Making AI Projects Become Easier With NVIDIA Jetson

Hardware development boards became a key enabler for many of recent hardware projects. Such as Arduino and Raspberry Pi, these boards are great for beginners and hobbyists to kick start and bring ideas to reality.

Artificial Intelligence and machine learning are the technologies of the future. So it is important to know how the process goes, and what type of hardware to use. But with the limited computing capabilities of current boards, developers need a powerful and easy to use tools.

Nvidia provides a good solution with its Jetson boards, which are siblings to NVIDIA’s Drive PX boards for autonomous driving. The first board TX1 was released in November, 2015, and now Nvidia has just released the more powerful and power-efficient Jetson TX2 board.

Image credit: Android central

The TX2 is a complete supercomputer. It is a development tool and a field-ready module to power any AI-based equipment. Developers can use it to build equipment around, and also use it itself to run demos and simulations.

Jetson TX2 comes with NVIDIA’s Pascal™ architecture, which boasts 150 billion transistors built on 16 nanometer FinFET fabrication technology.

Some of technical specifications

  • NVIDIA Parker series Tegra X2: 256-core Pascal GPU and two 64-bit Denver CPU cores paired with four Cortex-A57 CPUs in an HMP configuration
  • 8GB of 128-bit LPDDR4 RAM
  • 32GB eMMC 5.1 onboard storage
  • 802.11b/g/n/ac 2×2 MIMO Wi-Fi
  • Bluetooth 4.1
  • USB 3.0 and USB 2.0
  • Gigabit Ethernet
  • SD card slot for external storage
  • SATA 2.0
  • Complete multi-channel PMIC
  • 400 pin high-speed and low-speed industry standard I/O connector
Nvidia Jetson TX1 and TX2 comparision

TX2 has two performance operating modes: Max-Q and Max-P. Max-Q is the TX2’s energy efficiency mode, at 7.5W, this mode clocks the Parker SoC for efficiency over performance (essentially placing it right before the bend in the power/performance curve) with NVIDIA claiming that this mode offers 2x the energy efficiency of the Jetson TX1. In this mode, TX2 should have similar performance to TX1 in the latter’s max performance mode.

Meanwhile the board’s Max-P mode is its maximum performance mode. In this mode NVIDIA sets the board TDP to 15W, allowing the TX2 to hit higher performance at the cost of some energy efficiency. NVIDIA claims that Max-P offers up to 2x the performance of the Jetson TX1, though as GPU clock speeds aren’t double TX1’s, it’s going to be a bit more sensitive on an application-by-application basis.

Image credit: anandtech

Devices such as robots, drones, 360 cameras, medical, etc., can use Jetson for “edge” machine learning. The ability to process data locally and with limited power is useful when connectivity bandwidth is limited or spotty (like in remote locations), latency is critical (real-time control), or where privacy and security is a concern.

Jetson TX2 is available as a developer kit for $500 at arrow.com. In fact, this kit comes with design guides and documentation, and is pre-flashed with a Linux development environment. It also supports the NVIDIA Jetpack SDK, which includes the BSP, libraries for deep learning, computer vision, GPU computing, multimedia processing, and more.

Finally, this video compares Jetson TX1 and TX2 boards:

Node-RED with Raspberry Pi Camera

In this project we’re going to take photos with Node-RED using the Raspberry Pi Camera Module V2. We’re using this application to monitor our 3D printer. You can edit the flow and the template to use the camera in your own projects whether you want to monitor your lab, door or 3D printer.

Node-RED with Raspberry Pi Camera – [Link]

MappyDot – Micro Smart LiDAR Sensor

Blecky @ hackaday.io:

MappyDot is a smart ranging sensor which provides system designers with the ability to measure accurate distances on drones and robotic platforms for collision avoidance, area mapping, distance measurement, gesture recognition and motion sensing. The MappyDot uses the VL53L0X laser time-of-flight ranging sensor from STMicroelectronics, which is a tried and tested 940nm Class 1 laser sensor in use in millions of devices worldwide.

MappyDot – Micro Smart LiDAR Sensor – [Link]

24-48V to 5V – 3A DC-DC Converter

24-48V input voltage range 3A output current DC-DC Converter using BD9G341AEFJ IC from ROHM semiconductor. This IC is ideal for high voltage to low voltage converter with 3A output current. Pin configuration of the board with 3 Pin horizontal mounting of the regulator is similar to LM7805 LDO regulator and is suitable to use this IC as replacement which can provide more current and take high voltage input.

Different voltage output are possible by changing few components. Refer to datasheet for the same. Example circuit can provide 5.1V/3A with input supply range 24-48V DC and operating frequency 200 KHz.

