EdgeAI AMB82mini

人工智慧教材

1. AMB82-mini 開發板介紹

RTL8735B晶片簡介

32-bit Arm v8M, up to 500MHz, 768KB ROM, 512KB RAM, 16MB Flash (MCM embedded DDR2/DDR3L up to 128MB)
802.11 a/b/g/n WiFi 2.4GHz/5GHz, BLE 5.1, NN Engine 0.4 TOPS, Crypto Engine, Audio Codec, ...

---

HUB 8735 Ultra

https://github.com/ideashatch/HUB-8735

---

AMB82-mini

Ameba Arduino

---

2. IDE使用介紹 (Arduino-IDE intro)

Arduino IDE 2.3.10 下載安裝

---

偏好設定 (Preferences)

Hub8735 ultra
https://raw.githubusercontent.com/ideashatch/HUB-8735/main/amebapro2_arduino/Arduino_package/ideasHatch.json

AMB82-mini
main https://github.com/Ameba-AIoT/ameba-arduino-pro2/raw/main/Arduino_package/package_realtek_amebapro2_index.json
dev https://github.com/Ameba-AIoT/ameba-arduino-pro2/raw/dev/Arduino_package/package_realtek_amebapro2_early_index.json

---

選定開發板 AMB82-MINI

Tools > Board Manager > Search AMB82 : Realtek Ameba Boards 4.1.1-build20260823

Serial-monitor = 115200 baud

---

Getting Started

首先將AMB82-mini板子用MicroUSB線 連接至電腦的USB port
確認UART com port (Ubuntu OS需 sudo chown usrname /dev/ttyUSB0)

燒錄程式碼：

• 按下UART_DOWNLOAD按鈕, 再按下RESET按鈕, 放開RESET按鈕, 再放開UART_DOWNLOAD按鈕,板子就進入燒錄模式.
• 然後于Arduino IDE上按下燒錄按鍵Upload

---

Realtek AmebaPro2 hardware libraries

C:\Users\user\AppData\Local\Arduino15\packages\realtek\hardware\AmebaPro2\4.1.0-build20260213\libraries

C:\Users\user\AppData\Local\Arduino15\packages\realtek\hardware\AmebaPro2\4.1.0-build20260213\libraries\NeuralNetwork\src
GenAI.h
GenAI.cpp

---

基本練習 (Arduino examples)

教學範例程式

1. 瀏覽器打開 EdgeAI-AMB82mini, 點[Code]並選 [Download ZIP]
2. 解壓縮.zip, 並將 Arduino/AMB82-mini 複製到 文件/Arduino下, 成為 文件/Arduino/AMB82-mini

基本範例程式練習

Examples> 01.Basics > Blink

Examples> 02.Digitial > GPIO > Button

程式碼修改：
const int buttonPin = 1; // the number of the pushbutton pin
const int ledPin = LED_BUILTIN; // the number of the LED pin

Examples> 01.Basic > AnalogReadSerial

程式碼修改：Serial.begin(115200);

---

3. 通訊硬體界面

BLE (低功耗藍牙）

Examples> AmebaBLE > BLEWiFiConfig

• Google Play Store: https://play.google.com/store/apps/details?id=com.rtk.btconfig
• Apple App Store: https://apps.apple.com/sg/app/easy-wifi-config/id1194919510

---

Examples> AmebaBLE > BLEUartClient

BLE UART Client

---

Examples> AmebaBLE > DHT_Over_BLEUart

DHT over BLE UART

---

Examples> AmebaBLE > BLEWifiConfig

WiFi Config Service

---

Examples> AmebaBLE > BLEV7RC_CAR_VIDEO

BLE V7RC

• V7RC APP 介紹
  
• 安裝手機App V7RC
  

---

WiFi（無線網路）

Examples > WiFi > SimpleTCPServer

WiFi - Simple TCP Server

Examples > WiFi > SimpleHttpWeb > ReceiveData

WiFi - Simple Http Server to Receive Data

Sketchbook > AMB82-mini > WebServer_ControlLED

Sketchbook> WebServer_ControlLED

Sketchbook > AMB82-min > BLEConfig_WebServer_ControlLED

Sketchbook> BLEConfig_WebServer_ControlLED

Examples > AmebaFileSystem > ReadHTMLFile

Read and display HTML file from SD card

---

MQTT通訊協定

MQTT is an OASIS standard messaging protocol for the Internet of Things (IoT)
How MQTT Works -Beginners Guide

---

Examples> AmebaMQTTClient > MQTT_basic

MQTT - Set up MQTT Client to Communicate with Broker

---

MQTT App

Prompt: make a HTTP Server html to input MQTT topic and text to publish through Paho-MQTT test.mosquitto.org

Paho-MQTT Publisher

---

OTA (Over-The-Air)

