AeroCore 2 for NVIDIA Jetson in action!

September 14, 2018 | Celine Marie Barrozo

On a beautiful summer day in Canada (where our Research Center is located), our engineer, Andrew Smith, decided to demo the AeroCore 2 for NVIDIA Jetson in the field. This board has our Caspa HD Camera and is running Tensor Flow for object detection and recognition.

Watch it in action

See it in the lab

On top of our own testing, the AeroCore 2 for NVIDIA Jetson was tested by Technology Editor of Electronic Design, William Wong.

“The Gumstix carrier board is designed for drones and robots but it can be used for other applications where bringing the compute power of the Jetson TX1 or TX2 to bear can be invaluable. This nice thing about the Jetson is that the applications that ran on the development board work well with the Gumstix platform.”

– William Wong, Technology Editor at Electronic Design

Geppetto Limited Offer: 2 Designs for 1 Manufacturing Fee

September 10, 2018 | Celine Marie Barrozo

We are giving you an opportunity to prototype 2 designs for 1 manufacturing fee.

Yes, that’s right, you can order 2 different designs for only $1999 and with the same lead time of 15 business days.

Why are we doing this?

Simple, we want to help you get to market as fast as possible. We know how expensive and time consuming it is to compare which COM or processor you want OR confirm which components meet your requirements exactly. We want to help YOU do these things better, faster.


  • Build 2 Geppetto boards for a single manufacturing fee of $1,999.00.
  • Designs must be ordered at same time in one order.
  • Each design requires a minimum order of five units.
  • Use the discount code Geppetto2for1 at checkout to activate the offer.
  • For a repeat order, standard setup fee will apply. See Geppetto Orders page.
  • Offer valid until December 31, 2018.

What are you waiting for? Start a free design today.

Want a demo?
Send a request.

I urge you to maximize this limited offer! This is our way of communicating to the world that Geppetto is not another online CAD tool. It’s MUCH more than that. Geppetto is here to make sure you get a custom board (not just PCB) you can work with in 15 business days.

Too good to be true? Read Bruce’s Story.

Geppetto is our free online design tool that allows you to create a custom hardware design. Moreover, we handle everything, from sourcing of parts to production, to ensuring that your board boots out of the box. We take care of production while you focus on your software or application. We will deliver your pre-tested, fully assembled boards (not just PCB) after 15 business days.

Customer Review: Geppetto Guarantees What Gets Delivered Works

August 29, 2018 | Celine Marie Barrozo

Why use Geppetto?

From a customer who used and loved it!
Geppetto has been serving customers since 2013. In that time, we’ve had many customers, but it’s a challenge for us to find one willing to share their story due to NDAs.

Without breaking any NDA, I interviewed Geppetto customer, Bruce R. Koball on his Geppetto experience.

About Bruce

Bruce is an independent engineering consultant based in Berkeley, California, specializing in embedded systems hardware and software. With more than 40 years of experience under his belt, Bruce was impressed with Geppetto!


He works on different kind of projects, often simultaneously. Right now, he is working on a cryptographic signing appliance based on the Raspberry Pi Compute Module 3. Originally, he was planning to design the board from scratch with an estimated cost of $20,000 USD for engineering, a project timeline of 6-12 months, and at least two spins of the PCB.

Yes, it’s difficult, expensive, and it takes a long time to build a customized board.

Geppetto and Bruce

Bruce was searching for solutions that used the RPi CM3 board and he found Gumstix. He was looking at our off-the-shelf boards which are all designed in Geppetto and found the Geppetto app there. Below are things we asked him:


You found Geppetto, what made you decide to contact us?

It’s an interesting approach and I wanted to learn more. I called customer support to see if Geppetto was real or smoke and mirrors. And, I am usually able to gauge vendors by how they interact with me.

What made you decide to use Geppetto?

After our call, I sent you a requirements list and that same day you sent back a preliminary design with a guarantee that what you delivered would work or Gumstix would fix it. It was too good to be true. I was ready to be impressed.

How was the experience of designing using Geppetto?

It was remarkably easy, especially with your support. It’s a building-blocks approach using modular functions that the designer selects from a library. Unlike using a traditional PCB CAD tool where one usually has to define every part of the circuit from scratch, Geppetto’s modules are complete functional circuits that are well characterized and ready to be inserted into a design; I am sure your engineers spent many hours building this library. All the designer has to do is define the functions required for the design, select them from the library, drag them onto the board, and satisfy the modules’ dependencies with a connect-the-dots interface.

