BeagleBoneRegistered AI - Fast Track for Embedded Machine Learning

Manufactured By:beagleboard.org
Part Number:BBONE-AI

BeagleBone® AI, a new addition to the BeagleBoard.org® BeagleBone® family, is a high-end Single Board Computer aimed at developers interested in implementing machine-learning and computer vision with simplicity.

BeagleBone® AI is the most powerful BeagleBone® ever developed with dual-core ARM Cortex-A15 running at 1.5 GHz, 16GB on-board eMMC flash, a SuperSpeed USB Type-C interface, Gigabit Ethernet and dual band wireless connectivity. BeagleBone® AI simplify the use of artificial intelligence (AI) in daily application via the TI C66x digital-signal-processor (DSP) cores, two dual-core ARM Cortex-M4 co-processors for real-time control, two dual-core Programmable Real-Time Unit (PRU) subsystems and four Embedded Vision Engines(EVEs) supported through an optimized TIDL machine learning OpenCL API with pre-installed tools. The BeagleBone® AI also has an additional dual-core PowerVR SGX544 3D GPU and a Vivante GC320 2D graphics accelerator. Focused on everyday automation in industrial, commercial and home applications.

BeagleBone® AI comes in a similar form-fact as BeagleBone® Black and compatible with many BeagleBone® Cape add-on boards make it easy to extend the functionality.

Features:

  • TI AM5729 Dual Core ARM Cortex-A15 processor running at 1.5GHz
  • Dual C66 DSP, Four ARM Cortex-M4, Four PRU and Four Embedded Vision Engine
  • Four Programmable Real-time Units (PRUs)
  • Memory: 1GB RAM and 16GB on-board eMMC Flash
  • Connectivity: Gigabit Ethernet, 2.4/5GHz WiFi, and Bluetooth
  • USB Type-C for power and superspeed dual-role controller
  • USB type-A host
  • Audio & Video: microHDMI
  • Headers compatible with manyBeagleBone® Cape add-on boards
  • Zero-download out-of-box software experience

Features

Processor & Co-Processors:

  • Main Processor Features of the AM5729 Within BeagleBone® AI
  • Dual 1.5GHz ARM® Cortex®-A15 with out-of-order speculative issue 3-way superscalar execution pipeline for the fastest execution of existing 32-bit code
  • 2 C66x Floating-Point VLIW DSP supported by OpenCL
  • 4 Embedded Vision Engines (EVEs) supported by TIDL machine learning library
  • 2x Dual-Core Programmable Real-Time Unit (PRU) subsystems (4 PRUs total) for ultra low-latency control and software generated peripherals
  • 2x Dual ARM® Cortex®-M4 co-processors for real-time control
  • IVA-HD subsystem with support for 4K @ 15fps H.264 encode/decode and other codecs @ 1080p60
  • Vivante® GC320 2D graphics accelerator
  • Dual-Core PowerVR® SGX544™ 3D GPU
  • 2x46 expansion headers compatible with many BeagleBone® cape add-on boards
    • 16-bit LCD interfaces
    • 4+ UARTs
    • 2 I2C ports
    • 2 SPI ports
    • Lots of PRU I/O pins

Memory

  • 1GB RAM
  • 16GB on-board eMMC flash

Connectors

  • USB Type-C connector for power and SuperSpeed dual-role controller
  • USB Type-A high-speed host
  • Gigabit Ethernet
  • Serial debug header

Wireless Connectivity

  • 11ac 2.4/5GHz WiFi via the AzureWave AW-CM256SM
  • Bluetooth 4.2 and Bluetooth Low Energy via the AzureWave AW-CM256SM

Out of Box Software

  • Zero-download out of box software environment
  • Self-hosted web IDE with local compilers, libraries and examples
  • Debian distribution (initially version 9.9, 10.0 available)
  • Linux kernel support (initially 4.14, with 4.19 and 5.2 available)
  • Connectivity via USB gadget (network/serial), WiFi access point and station, Ethernet, and serial debug header

Ships With

  • BeagleBone® AI Board
    • Pre-mounted heatsink and antenna
    • Pre-programmed with a Linux distribution, developers can get up and running in 5-minutes
  • Quick Start Guide

Required Tools

Accessory Tools

Documents

Related Blog Posts
  • The great Dobble adventure!

    In January of last 2021, my team created a series of projects documenting how to train a model to play the card game Dobble.  It walks through all of the steps of collecting data, training the model in keras, testing the model, augment...
  • CELLULAR: IOT CONNECTIVITY OPTIONS

    The main purpose of any IoT solution is to get data from the field to the cloud where analysis of the same generates the desired value proposition for the application. With a wide range of IoT connectivity options available, the connectivity decision…
  • Top Findings from Avnet’s 2022 Global IoT Survey

    To keep up with the trends for the Internet of Things (IoT) market, Avnet recently conducted its annual Global IoT Survey and published the results. Respondents were asked a wide range of questions, from business-oriented to technical. The results we…
Anonymous