Cornell Builds Autonomous UAV

tshak writes "From Microsoft Research, 'Faculty and students at Cornell University have built an unmanned airplane with its own on-board, embedded control system. The large-scale model plane flies by accessing coordinates from an off-the-shelf GPS unit.' Not only does the plane run XP embedded, but the software is written in C# on the .NET Compact Framework. This is all powered by an 800mhz Crusoe processor with 1GB of total system storage."

Blue Sky of Death?

Duck!

Brings new meaning....

...to the term "crash"

Re:Brings new meaning....

Not to mention the use of embedded XP - hopefully it won't be embedded in the ground...

*rimshot*

Ugh.

I fear the onslaught of 1001 jokes about this plane crashing.

Re:Kick back?

Nothing so "shady"...

Award of academic grant. [microsoft.com]

The article itsself states: Last year, the group won an Innovation Excellence Award from Microsoft Research to continue their previous work in designing an autopilot system for a large scale model aircraft. Schools around the globe received awards from the Microsoft Research University Relations program to enable them to conduct research in emerging technologies.

So they are up front about it - I personally think this is interesting - doesn't matter that they used XP-Embedded over another operating system - whatever gets the job done.

Re:Kick back?

Why do most people here seem to concentrate not on the fact that something very cool was accomplished, but rather on the fact that it was accomplished using technology from a vendor they don't like?
</rhetorical>

How about commenting on the project itself rather than posing conspiracy theories? The article itself even mentions that the team had gotten previous awards from Microsoft.

Re:Kick back?

They use XP embedded because you can write complex applications and do lots of programming without re-inventing the wheel.

In this case, I think XP + .NET is a great choice instead of using a simple microcontroller with assembler code. Why?

1. Device drivers. They are using a wireless modem to get data back and forth to the ground. That's important.

2. Telemetry. The plane fly's itself without help from the ground. This isn't often done. Most of these projects the plane is a dumb terminal to a complex application running on the ground. This way is the exact oppsite. The ground system gives the plane mission goals, and the plane and it's onboard "overhead" process the goals and determine what actions are needed to get there. The goals are things like "fly between nav point 1 and 2, then directly proceed to nav point 3".

3. Advanced image processing. One of the goals of the project is to recognize objects on land. Other systems have to take a picture, transmit back to the ground station for processing. On this one the plane can do it right away, and proceed to their next point without the latency (which is significant) of transmitting back and forth.

4. Robustness. Their plane is better than most others because it can operate with very little supervision from the ground. That's pretty important step forward. It can land itself in the case of something going wrong, the plane's flight hardware failing, etc.

You really have to have tried to do something like this before to appreciate the difficulty of having an autonomous plane like this. Even the Pentagon/CIA recognizes the trouble involved. The first UAV's were basically just remote controlled. They spent two years making them more autonomous which to me is a big deal.

Lastly I doubt many people here would consider an "award from Microsoft" as being much of anything to brag about.
You mean most people wouldn't like to get cash to work on cool geek projects you want to be working on anyways?

Re:Kick back?

Right, so I'm actually on the team.

Rather than you all speculate (rather sarcastically and incorrectly) about how we do things, why don't I actually tell you? :)

First off: We couldn't have written the software without XP Embedded. Just to get that out in the open. Couldn't have done it.

Testing code on custom chips is *slow* (We have a couple systems that use custom ATMEL 8-bit microprocessors). If we had to write the bulk of our flight control software on those, we'd never get anywhere.

With XP Embedded, we were able to write our code on normal Windows desktops, and run it right there in simulator mode. Once we got as many bugs worked out there as we could, then we could move it down onto the plane.

Also, we use a *lot* of hardware. Sure, it's possible that we could've hand-written assembly language for ATMEL chips to do everything. Turing completeness states that's a truth. But realistically speaking, we'd never get it done before we graduated. For one thing: We have a wireless modem link to a ground station that can monitor the plane. It was hard enough designing a protocol and implementing that to get the data down to the ground. The last thing I wanted to do on top of this is write the driver for the serial modem itself!

Since we were able to take advantage of existing development tools, though, that inital hurdle was quickly cleared.

As for whomever thinks we fly the plane "using flight simulator:"

It's really much simpler than that.

The plane flies itself by its knowledge of its position through GPS and its orientation through a gyro.

Before the plane launches, we feed it in a set of GPS waypoints we want it to fly through. (The flight control protocol we're shooting for next year will allow in-flight course changes.) The plane sees its position, sees where it wants to be next, and goes there. No flight simulator involved. If the target is to the plane's left, it flips the ailerons and it turns left. That's all it does.

That having been said, we did use Flight Simulator for testing. Our software was able to fly planes around in Flight Sim 2004 long before we loaded it into the real plane -- an enormous time, money, and effort saver.