Drag and drop modules to Geppetto board
Satisfy module dependency with a connect-the-dots interface

What are the things you want to change in Geppetto?

I’d like to see more modules in the library; things like networking components (ethernet switches, etc.), other I2C and SPI–based analog sensors, etc. Perhaps you could offer qualified engineers the ability to define their own functional modules; simple circuits like bit-banging logic functions or analog signal conditioning functions using an enhanced Geppetto interface, under NDA.

What was the deciding factor in choosing Geppetto for the project?

Your team answered as many questions as I had so that built confidence in the Gumstix/Geppetto system. But the key factor was the bottom line: the non-recurring engineering investment (NRE) and unit price for an assembled, tested board with a working Linux build was so low that it was worth a try, just as a proof-of-concept prototype, even if it didn’t work out for the finished product. Fortunately for us it yielded a finished working product for a fraction of our initial budget.


After you placed an order and received your board, what was your initial impression of the quality and performance of the board bring up of the device?

It worked the first time I powered it up. I plugged in a keyboard, mouse, HDMI monitor, and microSD card with the system image, and it booted Raspbian Linux right up. I was writing and running code on it immediately. I connected the ethernet to my network and it worked. I tested the peripherals (I2C GPIO expander, RTC, RS232 port, codec) and they all worked. I was so impressed I almost fell over!

Were there any changes to project timeline and cost?

It changed from months to weeks and from an estimate of $20,000 to roughly $4,000 (NRE plus 10 working boards). It saved us time and money.

Before Geppetto After Geppetto
Estimate Cost $20,000 $4,000
Project Timeline 6-12 months 3 weeks
Number of PCB spin 2 1

Sharing Geppetto

Would you recommend Geppetto to customers, colleagues, and friends?

I already have! My engineering colleagues and friends were quite impressed when I told them the price point for an assembled, tested board, with a function Linux build. As I said earlier, it would be worth it simply as a proof-of-concept. The $2000 NRE cost is a bargain; a price point that most people would be more than comfortable with to get them to 75% to 100% of their project.

Why do you think people should use Geppetto?

If your collection of modules can solve their problem and meet their requirements, it’s a no brainer. Are you familiar with the phrase “shaving the yak”? It’s a metaphor for the seemingly endless series of small tasks that have to be completed before a project can move forward from one step to the next. Geppetto solves a lot of that for electrical engineers.

Start a Free Design

How do you recommend or explain Geppetto to others?

It’s a board design and manufacturing service using a browser-based CAD interface that allows customers to create a PCB using a “building-block” approach. The designer selects a set of predefined functional modules from an extensive library, satisfies each module’s dependencies by “connecting the dots,” then, after a minimal lead-time, receives assembled and tested units (with software!). It could not be simpler.

Thanks for sharing your thoughts and time with us Bruce. It was a delight working with you and we couldn’t be happier to help you and your customer save time and money with your Geppetto board.

If you’re looking for an embedded hardware and software consultant, be sure to let us know and we’ll happily refer you to Bruce.

Are you a Geppetto customer who wants to share your story with us? Send us an email at with the subject: Geppetto Success Story.

Geppetto is our free online design tool that allows you to create a custom hardware design. Moreover, we handle everything, from sourcing of parts to production, to ensuring that your board boots out of the box. We take care of production while you focus on your software or application. We will deliver your pre-tested, fully assembled boards (not just PCB) after 15 business days.

Gumstix Intern Kenny Akers Tackles the Aerocore 2 for NVIDIA Jetson

July 26, 2018 | Keith Lee

Kenny Akers is a rising senior student at Woodside Priory High School in Portola Valley California and 3-year veteran of the FIRST Robotics Competition — An international contest of wits to see which team of High School students can custom-build a robot to complete a complex task. When Gumstix released the Aerocore 2 for NVIDIA Jetson we called upon his experience, skill, and enthusiasm to demonstrate its potential in robotics and automation. He aims to demonstrate its ability to drive autonomous problem solving in robotics through computer vision and deep learning.

Steam Bot Willie, Team 751’s 2017 submission for the FIRST robotics competition

Kenny is your average high school kid, enjoying running, music and hanging out with his friends, but he is also a self-professed, self-taught tinkerer and software developer. His interest in Arduino, C++, and Raspberry Pi eventually led him to us, and he promptly got himself a seat at the table. Now he is interning here for the second consecutive summer and applying his skills to the Aerocore 2 for Jetson. “I knew about the Jetson platform through the FIRST competition, where a few teams [were] using it for computer vision,” he shared, “Coupled with TensorRT and NVIDIA’s support for AI applications, the Jetson is the optimal platform for my purposes.

