[dogcomplex]

You're very knowledgeable, this is great. Is there any automated tech on the market you've seen to do the spotting for you, so you can dynamically ground drones as air conditions change? Also, are you piloting all these manually (yknow, if they weren't gathering dust), is it a preset flight plan, or are you already experimenting with AI control? Would think even an LLM fed with air traffic sensor data could make the call to ground drones and switch between flight plans dynamically at this point - though I'd want it thoroughly tested and airing on the side of caution always. Also - what kind of height do you require for drone dusting? Could you get away with keeping it low to the ground, dusting only a few plants at a time at the expense of longer flight time and battery charging, but at least hopefully practically low enough to skirt any potential collision and legal issues, and potentially still entirely automated? Would think that kind of specificity also allows for stuff like dusting individual crop areas differently according to need, too.

All just thoughts from a programmer here - very cool you get to experiment with this kind of stuff in a practical setting. Hope it gets more practical soon!

Bummer the law is so slow on this.

[AShyFig]

Automated spotting is a bit of a bandaid, but might prove more useful as this situation drags on. I've thought about those raspberry pi flight trackers, but I don't think you can get the data I'm looking for from from Mode C Transponders, which is what I assume the small guys use. I haven't looked into it too deeply. The optics needed for a visual system are daunting, (the area I need to watch is large, and planes are small and fast!) but might be possible. A radar solution might be possible as well. Based on my understanding of the technology I don't think this is the right application for an LLM, but perhaps more traditional algorithm coupled with a modification of the right-of-way rules would do the trick.

The drones I fly for scouting are on various premade flight plans. DroneDeploy.com offers a good application for mapping fields from 300' high, and FlyLitchi.com works well for custom paths (flying to one spot in the field, dropping down low to take a high resolution picture of the crop, then zipping back up and repeating several times.) I can't see much benefit to full AI control of the aircraft. The current mode of operation has them on preset "rails" with room for adapting to obstacles using ultrasonic sensors. I'd like some visual adaption capabilities, perhaps something to do with lidar and SLAM (Simultaneous localization and mapping), but my drones don't have these sensors, and the last time I looked into this a DIY solution was out of my wheelhouse.

I've only seen water trials of spray drones, but my understanding is the lower the better, within reason. depending on the vortices the aircraft generates the spray booms need to be about 4-6' off the canopy top, so ~15' total flight height. You can find a little bit of an overview here: https://sprayers101.com/drone-sprayers-are-we-ready/

[dogcomplex]

Fascinating. Thank you for answering that all - I will definitely be looking back at this post one day if and when I get to play with this stuff myself. Appreciate the site links especially

Sounds like a lot of legal overhead is mainly what's standing between drone spraying... 30-60 day delay between plan submission and operation, not easy to keep that practical. Though at least yeah - 15' seems like a much more manageable height - hopefully that would at least be underneath any neighboring aircraft

Fair on the LLM - always use traditional algorithms if available and with effort/time for such things. LLMs are just the convenient duct tape / superglue to throw at handling edge cases with some confidence they'll generally use common sense about it. Untrained intern equivalent which can be combined with the algorithms if they're brittle.