Under the current Administration, NASA has been tasked with returning American astronauts to the Moon as quickly as possible. The Artemis program would launch a crewed mission to our nearest celestial neighbor as soon as 2024, and establish a system for sustainable exploration and habitation by 2028. It’s an extremely aggressive timeline, to put it mildly.
To have any chance of meeting these goals, NASA will have to enlist the help of not only its international partners, but private industry. There simply isn’t enough time for the agency to design, build, and test all of the hardware that will eventually be required for any sort of sustained presence on or around the Moon. By awarding a series of contracts, NASA plans to offload some of the logistical components of the Artemis program to qualified companies and agencies.
For anyone who’s been following the New Space race these last few years, it should come as no surprise to hear that SpaceX has already been awarded one of these lucrative logistics contracts. They’ve been selected as the first commercial provider for cargo deliveries to Gateway, a small space station that NASA intendeds to operate in lunar orbit. Considering SpaceX already has a contract to resupply the International Space Station, they were the ideal candidate to offer similar services for a future lunar outpost.
But that certainly doesn’t mean it will be easy. The so-called “Gateway Logistics Services” contract stipulates that providers must be able to deliver at least 3,400 kilograms (7,500 pounds) of pressurized cargo and 1,000 kilograms (2,200 pounds) of unpressurized cargo to lunar orbit. That’s beyond the capabilities of SpaceX’s Dragon spacecraft, which was only designed to service low Earth orbit.
To complete this new mission, the company is proposing a new vehicle they’re calling the Dragon XL that would ride to orbit on the Falcon Heavy booster. But even for this New Space darling, there’s not a lot of time to design, test, and build a brand-new spacecraft. To get the Dragon XL flying as quickly as possible, SpaceX is going to need to strip the craft down to the bare minimum.
Back in January when we announced the Train All the Things contest, we weren’t sure what kind of entries we’d see. Machine learning is a huge and rapidly evolving field, after all, and the traditional barriers that computationally intensive processes face have been falling just as rapidly. Constraints are fading away, and we want you to explore this wild new world and show us what you come up with.
Where Do You Run Your Algorithms?
To give your effort a little structure, we’ve come up with four broad categories:
Machine Learning on the Edge
Edge computing, where systems reach out to cloud resources but run locally, is all the rage. It allows you to leverage the power of other people’s computers the cloud for training a model, which is then executed locally. Edge computing is a great way to keep your data local.
Machine Learning on the Gateway
Pi’s, old routers, what-have-yous – we’ve all got a bunch of devices laying around that bridge space between your local world and the cloud. What can you come up with that takes advantage of this unique computing environment?
Machine Learning in the Cloud
Forget about subtle — this category unleashes the power of the cloud for your application. Whether it’s Google, Azure, or AWS, show us what you can do with all that raw horsepower at your disposal.
Artificial Intelligence Blinky
Everyone’s “hardware ‘Hello, world'” is blinking an LED, and this is the machine learning version of that. We want you to use a simple microprocessor to run a machine learning algorithm. Amaze us with what you can make an Arduino do.
These Hackers Trained Their Projects, You Should Too!
We’re a little more than a month into the contest. We’ve seen some interesting entries bit of course we’re hungry for more! Here are a few that have caught our eye so far:
Intelligent Bat Detector – [Tegwyn☠Twmffat] has bats in his… backyard, so he built this Jetson Nano-powered device to capture their calls and classify them by species. It’s a fascinating adventure at the intersection of biology and machine learning.
Blackjack Robot – RAIN MAN 2.0 is [Evan Juras]’ cure for the casino adage of “The house always wins.” We wouldn’t try taking the Raspberry Pi card counter to Vegas, but it’s a great example of what YOLO can do.
AI-enabled Glasses – AI meets AR in ShAIdes, [Nick Bild]’s sunglasses equipped with a camera and Nano to provide a user interface to the world. Wave your hand over a lamp and it turns off. Brilliant!