Re:1 GB?

Engine control software decides what the engine will do based on what the operator is doing. The controls for a UAV ARE the operator. Big difference.

Re:1 GB?

Half of that memory is used as a flight recorder. Like it says in the article [microsoft.com].

Re:1 GB?

Oh of course -- because a technology demo -- like a UAV that flies itself-- is completely unimpressive unless it's hyperefficient and has a tiny footprint.

Give me a break, man. It's a STUDENT PROJECT. They probably had a few months to do it. And you expect them to build their own OS and heavily optimize code? The REASON they used embedded XP/C# (besides getting them free from MS) was that they are efficient environments for rapid development that are easy to learn. There's very little bizarre apocrypha in C#, and when you're strapped for time that's way more important than impressing embedded developers.

Re:Instead of the usual...

XP embedded is quite robust due to its scalability.

When creating an version of it for a machine, you can pick and choose what you want to use and contain. "Lets see... I do not want FAT/FAT32 support but I do want NTFS... no need for a GUI display here... yea... better leave out sol. and calc.exe."

The setup system for XPE is quite powerful and when you decide to add or remove one component, it'll tell you everything that it depends on and that depends on it to ensure that dependencies are satisfied.

Because of this scalability, you can strip down an XPE install to practically nothing, with no unnecessary processes/apps in the background and only what you want running you end up with a very stable system.

Did they read the eula?

Haven't seen the EULA for XP embedded but the consumer one says do not use for 'mission critical' applications. somehow an airplane seems kinda critical? sounds more like VxWorks or QNX would be appropriate.

Unknown Error

"Hello, this is your pilot software speaking. We've encountered an unknown error as a result from an unknown error.

Please click OK to crash."

Wow

11 out of 14 posts so far have been modded down as Flamebait, Troll, Redundant, or Off Topic. Is this usual? In any case, how long until these little plains are fitted with a collision detection and avoidance system? Flying based on checkpoints is all fine and well if you're the only one in the sky, but othrewise its equivalent to a blind person without a dog or a cane walking down a street he knows very well.

Cruise missile

And the difference between this and a cruise missile [bbc.co.uk] is what exactly?

Trans Atlantic Model

Small GPS controlled planes are old news. Check out the TAM project. Trans Atlantic Model. They flew a model plane across the Atlantic Ocean last year. Check it out here -> http://news.bbc.co.uk/2/hi/europe/3145577.stm [bbc.co.uk]

CUUAV

One of my friends is one of the leads on the project for Cornell University. He was the one who designed the site and a bunch of other things on the plane.

Yes, they were given grant money from Microsoft, but that wasn't the only influence in their decisions. They've put long hard hours into the plane. XP Embedded does allow them to add functionality to the plane. A lot of companies have given then grants and sponsorships that have allowed them to build the plane. Don't forget this is Cornell here and they're not going to just rely on Microsoft to make the plane run. They also weren't attempting to make a "real" plane - this is still an UAV which isn't meant to have the power of a full aeronautical vehicle.

Unfortionatly one of their planes was destroyed in a fire at a hotel in Maryland while they went down to show off the plane. Luckily, their backup plane that is still being built was not destroyed.

Make way...

for the first airborne trojan horse !

Now all it needs is WiFi, and it can mass infect :-)

Mean-spirited

Not to come over all gee-whiz and so on, but how relentlessly negative these posts are. The students deserve some congratulations for successfully completing an impressive piece of work. Maybe they didn't go the most efficient/difficult/brag-worthy route. So what? Everything they've learned will be useful, regardless of what hardware/software they end up using in the 'real' world. They probably had fun and have achieved something real, instead of just sitting back criticising.

Good point about the cruise missile though...

Re:Mean-spirited

Yes - at least they produced something original. :-)

Congratulations to them.

OTOH, if they had used Linux, everyone would have just gone on about how great it was that they'd used Linux, not how clever that they'd got the UAV to work. Can't win...

Re:Mean-spirited

That's the thing - they did use the most efficient/difficult/brag-worthy route to completion. Any other route (including linux) would have required a LOT more work, more than they could have been expected to do. Crusoe chips and 1gb of memory could fit in your hand and you'd not notice. We're talking two small wafers of electronics. They didn't bolt a P4 to the side, but came up with an elegant embedded solution, which can talk to every piece of hardware they need it to, and be small enough to fly where ever they tell it to. If they'd been using linux for the project (with all due respect) they'd probably have spent more time getting linux to talk to the various peripherals than making the flying vehicle itself.

Credit where credit's due - it's a truly great feat of engineering.

800 mhz?

In my day, when we wanted mobile computing power, we had to do it with a 6 Mhz Z80 [ticalc.org]. I mean really, you DONT need a desktop computer for waypoint flying.

