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.

CubeSat sets NASA record to Mars

July 24, 2018 | Karen Schultz
Launch Date: May 5, 2018 (with Insight)
Location: Vandenberg Air Force Base, California
Launch Vehicle: Atlas V launch vehicle
Project Manager: Joel Krajewski
Chief Engineer: Andy Klesh

Gumstix Caspa VL camera onboard to snap history

NASA set a new distance record for CubeSats this May when a pair of CubeSats called Mars Cube One (MarCO) reached 621,371 miles (1 million kilometers) from Earth. One of the CubeSats, called MarCO-B used a Gumstix Caspa VL fisheye camera to snap its first photo on May 9, 2018. That photo is part of the process used by the engineering team to confirm the spacecraft’s high-gain antenna has properly unfolded.

Photo Caption: The first image captured with Gumstix Caspa VL camera by NASA’s Mars Cube One (MarCO) CubeSats. The image, which shows both the CubeSat’s unfolded high-gain antenna at right and the Earth and its moon in the center, was acquired by MarCO-B on May 9. Image Credit: NASA/JPL-Caltech

The MarCO spacecraft including the Gumstix Overo IronSTORM-Y are the first CubeSats ever launched to deep space. Most never go beyond Earth orbit; they generally stay below 497 miles (800 kilometers) above the planet. Though they were originally developed to teach university students about satellites, CubeSats are now a major commercial technology, providing data on everything from shipping routes to environmental changes.

If the MarCO CubeSats make the entire journey to Mars, they will attempt to relay data about InSight back to Earth as the lander enters the Martian atmosphere and lands. MarCO will not collect any science, but are intended purely as a technology demonstration. They could serve as a pathfinder for future CubeSat missions.

The MarCO and InSight projects are managed for NASA’s Science Mission Directorate, Washington, by JPL, a division of the California Institute of Technology, Pasadena.

Related Links
For more information about MarCO, visit: go.nasa.gov/marco_launch
A MarCO media reel is available at https://vimeo.com/265040492
Insight Mission to Mars
NASA’s journey to Mars
MarCo Images on PhotoJournal

Share designs in Geppetto

July 20, 2018 | Celine Marie Barrozo

The most requested Geppetto feature is sharing and we’re happy to announce that you can (finally!) share designs with your colleagues! No more sharing of account passwords. Below is a quick guide on how to share designs in Geppetto.

How to share a design in Geppetto

1. Open the design and click on share on the toolbar. OR


Share button in toolbar

Go to the “My Account” tab, select a design and click share.


Share button in My Account

2. Add the name, email address, and a short message to the person you’re sharing the design with. Then, click Send Email. They will receive an email with your message a link to the design.


Share window

3. Your colleague will need to be login in Geppetto to be able to view your design. They will find it under the “Shared with Me” tab. When they open the design, it will be cloned to their workspace and they won’t be able to edit the design you own. Moreover, they will be able to download Autodoc and AutoBSP on your design.

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.

What’s new in Geppetto? Delete and Chat

June 30, 2018 | Celine Marie Barrozo

Every month the Geppetto development team works hard to release new features that our users are asking for and our engineers develop to improve the design to order process. What did we release this month? Delete and Chat functionalities in Geppetto.

Delete

We noticed that one user hsa more than 90 designs in Geppetto already. While each design is unique, what if they would like to delete a design. So our engineers created the Delete Design functionality. To delete a design, go to the My Account tab.

Delete Design

Select the design you want to delete and click Delete Design.

Delete Design Confirmation

NOTE: You will not be able to delete designs you already validated and that are available in the store.

Chat

We want to your design experience to be as simple and fast as possible. For instance support, we have added a Chat widget in Geppetto where you will be able to ask questions, provide feedback, or just talk to someone from Gumstix about what you have in mind.


New Visitor Chat

NOTE: Live chat is only available from 8:30 AM to 5:00 PM (Pacific Time). If you send us a message when we’re offline, we will still receive and respond either via email or in the chat. Our commitment is to respond to you, at most, the following business day.

Please keep in mind that our Customer Success team is located in our Research Center in Vancouver, Canada so they follow the non-working holiday of the region.


Open Chat App

Next Features

I am really excited about the things we’re currently testing for release next month and you’ll definitely hear about it! Do you have a feature in mind? Visit Geppetto and send us a chat or send an email to support@gumstix.com.

Geppetto is our free online design tool that allows you to create a custom hardware design — no electrical engineering required from you. 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, production-ready boards after 15 business days.