You’ve got till noon Pacific time on April 7, 2020 to get your entry in, and four winners from each of the four categories will be awarded a $100 Tindie gift card, courtesy of our sponsor Digi-Key. It’s time to ramp up your machine learning efforts and get a project entered! We’d love to see more examples of straight cloud AI applications, and the AI blinky category remains wide open at this point. Get in there and give machine learning a try!
Ecology is a strange discipline. At its most basic, it’s the study of how living things interact with their environment. It doesn’t so much seek to explain how life works, but rather how lives work together. A guiding principle of ecology is that life finds a way to exploit niches, subregions within the larger world with a particular mix of resources and challenges. It’s actually all quite fascinating.
But what does ecology have to do with Luka Mustafa’s talk at the 2018 Hackaday Belgrade Conference? Everything, as it turns out, and not just because Luka and his colleagues put IoT tools on animals and in their environments to measure and monitor them. It’s also that Luka has found a fascinating niche of his own to exploit, one on the edge of technology and ecology. As CEO of Institute IRNAS, a non-profit technology development group in Slovenia, Luka has leveraged his MEng degree, background in ham radio, and interest in LoRaWAN and other wide-area radio networks to explore ecological niches in ways that would have been unthinkable even 10 years ago, let alone in the days when animal tracking was limited by bulky radio collars.
The Broadband Internet Service BenchMARK is an open source initiative to put tools in the hands of the common Internet user that will make measurement and analyzation of home network traffic easier. It targets LAN and WAN network utilization by measuring latency, packet loss, jitter, upstream throughput, and downstream throughput. Of course gathering data isn’t worth anything unless you have a way to present it, and to that end the Project BISMark team has been developing a web interface where you can view the usage of anyone who’s running the firmware.
The project builds on top of OpenWRT, which means that you should be able to run it on any router that’s OpenWRT compatible. This includes the ubiquitous WRT54G routers and many others. We remember when DD-WRT added bandwidth monitoring as part of the standard release, which really came in handy when the stories about ISP bandwidth capping started to hit. We’re glad to see even more functionality with this package as it can be hard to really understand what is going on in your network. After the break you’ll find a video detailing the features of BISMark.
[GuySoft] threw together a cellphone-based SMS gateway that allows him to push text messages to Twitter. Once up and running, it can be used by multiple people, either with shared or individual Twitter accounts. At its core, this setup uses the cellphone as a tethered modem on a Linux box. The open source software package, Gammu SMSD, provides hardware hooks for phones running in modem mode. The package is already in the Ubuntu repositories but it runs cross-platform and can be downloaded from the project site. This gave [GuySoft] the ability to script a framework that checks for received SMS messages, compares the incoming phone number for a match on a saved list, then pushes the message from a confirmed number to Twitter via their API.
A web interface is used to register new numbers and associate them with Twitter accounts. On the back-end, [GuySoft’s] own Python script handles the translation of the message. You can download all of the code, and get more insight on setup from the readme file, over at the GitHub repository.
[Matt Richardson] built this on-air light to indicate whether a Make streaming show is currently in progress. Despite the obvious cord leaving the bottom of the base (it’s a power cord) his creation is pulling data from the Internet wirelessly. He’s using an Xbee module along with an Arduino to pull this off.
In addition to the light itself there’s a base station that we haven’t seen before. The hardware is a Digi ConnectPort Zigbee-to-Internet Gateway. That’s a mouthful but it’s just a box that acts as an Xbee node and facilitates communication between its own Ethernet port and other Xbee devices in the network. So no, you don’t need a computer but you do need an Ethernet connection somewhere for the base station. [Matt] is running an open source software package on the ConnectPort call Xbee Internet Gateway (xig). Watch the video after the break to see the configuration for this package. It’s a snap, and if you’ve never used an Xbee module before this gives you a good idea of how easy it really is.