To install Ameba-OTA-UI, read https://github.com/Ameba-AioT/ameba-OTA-UI

Examples > AmebaOTA > OTA

Ameba Over-the-Air Firmware Update

Examples > AmebaOTA > SDCardOTA

Ameba SDCard OTA Firmware Update

---

4. 感測器與週邊裝置

Sensors

IMU

---

ToF Distance Sensor (紅外線測距感測器)

VL53L0X

---

Peripherals

TFT-LCD (液晶顯示器)

AMB82-mini and QVGA TFT LCD Wiring Diagram

---

Motor Driver (馬達驅動器)

PWM

myservo.attach(8);

myservo.write(pos);

---

TB6612

---

DRV8833

Sketchbook > AMB82-mini > RoboCar_DRV8833

---

Gripper (夾具)

Examples> AmebaAnalog > PWM_ServoControl

---

5. 音頻應用

播放MP3

AMB82-mini + PAM8403 + 4ohm 3W speaker

Examples > AmebaMultimedia > SDCardPlayMP3

Sketchbook> AMB82-mini > SDCardPlayMP_All

.mp3 files stored under mp3 directory

---

音頻串流 (Audio Streaming)

Examples > AmebaMultimedia > Audio > RTSPAudioStream

---

MP4錄音 (Audio Recording)

Examples> AmebaMultimedia > Audio > AudioTriggerRecording

Examples> AmebaMultimedia > RecordMP4 > AudioOnly

---

音頻分類 (Audio Classification)

Examples> AmebaNN > AudioClassification

The default pretrained model can recognise 521 different types of audios in total.

YAMNet

---

聲音播放 (Play MP3)

• Examples > AmebaMultimedia > SDCardPlayMP3
• Sketchbook> AMB82-mini > SDCardPlayMP_All

---

6. 影像串流 (Video Streaming)

• Amebapro2 AMB82-mini Arduino Example Guides

Video-Only

Examples> AmebaMultimedia > StreamRTSP > VideoOnly

Sketchbook> RTSP_VideoOnly

---

WebSocket Viewer

Examples > AmebaMultimedia > WebSocketViewer

---

動作偵測 (motion detection)

Examples> AmebaMultimedia > MotionDetection > LoopPostProcessing

• 修改ssid, passwd, 後燒錄到AMB82-mini,
• 按reset後程式即開始運行, 用serial-monitor 查看顯示串流網址
• 啟動手機或電腦上之VLC player, 設定RTSP串流網址

---

7. 神經網路模型 (AmebaNN)

人臉辨識與識別

人臉檢測範例

Examples> AmebaNN > RTSPFaceDetection

---

人臉識別範例

Examples> AmebaNN > RTSPFaceRecognition

Serial_monitor: REG=RKUO

• Enter the command REG=Name to give the targeted face a name.
• Enter the command DEL=Name to delete a certain registered face. For example, DEL=SAM
• Enter the command BACKUP to save a copy of registered faces to flash.
• If a backup exists, enter the command RESTORE to load registered faces from flash.
• Enter the command RESET to forget all previously registered faces.

---

影像分類 (Image Classification)

Examples > AmebaNN > RTSPImageClassification

---

Garbage模型訓練與檔案轉換

模型訓練： kaggle.com/rkuo2000/garbage-cnn

required in kaggle for AmebaPro2

1. pip install tensorflow==2.14.1
2. model.save('garbage_cnn.h5', include_optimizer=False)

模型轉換：AMB82 AI Model Conversion

1. Download garbage_cnn.h5 from kaggle.com/rkuo2000/garbage-cnn Output
2. Compress garbage_cnn.h5 to garbage_cnn.zip
3. Go to Amebapro2 AI convert model, fill up your E-mail
4. Upload garbage_cnn.zip
5. Upload one (.jpg) test picture (EX. glass100.jpg from Garbage dataset)
6. Email will be sent to you for the link of network_binary.nb

程式範例：RTSP_GarbageClassification.ino

1. click the recieved Email link to download network_binary.nb
2. create NN_MDL folder in SDcard, save network_binary.nb under NN_MDL folder, and rename it to imgclassification.nb
3. plugin SDcard back to AMB82-MINI
4. modify Sketch RTSP_GarbageClassification.ino
   1. modify SSID and PASSWD
   2. modify imgclass.modelSelect (change DEFAULT_IMGCLASS to CUSTOMIZED_IMGCLASS)
5. burn code into board AMB82-MINI, and run it with VLC player streaming

---

物件偵測 (Object Detection)

Roboflow Datasets

Examples > AmebaNN > ObjectDetectionLoop

---

Kaggle 範例:

• YOLOv7 FaceMask
• YOLOv7 Pothole
• YOLOv7 Sushi
• YOLOv7 RefrigFood
• YOLOv7 TrafficSign
• YOLOv7 Tanks
• YOLOv7 reparm