24-48V to 5V – 3A DC-DC Converter – Link

OwnCloud on Raspberry Pi

Install OwnCloud on Raspberry Pi And make your own cloud server.

OwnCloud set on Raspberry Pi can be a good example of smart cloud storage. A cloud storage is a cloud computing model in which the data is stored on remote servers and maintained by a cloud storage service provider. This allows users to customize their data and share it with friends and business partners over the Internet.

OwnCloud as cloud storage server is a great opportunity, especially for those who would like to use OwnCloud on Raspberry Pi (or any other ARM device).

OwnCloud on Raspberry Pi – [Link]

Researchers Developed New Efficient, Thin, and Flexible Cooling Device

Engineers and scientists from the UCLA Henry Samueli School of Engineering and Applied Science and SRI International, California, have created a thin flexible device that could keep smartphones and laptop computers cool and prevent overheating. The component is based on the electrocaloric effect – a phenomenon where the temperature of material changes when an electric field is applied to it. The research has been published in Science.

Thin, flexible cooling device
Thin, flexible cooling device

The system’s flexibility also allows it to be used in wearable electronics, robotic systems, and new types of personalized cooling systems. It is the first demonstration of a solid-state cooling device based on the electrocaloric effect. The method devised by UCLA and SRI researchers is very energy-efficient. It uses a thin polymer film that transfers heat from the heat source – a battery or a processor – to a heat sink, and alternates contact between the two by switching on and off the electric voltage.

Because the polymer film is very flexible, the system can be used in devices with complex shapes or moving surfaces. Body tracking wearable devices can easily accommodate this flexible cooling device. Such cooling pad could keep a person comfortable in a hot office and thus lower the electricity consumption for air conditioning. Or it could be placed in a shoe to keep a runner comfortable while running in the sun. It’s like a personal air conditioner.

The tendency of flexible electronics to overheat remains a major challenge for engineers. The cooling systems in larger devices like air conditioners and refrigerators, which use vapor compression, are just too large for mobile electronics. The new cooling device produces a specific cooling power of 2.8 watts per gram and a COP of 13. This is more efficient and compact than the existing surface-mountable solid-state cooling technologies, opening a path to using the technology for a variety of practical applications.

Roy Kornbluh, an SRI research engineer, said,

The development of practical efficient cooling systems that do not use chemical coolants that are potent greenhouse gases is becoming even more important as developing nations increase their use of air conditioning.

Arduino Two-Way Bluetooth Communication Tutorial

Welcome to another Arduino Tutorial! Today we are going to learn how to use Bluetooth to exchange data between two Arduino boards! As a demonstration project, we are going to build a simple weather station. There is a lot to cover so let’s get started!

Arduino Two-Way Bluetooth Communication Tutorial – [Link]

Design and Implementation of a 12 Lead Portable ECG

Alex Lao and his team at McMaster University have developed a compact, battery powered, 12-lead electro-cardiogram:

During the academic year of 2016-2017 at McMaster University, in conjunction with Dr. DeBruin, Christina Riczu, Thomas Phan and Emilie Corcoran, we developed a compact, battery powered, 12-lead electro-cardiogram. The project won 1st place in the biomedical category at the ECE Capstone Poster Day.

Design and Implementation of a 12 Lead Portable ECG – [Link]

Haasoscope – Cheap, flexible, data acquisition for all!

Haasoscope is the first open-source, open-hardware, flexible, small, cheap, oscilloscope and data-acquisition board. You can use the stock firmware for basic oscilloscope functionality, or modify the firmware to customize what the Haasoscope does.

Preliminary features and specifications:

  • 4 x 100 MHz, 8-bit ADC channels with BNC cable inputs
  • Altera Max10 FPGA with 8k logic elements and 387kb of memory
  • Reprogram firmware over JTAG, or on the fly, with free Quartus II software
  • Readout over serial-to-USB at 1.5 Mb/s, about 20 Hz for 4 channels of 512 samples each
  • USB powered, (or other 5 V input, switchable), ~1.2 Watt
  • 8 x spare digital I/O
  • 9 x additional analog I/O with 1 MHz (1MSPS combined) at 12 bits
  • 7 x programmable LEDs, and a reset button

Haasoscope – Cheap, flexible, data acquisition for all! – [Link]

Arduino Weather Station using DHT11

Using a display to view the temperature and humidity of your environment can be possible using the DHT11 or DHT22 sensor with the easy to use Arduino microcontroller platform and that’s the goal of this project. For this project, we will be using the 16×2 LCD display module to display the temperature and humidity readings gathered from the environment using the DHT11 temperature and humidity sensor.

Arduino Weather Station using DHT11 – [Link]