I stumbled upon this 2015 post from Gerard Toonstra and am looking to build a similar setup:
There’s a ton of useful information in his post/blog, but since several of the links have now aged and technology has advanced, I thought I’d create a new thread on the topic.
I have a Phantom 4 Pro which I have a few years of surveying experience with (I’m not a licensed surveyor) doing aerial mapping and using Pix4D, so that part's covered. What I don’t have is $30k for an RTK unit lol.
I'm looking to build five small GPS "boxes" to place on my GCPs in order to increase the relative accuracy of my maps in all three axes. After a few days of research, I have a better understanding of how to build said boxes, but not enough to pull the trigger on the required components yet. Here’s where I’m at:
- Accuracy: Relative accuracy is more important than absolute accuracy in my case, at least for now. I’m shooting for sub-20cm accuracy after letting them log for 1-2 hours and processing using PPK. Getting down to sub-10cm without needing a base would be awesome, but I’m not sure that’s realistic.
- Arduino+Shields vs. Raspberry Pi 4: I don’t have any experience with either option. I plan on getting familiar with one or the other so I can build these boxes now as well as a mapping UAV in the future. It seems Arduino+Shields is the simpler and cheaper route, but I like how the Raspberry Pi 4 comes with so much capability packed right on the original board. I’d happily pay the extra money for the Pi if it makes sense for this project. If I go with the Pi 4, is 2gb enough memory or should I go with the 4gb version?
- GPS Module: Although the ZED-F9P claims to be around 1cm accuracy with RTK, it seems a bit overkill if using it for static logging and PPK. As for cheaper GPS modules I'm looking at the M8N or M8T, unless there's another capable/cost-effective module that I'm unaware of.
- Usability/IO: I'd like to be able to have my settings saved for the boxes instead of configuring them before each job/flight (EEPROM?) so that I just flip a switch and they eventually start recording until I turn them off. A few LEDs (or mini LCD screen) to indicate battery charge and satellite fix/data activity.
- Runtime: Battery operated, rechargeable. If I had to let them collect for let’s say four hours would one or two 18650s do the trick? AAA’s? I’ll likely be logging at 1Hz.
- Communication: Do I need antennas for them if they’re not communicating to one-another?
- Data Storage: Stored onboard each of the boxes. I assume via SD cards.
- Programming: I have a little coding experience, I’m sure I can learn what’s required.
- Enclosures: I’ll model and 3d print them.
- Random unknowns: Data Logger (Arduino + Sparkfun Logomatic v2? Do Raspberry Pi’s already come with data logging capabilities?), Software (u-Center looks nifty, not sure if that’s needed for PPK though), Data Processing (RTKLIB? RCTM?).
- Budget: A few thousand USD, I realize that generally speaking higher accuracy = more money.
- Working Location: NW United States.
I know this is an absolute mountain of questions, many of which are subjective, so any spattering of info would be greatly appreciated! I’ll be sure to share my build-in-progress and performance of the boxes here in case others find it useful. Thanks!
Yeah I'm starting to wonder if there's even a solution that's within my budget. The Emlid Reach M2 definitely looks like the way to go if I were to get an RTK setup though, I'll keep that in mind for the future. My area (North Idaho) is very wooded and mountainous, so it'd be tough using only L1 in a lot of situations. That being said, I just ordered a Raspberry Pi 4 4gb and a HolyBro M8N module to mess around with, so we'll see how that goes. I may order an Arduino for the heck of it too just to become familiar. I figure I'll find a purpose for them at some point.
It seems like the only way to break into reliable, accurate positioning in difficult terrain is to spend about $5k and up, whether it's terrestrial or aerial. This may literally halt my plans for building GPS boxes until I... make more money mapping? A nice chicken-or-the-egg situation.
Well, thanks Darrel for the info, and if I run into the same Pi logging issue at least it won't be a surprise. I'll report back if I'm able to make forward progress on this.
Sorry Jerry I did not mean to sound flippant. I guess I would still recommend going for 3 reaches though.
I note the accuracy you require is not high so L1 would probably be sufficient. Just be aware that getting the logging to work consistently on a Pi is challenging. You can run the gui for rtklib on a pi4 but not on a pi zero. Getting the hotspots to work consistently is also challenging - even if you get the thing working headless with a startup script that kick everything off you still need to connect to be sure things are happening. We found often the recordings would stop for no reason or the pi would freeze.
On the thought of leaving your targets - well it depends where you work. In the remote places I work local would often get curious and pick them up. Stopping them blowing in the wind was also an issue. In less remote areas landowners often take a dislike to them (I had some taken away).
All in all we have found it best to measure the GCP onsite. By using dual frequency we can get away with 5 minutes recording which is not too bad, We still hold out the hope that direct georeferencing will work well enough.
May be you will be more successful in linux than we were (although I am no expert I use linux daily for my work). I would certainly welcome a cheap solution. So far, for us, the emlid reach (yes on the ground) has worked better than anything else.
So five M2's!? That's out of my budget. I'm looking for a solution I can leave on the ground to collect data while I fly, just like Aeropoints. If Aeropoints weren't so expensive I'd just order a set of them, for example. I keep bouncing between the accuracy of the M8N and the F9P. Somewhere in the middle is what I'm looking for.
Also I mentioned using PPK vs. RTK in the original post. After reading some more it looks like PPP is the way to go instead... didn't even know that existed. For me, leaving the "boxes" on the GCPs for a few hours is no big deal since it generally takes that long to map a large job anyways. I'm starting to think a handful of M8N's might do the trick..
I have experimented with the ardusimple boards for L1+L2 processing. Problem is they do not have on-board storage and setting up the pi (in my case pi zero) has just added to the things that can (and do) go wrong. Given your budget I would just get the emlid reach M2 - I have the original reach (L1 only) and the hardware/software combination is unbeatable. Let EMLID do the hard work for you :)