Features
- IoT test bed platform based on Open API that can test the interworking of smart home products
- Divided into door, living room, and kitchen areas, and AI IoT Service for each area is supported
- Consists of high-performance AIoT server, high-performance access point, IoT nodes (sensors and actuators), display, camera, and audio (microphone, speaker)
- High-performance IoT server supports AI accelerated computation through CUDA GPGPU
- GUI-based test bed operation monitoring through 43-inch 4K UHD large monitor including touch screen
- Provides a large pixel display that can implement emotional lighting and real-time notification services
- Supports various IoT connectivity through Gigabit Ethernet, Wi-Fi, Bluetooth, and ZigBee Provides high-performance digital microphones and speakers necessary for implementing AI-based voice command services Supports for deep learning-based image recognition services required to implement customized services
- Soda OS and Pop library, the AIoT dedicated operating system
- Interpreter-based C/C++ development environments optimized for programming beginners, including Python 3
- A dedicated web browser-based learning environment for training Python 3 and C/C++ simultaneously on PCs and tablets
- mDNS/DNS-SD based distributed name resolution, network service publishing and discovery support
- Open Integrated development environment based on Visual Studio Code for professional application development
- Provides comprehensive AIoT practical exercise contents in connection with existing AIoT educational equipment
The post AIoT TestBed Trainer appeared first on EDU Market.
]]>Training Contents
- Lab Environment of AIoT Test Bed
- Low Power Wireless Sensor Network Programming
- IoT Sensor Control Programming by Voice Command
- Smartphone Interlocking Programming
- Cloud Programming
- Face Recognition Programming Based on Deep Learning
The post AIoT TestBed Trainer appeared first on EDU Market.
]]>- AI and IoT convergence training equipment using 2D model of living room of home
- Main module supporting AI acceleration calculation, multimedia and various IoT sensors are integrated into the base board
- The main module is selectable between a 128-core GPU supercomputer for edge devices or a Cortex-A72 quadcore processor with tensor processor unit
- 4 inch TFT LCD with 800×480 resolution and 8M pixel high resolution camera
- Provides Gigabit Ethernet, dual band Wi-Fi(2.4GHz, 5GHz) and Bluetooth 4.2 or 5.0
- Digital microphones and speakers support cloud-based speech recognition and audio playback
- 4 dedicated expansion interfaces support various IoT sensor modules
- Positioning sensors and actuators by creating 2D models of living rooms in real homes to increase immersion
- Soda OS, the exclusive AIoT operating system, and Pop library
- Interpreter-based C/C++ development environments optimized for programming beginners, including Python 3
- A dedicated web browser-based learning environment for training Python 3 and C/C++ simultaneously on PCs and tablets
- mDNS/DNS-SD based distributed name resolution, network service publishing and discovery support
- Open Integrated development environment based on Visual Studio Code for professional application development
- Educational contents for IoT sensor control, multimedia and AI
- Provides 8 types of IoT sensor modules connected to a dedicated expansion interface
- Contains a supercomputer up to 21TOPS supporting all AI frameworks.
The post AIoT Home Trainer appeared first on EDU Market.
]]>Configuration and Practice Environment of AIoT Home
Python and Linux 101
IoT Application Technology
Sensor Control:
File and DB-Based Data Persistence
Audio Recording and Playback
Google Text-to-Speech Converter
Google Assistant and User Device Actions
Camera and Sensor Applications.
AI Technology:
Numpy for Fast Multidimensional Matrix Operations
Pandas for Time Series and Tabular Data Analysis
Matplotlib for Data Visualization
Supervised and Unsupervised Learning
Theory & Practice for Pop.AI-based Linear and Logistic Regression Algorithm
Theory & Practice for Pop.AI-based Perceptron
Theory & Practice for Pop.AI-based ANN, DNN, and CNN
Theory & Practice for Pop.AI & OpenAI DQN-based Reinforcement Learning
Understanding Tensorflow
The post AIoT Home Trainer appeared first on EDU Market.
]]>2- Motor, encoder, and sensor control with a controller.
3- IoT connectivity applications
4- DToF lidar for SLAM.
5- Supports CUDA-based PyTorch and Tensorflow artificial intelligence framework
6- Supports Blockly.
7- Supports ROS2
The post AI Autonomous Driving Vehicle Training Equipment AutoCar III G appeared first on EDU Market.
