual update needs to be done, wherein the ai_artifacts need to copied from the base example and copied over to the intended device example.
| Device Example | Base Example |
|---|---|
| CC2755P10 | CC2745R10_Q1 |
| CC1312R | CC1312PSIP |
| CC1312R7 | CC1312PSIP |
| CC1352P7 | CC1352R1 |
| CC1352P1 | CC1352R1 |
| CC1354P10-6 | CC1354P10-1 |
Operating System Support
- This Plugin supports only the same Operating System as the main SDK.
Dependencies
EDGEAI requires the following dependency versions (or compatible):
- SimpleLink™ Low Power F3 SDK 9.20.00.81
- SimpleLink™ Low Power F2 SDK 8.33.00.16
- SimpleLink™ Wi-Fi SDK 10.10.01.08
- TI Clang 4.0.2.LTS-0
- Python 3.10.12
- TI’s Edge AIs Studio - Cloud Base
- TI’s Edge AIs Studio - Desktop Base EDGE-AI-STUDIO_1.7.0
- TI Sysconfig SysConfig 1.26.3.4558
- TI Neural Network Compiler for MCUs MCU_2.1.2 LTS
NOTE: For CC35xx SimpleLink™ wireless MCU examples, please ensure you are using SimpleLink™ Wi-Fi SDK version 10.10.01.08 or higher to avoid compilation errors.
Device Support
This SDK supports the following SimpleLink™ wireless MCUs:
Versioning
All releases have 4 segment versions (M.mm.pp.bb). This includes GA and pre-releases (engineering, alpha/EA, beta, etc.). Pre-releases are denoted with a suffix (e.g. 1.00.00.00_eng).
This product’s version follows a version format, M.mm.pp.bb, where M is a single digit Major number, mm is 2 digit minor number, pp is a 2 digit patch number, and bb is an unrestricted set of digits used as an incrementing build counter.
To support multiple side-by-side installations of the product, the product version is encoded in the top level directory.
Subsequent releases of patch upgrades will be identified by the patch number. Typically, these patches only include critical bug fixes.
Technical Support
- For support related to cc27XX devices please go to TI E2E BLE Connectivity Support Community
- For support related to cc135xxx devices please go to TI E2E sub-1 GHz Connectivity Support Community
- For support related to cc355xx devices please go to TI E2E Wi-Fi Connectivity Support Community
Last updated: 2026-07-16