All Projects → antmicro → Jetson Nano Baseboard

antmicro / Jetson Nano Baseboard

Licence: apache-2.0
Antmicro's open hardware baseboard for the NVIDIA Jetson Nano and Jetson Xavier NX

Projects that are alternatives of or similar to Jetson Nano Baseboard

Awesome Learning Resources
🔥 Awesome list of resources on Web Development.
Stars: ✭ 3,928 (+1779.43%)
Mutual labels:  ai, open-source
Pconv Keras
Unofficial implementation of "Image Inpainting for Irregular Holes Using Partial Convolutions". Try at: www.fixmyphoto.ai
Stars: ✭ 786 (+276.08%)
Mutual labels:  ai, nvidia
Anakin
High performance Cross-platform Inference-engine, you could run Anakin on x86-cpu,arm, nv-gpu, amd-gpu,bitmain and cambricon devices.
Stars: ✭ 488 (+133.49%)
Mutual labels:  ai, nvidia
Openvoiceos
OpenVoiceOS is a minimalistic linux OS bringing the open source voice assistant Mycroft A.I. to embbeded, low-spec headless and/or small (touch)screen devices.
Stars: ✭ 64 (-69.38%)
Mutual labels:  ai, open-source
Mycroft Core
Mycroft Core, the Mycroft Artificial Intelligence platform.
Stars: ✭ 5,489 (+2526.32%)
Mutual labels:  ai, open-source
Webots
Webots Robot Simulator
Stars: ✭ 1,324 (+533.49%)
Mutual labels:  ai, open-source
Opensteer
OpenSteer is a C++ library to help build steering behaviors for autonomous characters in games and animation.
Stars: ✭ 202 (-3.35%)
Mutual labels:  ai
Android
📱 Nextcloud Android app
Stars: ✭ 2,669 (+1177.03%)
Mutual labels:  open-source
Qtwebflix
A qt webengine program for netflix
Stars: ✭ 202 (-3.35%)
Mutual labels:  open-source
Nvidia Sniper
🎯 Autonomously buy Nvidia Founders Edition GPUs as soon as they become available.
Stars: ✭ 193 (-7.66%)
Mutual labels:  nvidia
Compose
A machine learning tool for automated prediction engineering. It allows you to easily structure prediction problems and generate labels for supervised learning.
Stars: ✭ 203 (-2.87%)
Mutual labels:  ai
Code Samples
Just some code samples for MahApps and other experiments...
Stars: ✭ 205 (-1.91%)
Mutual labels:  open-source
Rl trading
An environment to high-frequency trading agents under reinforcement learning
Stars: ✭ 205 (-1.91%)
Mutual labels:  ai
Pine
🌲 Aimbot powered by real-time object detection with neural networks, GPU accelerated with Nvidia. Optimized for use with CS:GO.
Stars: ✭ 202 (-3.35%)
Mutual labels:  nvidia
Learnopencv
Learn OpenCV : C++ and Python Examples
Stars: ✭ 15,385 (+7261.24%)
Mutual labels:  ai
Simple App Launcher
A simple holder for favourite apps for quick & easy app launcher icon management
Stars: ✭ 202 (-3.35%)
Mutual labels:  open-source
Depthai
DepthAI Python API utilities, examples, and tutorials.
Stars: ✭ 203 (-2.87%)
Mutual labels:  ai
Nextcloud Spreed Signaling
Standalone signaling server for Nextcloud Talk.
Stars: ✭ 201 (-3.83%)
Mutual labels:  open-source
Funding
Let's get open source maintainers paid ✨
Stars: ✭ 205 (-1.91%)
Mutual labels:  open-source
Netron
Visualizer for neural network, deep learning, and machine learning models
Stars: ✭ 17,193 (+8126.32%)
Mutual labels:  ai

================================= Jetson Nano / Xavier NX baseboard

Copyright (c) 2020-2021 Antmicro <https://www.antmicro.com>_

.. image:: Images/jetson-nano-baseboard.png :scale: 40%

Overview

This repository contains open hardware design files for a baseboard supporting the NVIDIA Jetson Nano and Xavier NX SoMs. It's been created by Antmicro <https://antmicro.com>, a custom hardware, software and AI engineering company and a Jetson ecosystem partner of NVIDIA <https://nvidia.com>. The board can be interfaced with MIPI CSI-2 video devices through a unified Flexible Flat Cable (FFC) connector, supporting up to 4 sensors in a 2-lane configuration or 3 sensors in a 4-lane configuration. Please refer to the Jetson Nano OEM Product Design Guide for more details regarding the supported CSI lane mappings.