Kenny’s Aerocore 2 wired up for test

Diving headlong into deep learning, Kenny has already brought up a convolutional neural network, using TensorFlow as the backbone, that uses our Caspa HD camera module and the Aerocore 2 for NVIDIA Jetson to identify and classify up to 80 objects concurrently, and in real-time.


His goal is to demonstrate the capabilities of the NVIDIA Jetson TX2, coupled with the Aerocore 2 platform, to his team and incorporate it into their design for this year’s FIRST robotics challenge, so he has set aside the object classification for now to work on interpreting the AI’s output and translating it into robotic actions. As a proof of concept, he hopes to have an iRobot Create 2 navigate to an object of specific class and interact with it, which at this point could be as simple as turning on an LED.

Early demo of Kenny’s progress with OpenCV and TensorFlow on Aerocore 2 for Jetson

He won’t find out until January what his challenge will be, and then he and his team will have 6 weeks to fund, design, program, and test his bot before the competition begins in earnest. His work this summer, he hopes, will be helpful in improving the design’s autonomous performance at the competition.


Developing on the Jetson has proven to be far more agreeable than he had initially expected. “Besides a few technicalities with configuring library backends and getting a sufficient camera stream, I was surprised by the relatively low amount of hurdles I encountered compared to other embedded systems,” he confessed. NVIDIA has done a great job of documenting and supporting the Jetson TX series compute modules and has made the lives of developers of varying skill the better for it.

Aerocore 2 for NVIDIA Jetson TX2 with Caspa HD camera module identifying Kenny’s cellphone

Working with Aerocore 2, a Geppetto-designed board, has left a good impression on this high school self-starter. “I think Gumstix offers a level of customizability in the field of embedded computing that I am yet to see by other entities. Especially with Geppetto, the ability for a client to tailor a design to their application is very useful.

Kenny is the first, and definitely not the last, to employ the Aerocore 2 for NVIDIA Jetson for combining edge AI and robotics. And there is no reason to stop there. In the past, Geppetto and Geppetto-designed boards have been used by Yale undergrads to teach grade school students the fundamentals of computers.

Gumstix is lucky and grateful to have Kenny here working with NVIDIA Jetson and we are excited to see what he does with the Aerocore 2 for Jetson. Gumstix will be following his progress enthusiastically as he and his team take on the FIRST Robotics Challenge in January.

Customize Robotics and Edge Computing with NVIDIA® Jetson™ in Geppetto!

July 25, 2018 | Karen Schultz

We added the most powerful COM connector in Geppetto to date with the NVIDIA® Jetson™ COM Connector. With this addition, you can now design a custom robotic or AI board and plug in either the NVIDIA Jetson TX1, TX2, or TX2i to your project.

NVIDIA Jetson in Geppetto

The NVIDIA Jetson COM Connector is available under the COM Connector shelf in Geppetto. You can create a design in minutes and add the modules available on the Geppetto library like 4 cameras, HDMI, among other things that will allow you to design your own robot, edge computing design, or anything you can think of.

NVIDIA Jetson COM Connector

Aerocore 2 for NVIDIA® Jetson™ designed in Geppetto

To showcase the super computing of the NVIDIA Jetson, we designed the AeroCore 2 for the NVIDIA® Jetson™.

These latest addition to the Aerocore 2 family and Geppetto will bring the NVIDIA Tegra’s 256 CUDA cores to a multitude of robotic designs, along with up to 4 HD camera modules, USB 3.0, LTE connectivity, and micro-HDMI. Perform on-board image recognition and deep learning in robotics or aerial design with the Aerocore 2 for NVIDIA® Jetson™ priced at $275.00.

AeroCore 2 for NVIDIA Jetson in Geppetto

The Gumstix Aerocore 2 product line, developed in Geppetto®, is a proven robotics design combining real-time autopilot firmware and high-level processing capabilities, employing an ARM Cortex M4 microcontroller with PX4 firmware, PWMs, serial buses, and GPS along with powerful Linux devices.

Customized in Geppetto

Geppetto is our free online design tool that allows you to create a custom hardware design. Moreover, we handle everything, from sourcing of parts to production, to ensuring that your board boots out of the box. We take care of production while you focus on your software or application. We will deliver your pre-tested, fully assembled boards (not just PCB) after 15 business days.