]]>Operation Program
| List | Specifications | |
| Linux OS | Desktop | X-Server, Openbox, LightDM, Tint2, blueman, network-manager, conky |
| CLI | Zsh, Tmux, Peco, powerlevel9k theme, Powerline fonts, Powerline fonts | |
| Tool Chain | GCC, JDK, Node JS, Python3, Clang | |
| Connectivity | Mosquitto(MQTT), Bluez, mtr, nmap, iptraf, Samba, Blynk Server, Remote Desktop Server | |
| Multimedia | portaudio, sox, OpenCV 4, Google Assistant | |
| Data Science & AI | Python3, Numpy, Matplotlib, sympy, Pandas, Seaborn, Scipy, Gym, Scikit-learn, tensorflow, Keras | |
| Middleware | ROS2, Rviz2, RQt, ament, RTPS, Fast DDS, TF2 | |
| Pop Library | Output Object | Led, Laser, Buzzer, Relay, RGBLed, DCMotor, StepMotor, OLed, PiezoBuzzer, PixelDisplay, TextLCD, FND, Led Bar |
| Input Object | Switch, Touch, Reed, LimitSwitch, Mercury, Knock, Tilt, Opto, Pir, Flame, LineTrace, TempHumi, UltraSonic, Shock, Sound, Potentiometer, Cds | |
| SoilMoisture, Thermistor, Temperature, Gas, Dust, Psd, Gesture | ||
| Multimedia | AudioPlay, AudioPlayList, AudioRecord, Tone, SoundMeter | |
| Voice Assistant | GAssistant, create_conversation_stream | |
| AI | Linear Regression, Logistic Regression, Perceptron, ANN, DNN, CNN, DQN, Object Follow, Track Driving, YOLO | |
| PC linkage development environment | Jupyter Lab | Python3 and Cling support, IPython Widgets, Terminal support, Pop Library support |
| Visual Studio Code Insiders | Remote SSH, Python3 and Debugging support, Terminal support, Pop Library support | |
Block-Based Programming
Training Contents
DDS/RTPS Network-Based Autonomous Driving Vehicle Control in ROS2 Environment
- WSL2-Based Linux Development Environment
- Understanding Python Syntax for ROS2
- Understanding Network Programming for ROS2
- ROS2 Installation and Environment Configuration
- Understanding Node, Topic, Service, and Parameter Action
- ROS2 Build Environment
- Publisher and Subscriber Nodes
- Services and Customized Interface
- Actions and Multi-Node
- Launch and Multi-Execution
- Advanced ROS2
Deep Learning-Based Autonomous Driving Technology
- WSL2-Based Linux Development Environment
- Supervised Learning and Unsupervised Learning
- Linear Regression and Logistic Regression
- ANN, DNN, CNN Basics
- Understanding Machine Learning Framework
- High Speed Multidimensional Matrix Library
- Time Series, Table Data Analysis Library
- Data Visualization Library
- Overview of Autonomous Driving Technology
- Basic Driving and Remote Control
- Collision Prevention and Follow Object
- Transfer Learning
- Advanced Autonomous Driving
Layout
Components
The post AI Autonomous Driving Vehicle Training Equipment AutoCar III G appeared first on EDU Market.
]]>2- Supporting all popular AI frameworks.
3- Lidar and sensors connectivity.
The post AIoT SerBot G appeared first on EDU Market.
]]>- AI application practice equipment based on indoor service robot platform
- Main processor is GPU supercomputer platform for edge device
- 7-inch touch display with 1024×600 resolution and 8M pixel 160° wide-angle camera
- Gigabit Ethernet, dual-band Wi-Fi (2.4GHz, 5GHz), and Bluetooth 4.2
- Voice recognition and audio play through digital microphone and speaker
- Supports various IoT sensor modules through four exclusive expansion interfaces
- 3-axis omni wheel to maximize the movement efficiency and minimize the turning radius
- Multiple PowerPath blocks allowing to practice even while the battery is charging
- Robot standard middleware ROS2 and Pop library are provided
- Supports CUDA-based PyTorch and Tensorflow artificial intelligence framework
- Supports web browser-based Google block coding platform (Blockly)
- Supports a public integrated development environment based on Visual Studio Code for professional application development
- Service robot learning content based on artificial intelligence and deep learning is provided
Software Specifications
Training Contents
- Artificial Intelligence and Autonomous Driving
- 1.1. Components of Autonomous Driving
- 1.2. Autonomous Driving Overview
- Environment for Experiment
- 2.1. AIoT SerBot-G
- 2.2. Communication between PC and AIoT SerBot-G
- 2.3. Development Environment
- Control AIoT SerBot-G