The baseboard, its custom variants designed by Antmicro per customer's specification, and essential accessories can be purchased from Capable Robot Components <https://capablerobot.com/products/nx-baseboard/>_.

Repository structure:

The main repository directory contains the Altium PCB project file, the Outjob file, LICENSE and README. The remaining files are stored in the following directories:

  • PCB - contains all Altium design files
  • Libraries - contains the component libraries
  • Documentation - contains selected files for device fabrication (schematic in PDF, BoM) generated from the Altium project
  • Images - contains graphics for this README
  • 3DModels - contains files defining the mechanical model <3DModels/Jetson_Nano_Baseboard-Rev.1.4.7.stl>_ of the assembled board

Key features

  • Jetson Nano / Xavier NX SO-DIMM connector
  • Gigabit Ethernet RJ45 connector
  • Micro USB debug connector
  • USB-C DFP (Host) port
  • Mini HDMI video output interface
  • Mini DisplayPort video output interface
  • 2x 50-pin FFC connectors exposing up to 4 MIPI CSI-2 camera interfaces
  • M.2 (key M) connector exposing PCIe x4 interface
  • RTC battery backup
  • EEPROM for storing board ID/SN

The PCB project files were prepared in Altium Designer 14.1.

Board layout & dimensions

The picture below presents a general layout of the PCB with marked I/O interfaces.

.. figure:: Images/jetson-nano-layout.png

Getting started

The board can be produced and assembled using the provided design files. Please take a look at the mechanical layers for more information regarding the PCB stackup recommended for fabrication. The board can be powered by a voltage in the 6-36VDC range. It is recommended to use a 12V 2A DC supply to power the board. The board has an integrated power sequencer that starts the module automatically right after applying power supply.

BSP

The baseboard's IO interfaces are supported in the standard Linux for Tegra (L4T) BSPs <https://developer.nvidia.com/embedded/linux-tegra>_ provided by NVIDIA for Jetson Xavier NX / Nano. The BSP should work with the open source Jetson Nano / Xavier NX Baseboard out of the box. However, to use the baseboard with various cameras and other accessories you may need to make modifications. If you plan to use the board with Allied Vision Alvium <https://www.alliedvision.com/en/products/embedded-vision-solutions/alvium-camera-modules-for-embedded-and-machine-vision-applications.html>_ image sensors, there is a linux-patches directory, which contains patch files that add support for the Allied Vision cameras for this baseboard with the Nano NX module. The patches are named with the L4T release and can be applied to corresponding branches of the Linux repository <https://github.com/alliedvision/linux_nvidia_jetson>_ released by Allied Vision. Antmicro's services involve BSP development so you can hire us to the necessary modifications for you.

You can use the USB OTG interface connector to upload a BSP image to a SoM inserted into the baseboard.

Debug UART connection

Most of the debug messages are provided through the serial console. The board includes an FTDI chip providing the UART interface to the host PC. Please refer to the schematic sheets for more details. The default debug UART channel is accessible through /dev/ttyUSB0 (assuming that there are no other FTDI units connected to your PC). The default baudrate for serial debug connection is 115200 baud with an 8-bit transmission, 1 stop bit and with no flow control.

Revision info

The latest revision of the PCB includes the following changes and amendments:

  • Introduced an 8-layer PCB stackup for a better separation of PCIe lanes
  • Rotated the M.2 connector by 180 degrees to keep it away from the on-board DC/DC
  • Changed the stacking height of the M.2 connector
  • Simplified the M.2 supporting circuitry
  • Exposed the CSI-G and PCIE1 interfaces on the Jetson Xavier NX <https://developer.nvidia.com/embedded/jetson-xavier-nx>_
  • Updated FAN control circuitry
  • Changed GPIO assignment for camera-triggering signals
  • Optimized board cutout for the DisplayPort connector
  • Fine-tuned selected footprints to improve the reliability of the reflow soldering
  • Changed power sequencing of the on-board DC/DC converters
  • Fixed TPD8S009 footprint
  • Removed MicroSD card socket
  • Updated USBC_VBUS control circuitry
  • Added EEPROM for SN/ID storage

Please check the releases <https://github.com/antmicro/jetson-nano-baseboard/releases>_ for a brief summary of major changes introduced in previous revisions.

License

Apache-2.0 <LICENSE>_

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].