CPU Usage for UAV
XP Embedded - 35%
Waypoint system - 1%
Flight Control System - 2% (It's written in C# with .net framework)
Seti@home client - 62%

You had a 6 Mhz Z80?

Lucky bastard. We had to use a PDP 11/780 on a flatbed!

Uphill! Both ways! In the snow!

Joke if you like....

But XP embedded is actually a very useful product. It is something that should be released as an option to run desktop systems, as it can be modularized and stripped of nearly all Microsoftiness (Messenger, IE, you name it). Just want the XP OS with full GUI, no frills? XP embedded fits the bill. We use it for a custom application here and it's just what the DOJ ordered.

Clippy?

Clippy: It looks like you are flying a plane, would you like some help?

Aerial Hunter-Killer

For some reason, this story about an unmanned aerial vehicle running on Windows XP makes me think of it being infected with a virus called SkyNet and turning into an Aerial Hunter-Killer. (from the Terminator series)

Part of a the second AUVSI student competition

My school(Virginia Commonwealth University) also did this, and actually won the competition these were built for, the second AUVSI student competition.
http://auvsi-seafarer.org/seafarers/ default.htm
http://www.egr.vcu.edu/announcements/ uav.html
As far as I know, no Microsoft products were used on the plane, but I can't find too many details at the moment. The guy I know who worked on the project only knew C and C++, though from my understanding he did mostly the EE stuff, not as much programming....

Re:And I'm supposed to be impressed?

Anything that flies benefits from light components.

Anything that flies benefits from being actually completed already - a mystical state that higher-level toolkits help one achieve more quickly.

I'm sure they could start from the codebase they have now, work really hard, and have equivalent expertise built into a lighter package in some number of staff-years. Alternately, they could archive the source, go drink margaritas for a couple years, and then buy the lighter package with equivalent power off the shelf and use it to run the existing already-completed software.

Which would you consider the elegant way to proceed?

Re:And I'm supposed to be impressed?

I'm sure they could start from the codebase they have now, work really hard, and have equivalent expertise built into a lighter package in some number of staff-years. Alternately, they could archive the source, go drink margaritas for a couple years, and then buy the lighter package with equivalent power off the shelf and use it to run the existing already-completed software.

Oh yeah, that's just what we need, engineering students whose mindset is that of a business owner. How about busting your butt to achieve something? researching more elegant solutions (and no, that's not yours, elegance is in the design and performance software with tough constraints)?

You totally missed the point of research. Research isn't about using technology, it's about inventing new technology. Using off-the-shell components doesn't push the envelope, it just shows the Cornell students can take envelopes from their sponsors.

Good thing not everybody thinks like you, otherwise we'd all be waiting for everybody else to solve our problems for us...

Re:And I'm supposed to be impressed?

Oh yeah, that's just what we need, engineering students whose mindset is that of a business owner.

Actually, we do. Real-world end results are what actually matters.

How about busting your butt to achieve something?

I've known a lot of engineering students at Cornell. Suggesting that they don't "bust their butts" or serve as puppets of the Microsoft PR machine makes me laugh. A lot.

Think about this -- if the Cornell UAV team hadn't accomplished something unprecedented, would it have been "news for nerds"? Frankly I don't see why you care whether they developed new technologies from scratch, or built upon existing technologies.

Re:And I'm supposed to be impressed?

You're right. 1G of storage - that's equivalent to two whole USB keychains. It couldn't possibly get off the ground.

Here's how I see it. It's a freakin' prototype. It doesn't have to be elegant. It just has to work. And maybe they want to add other functionality later, such as "look out for that tree" and "don't fly into the building, even if it's a waypoint".

Besides, autonomous flying machines need all that extra power to run Skynet anyway.

Re:And I'm supposed to be impressed?

Have you even seen an 800mhz crusoe and 1gb of storage recently?? You can fit both in the palm of your hand. We're not in 1983 any more. Complaining about the size shows how hard you're clutching at straws. I mean, sheesh. If it was linux you'd be all over it. "oh it's so cool! i love it! linux rules!". Every single article on /. has some assclown calling something microsoft-based crap, for absolutely no good reason whatsoever. The most disappointing thing is the rest of the /. community doesn't correct such blatant assclownisms, but eggs them on. Really, really sad.

Have you read about XP embedded? It's a pick-and-choose OS, so you can select exactly what you want. That means no bloat. Absolutely none. Kinda destroys your ill-conceived argument, and shows it really was a rant against Microsoft.

Re:And I'm supposed to be impressed?

Keep in mind that the entire plan weight less than 13lbs, so the 800mhz crusoe was not weighing the thing down. Also, I think this was more of an excercise in software, not hardware.