- 3.1. 3WD Omni Wheel Moving Device
- 3.2. 9DOF IMU Sensor
- 3.3. Ultrasonic Sensor
- 3.4. Psd Sensor
- CAN Protocol
- 4.1. CAN Network
- 4.2. CAN Communication
- 4.3. CAN Communication in Linux
- 4.4. Example of CAN Protocol Application
- Moving Device Library based on CAN Communication
- 5.1. Start Library
- 5.2. Moving Device Control Library based on CAN Communication
- 5.3. Implement Sensor Action and Broadcast Reception
- MQTT
- 6.1. MQTT Standard
- 6.2. MQTT Broker and Client
- 6.3. Topic
- 6.4. Session
- 6.5. MQTT Development Environment
- 6.6. Remote Control of MQTT Moving Device
- LiDAR
- 7.1. LiDAR Sensor
- 7.2. LiDAR Control
- 7.3. Avoidance Driving using LiDAR
- Artificial Intelligence
- 8.1. Machine Learning and Perceptron
- 8.2. Neural Network and Learning
- 8.3. Machine Learning Framework
- Autonomous Driving
- 9.1. Vision Processing
- 9.2. Deep Learning and Convolutional Neural Network
- 9.3. Lane Recognition based on Deep Learning
- 9.4. Object Detection and Moving Object Control
Appendix
- A. Flame Sensor
- B. PIR Sensor
- C. ECO Sensor
- D. CO2
- E. Dust Sensor
- F. Thermopile Sensor
- G. Micro Wave Sensor
- H. Peripheral
- I. Pixel Display
Layout
Components
The post AIoT SerBot G appeared first on EDU Market.
]]>2- Linux Kernel API.
3- Image Processing
The post AI Mavin II appeared first on EDU Market.
]]>- User circuit configuration is possible through a breadboard, and application sensor modules are provided to integrate with the ARM Cortex-M processor
- High-resolution dual CSI camera with adjustable angle to enable image processing and deep learning-based vision processing learning is provided
- ARM Cortex-A based high-performance embedded system training Equipment for Linux-based device driver implementation and application
- Main module is an edge supercomputer with a built-in GPU of up to 21 TOPS level. Applications support popular AI frameworks such as TensorFlow2, PyTorch, Caffe/Caffe2, MXNet, Keras, etc.
- Integrated configuration of main module that supports CUDA artificial intelligence acceleration calculation, speaker, digital array microphone, camera, high-precision environmental sensor, and breadboard
- Gigabit Ethernet, dual-band Wi-Fi, and Bluetooth for IoT service to support PLC equipment and OPC-UA communication
- Support for MQTT-based IoT connectivity, OpenCV-based image processing, and QT-based GUI practice in conjunction with device driver
- Support Xeus-python and Cling interpreter for aarch64 and VSCode-based IDE to
enable learning C/C++ and Python 3
Training Content:
The post AI Mavin II appeared first on EDU Market.
]]>The post Developer Kit for OpenVINO™ Toolkit appeared first on EDU Market.
]]>
Toolkit includes reference designs for all the peripherals onboard. It also has a detailed user manual for developers to follow and start building up a system according to their needs immediately.
The Developer Kit for OpenVINO Toolkit is a perfect starting point as OpenCL HPC (High Performance Computing) development platform. It supports Intel FPGA OpenCL BSP for developers to design a system with high level programming language. The computation demanding tasks can be off-loaded from CPU to FPGA, resulting in significant system performance improvement.
Specifications
CPU System:
- CPU: Celeron Dual Core
- Memory:
- 32GB eMMC
- 4GB DDR4
- Interface
- Mini PCIe
- Ethernet
- HDMI
- UART
- USB
- Power Input: 5V DC
FPGA System:
- FPGA: Cyclone V 301K LE
- Memory
- EPCQ256
- 64MB SDRAM
- 1GB DDR3 SDRAM
- Communication
- UART to USB
- GT device supports PCIe Gen2 x4 (GX device supports PCIe Gen1 x4)
- Expansion IO:
- Two 2×40 Expansion IO
- Arduino Uno Revision 3 Expansion Header
- SMA In/Out
- On-Board USB Blaster
- Power Input : 12V DC
- LED/7-Segment/Button/Switch
Block Diagram of FPGA System
Layout
Resources
OpenVINO Development Guide – Download
Developer Kit for OpenVINO Toolkit Quick Start Guide – Download
Kit Contents
- Developer Kit for OpenVINO Toolkit
- USB 3.0 Cable for PCIe Conversion (Installed)
- Mini USB Cable (installed)
- 12V Power Supply (for FPGA Board)
- 5V power Supply (for PC system)
The post Developer Kit for OpenVINO™ Toolkit appeared first on EDU Market.
]]>