---

Pothole模型訓練與檔案轉換

模型訓練： kaggle.com/rkuo2000/yolov7-pothole

1. repro https://github.com/WongKinYiu/yolov7
2. create pothole.yaml %%writefile data/pothole.yaml
   

train: ./Datasets/pothole/train/images
val:  ./Datasets/pothole/valid/images
test: ./Datasets/pothole/test/images

# Classes
nc: 1  # number of classes
names: ['pothole']  # class names

3. YOLOv7-Tiny Fixed Resolution Training

!sed -i "s/nc: 80/nc: 1/" cfg/training/yolov7-tiny.yaml
!sed -i "s/IDetect/Detect/" cfg/training/yolov7-tiny.yaml

模型轉換：AMB82 AI Model Conversion

1. Download best.pt from kaggle.com/rkuo2000/yolov7-pothole
2. Compress best.pt to best.zip
3. Go to Amebapro2 AI convert model, fill up your E-mail
4. Upload best.zip
5. Upload one (.jpg) test picture (EX. pothole_test.jpg from Pothole dataset)
6. Email will be sent to you for the link of network_binary.nb

程式範例：RTSP_YOLOv7_Pothole_Detection.ino

1. click the recieved Email link to download network_binary.nb
2. create NN_MDL folder in SDcard, save network_binary.nb under NN_MDL folder, and rename it to yolov7_tiny.nb
3. plugin SDcard back to AMB82-MINI
4. modify Sketch RTSP_YOLOv7_Pothole_Detection.ino
   1. modify SSID and PASSWD
   2. modify ObjDet.modelSelect(OBJECT_DETECTION, CUSTOMIZED_YOLOV7TINY, NA_MODEL, NA_MODEL);
5. burn code into board AMB82-MINI, and run it with VLC player streaming

---

AMB82 Mini - 物件偵測範例

RTSP_YOLOv7_Pothole
RTSP_YOLOv7_Sushi

---

AMB82 Mini - SD卡加載模型範例

RTPS_ObjectDetection_AudioClassification.ino

---

AMB82 Mini - 綫上AI 模型轉換工具

---

8. 語音應用 (TTS & STT)

語音合成 (TTS)

Examples > AmebaNN > MultimediaAI > TextToSpeech (google-tts)

---

語音辨識 (STT)

聲音偵測 (VAD)

Examples> AmebaMultimedia > Audio > AudioTriggerRecording

Examples> AmebaMultimedia > Audio > SoundDetectorTrigger

---

雲端語音辨識

ffmpeg.exe is needed for Windows to run Whisper

Examples > AmebaNN > MultimediaAI > GenAISpeech_Whisper (Whisper)

Examples > AmebaNN > MultimediaAI > GenAISpeech_Gemini (Gemini)

---

本地PC語音辨識

AmebaPro2 Whisper LLM_server

• Examples -> AmebaHttp > HTTP_Post_MP4_Whisper_server
• Examples -> AmbeaHttp > HTTP_Post_MP4_Whisper_server_FastAPI

---

9. 語言模型 (LLM & VLM)

雲端視覺解析

Examples > AmebaNN > MultimediaAI > GenAIVision

Examples > AmebaNN > MultimediaAI > GenAIVisionTTS

Examples > AmebaNN > MultimediaAI > GenAIVideo

---

本地PC視覺解析

PC-RTX5060OC-8/16GB running Ollama-server with Gemma-4 model
ollama run gemma4:e2b

Examples > AmebaNN > MultimediaAI > SendImageOllama

Sketchbook > AMB82-mini > Ollama_sendText

Sketchbook > AMB82-mini > Ollama_sendImage

---

10. 機器人應用

AMB82 mini MCP Server for FreeRTOS SDK

• Dual-mode development:
  • Arduino — arduino-cli compile & upload
  • FreeRTOS SDK — cmake + arm-none-eabi-gcc compile, uartfwburn upload
• Semantic search with ONNX Runtime — pre-built index covers 3,500+ documents from:
  • amb82-mini-docs — official tutorials and API docs
  • ameba-arduino-pro2 — Arduino SDK libraries and examples
  • ameba-rtos-pro2 — FreeRTOS SDK components

---

VLA Robot

RoboCar: AMB82-mini + DRV8833 + MPU6050 + VL53L0X + PAM8403 + Speaker + DC-motor x2

PC: ollama run gemma4:e2b

Functions:

• 防撞 - 需讀取紅外線測距 (VL53L0X)
• 朝向 - 需讀取慣性感測元件偵測角度 (MPU6050)
• 行進 - 需讀取行進命令，執行馬達控制 (DRV8833)
• 導航 - 需拍照送VLM 識別 (Gemma4:E2B)
• 命令 - 提問LLM/Agent控制 (Gemma4:E2B)

---

Appendix. EdgeAI 應用專題實作

114年度專題實作

1. AI輔助回收系統
2. AI輔助英語讀字卡造句
3. AI看圖說故事
4. AI情緒感知音樂播放器
5. AI監視錄影系統
6. 盲人輔助系統
7. 盲人導航系統