> The hardware is built around a stackable 10×10cm compute module with two ARM Cortex-A55 SBCs — one for ROS 2 navigation/EKF localisation, one dedicated to vision/YOLO inference — connected via a single ethernet cable.

I will preface this by saying that I have nothing against ARM per se, that my employer/team supported a good chunk of the work for making ROS 2 actually work on arm64, and that there is some good hardware out there.

I really don't understand why startups and research projects keep using weird ARM SBCs for their robots. The best of these SBCs is still vastly shittier in terms of software support and stability than any random Chinese Intel ADL-N box. The only reasons to use (weird) ARM SBCs in robots are that either (1) you are using a Jetson for Jetson things (i.e. Nvidia libraries), or (2) you have a product which requires serious cost optimization to be produced at a large scale. Otherwise you are just committing yourselves and your users/customers to a future of terrible-to-nonexistent support and adding significantly to the amount of work you need to bring up the new system and port existing tools to it.

> The only reasons to use ARM SBCs in robots are...

Obviously, anyone can have there own opinion on this. I work in robotics, we are quite happy with our A53 and M4. Though, we use a SOM, not a SBC, if you feel like splitting hairs.

You probably aren't using some weird SOM, though. There is a bit of an unstated exception of "unless said SBC/SOM has specific hardware that is necessary/particularly valuable for your product/project". For example, if you need GMSL you are probably not going to be picking Intel, even though ADL-N and the bigger processors support MIPI, simply because no one else does and the documentation/support for it is basically nonexistent. Designs with closely-coupled A/M/R cores, or CPU/MCU/FPGA hybrids like Zynq would be others.

But generally projects which are choosing some random SBC aren't using any of these features, and are just suffering the pain/imposing it on their users for no good reason.

again, just an oppinion, but it feels really weird to hear you find "exception after exception", when the net result that you've ruled out more real world robotics projects on ARM than likely exist on x86 that you're suggesting should be the "norm".

you've ruled out the entire NXP ecosystem, the entire Nvidia Jetson ecosystem, the entire AMD/FPGA/Zynq ecosystem, even perfectly good options like beagle-board .... who else?

incidentally, you've also ruled out this project - as they are using an M7 microcontroller to meet their hard-real-time timing constraints...

The other poster had said nothing about microcontrollers, e.g. about the various MCU models based on Cortex-M cores.

Some things are best done with a microcontroller, and those are not suitable for being done with a general-purpose CPU either based on Intel/AMD or on Cortex-A cores. Actually there are many projects that mistakenly use something like a Raspberry Pi instead of a better and cheaper implementation with a microcontroller, e.g. one based on Cortex-M7 or its successor, Cortex-M85.

The other poster said that where you do not want a microcontroller, but you want to run a standard operating system, e.g. Linux, then the best choice is much more frequently a SBC with an Intel Alder Lake N or Twin Lake CPU, as these not only have a better performance per dollar than the ARM-based SBCs, but they also avoid any software problems and future maintainability problems.

Unfortunately, during the last few months the price of Intel-based SBCs has been affected by the fact that most of them do not have soldered memory but they use one SODIMM memory module. While you can buy an Intel Alder Lake N based SBC for $100, buying today a SODIMM for it may cost as much or more, depending on the amount of memory with which you are content.

The ARM SBCs that come with soldered LPDDR memory have initially been less affected by the price hikes, though now even for them the prices are rising.

I think you're missing my point entirely. If your project needs specific hardware, you have to use that specific hardware (the obvious examples of which would be Jetsons or Zynq/Zynq-like or something ASIL-D or something that tightly couples "A"/M/R cores together, or you are stuck using a SoC from Qualcomm for cell connectivity). There are a lot of projects that do fall into that category.

There are also a (much smaller) number of projects that will legitimately see the kind of scale of production that justifies aggressive cost optimization for the compute platform, either in terms of designing their own around a SoC or picking some SBC/SoM that they can get a good deal on, where the significant additional up-front engineering cost is outweighed by the production savings (and where the desire/need to keep a fixed platform means the often limited platform support from the vendor is less restrictive).

But a large number of robotics projects (basically everything in the research sphere) - this one very much included - just need "some computer" for general-purpose use. They are already separating realtime control onto a separate microcontroller board. For these projects, it is almost always committing a "premature pessimization" of picking some weird SBC. You are signing up for worse CPU and GPU performance, stability, and development future for very little reward.

If you can send me an open hardware Intel, or Jetson I'd happily use it.

Part of the point of this for me is to see what's possible with open hardware (down to chip level at least)

The South-Korean Hardkernel ODROID H4 models are open hardware.

You get their schematics/PCB documentation and their BIOS has features that are missing in most mini-PCs and laptops with Alder Lake N/Twin Lake, e.g. you can enable in-band ECC for the memory.

Also the Chinese Radxa has a Raspberry Pi sized SBC with an Intel N100, which is open hardware, with complete schematics/PCB documentation.

Moreover, unlike for many Intel/AMD CPUs, which no longer have public documentation, for Alder Lake N Intel still provides public datasheets, which contain e.g. the thousands of control registers for the on-chip peripherals. Most ARM Cortex-A based CPUs are undocumented, with few exceptions like Rockchip RK3588 and the very expensive NVDIA Orin/Thor (or the obsolete Xavier).

There are somewhat more ARM-based SBCs that are open hardware, but there are also plenty of undocumented ARM SBCs that are much worse from this PoV than the Intel/AMD based computers, where at least the IBM PC standards and the later standards pushed by Intel, e.g. ACPI/UEFI, apply.

There are a variety of x86 products with Coreboot support, if what you are looking for is firmware openness. If what you are looking for is PCB design openness, the options are much fewer, but at that point you are probably optimizing for an overly niche objective.

> Part of the point of this for me is to see what's possible with open hardware (down to chip level at least)

I appreciate the idea, but this is essentially saying "this project will prioritize a specific choice of one (core) piece of hardware to the detriment of everything else, users included". Approximately none of your potential users are going to benefit from the "openness" of the SBC versus that of a more broadly-supported platform (I say "openness" because the reality of SBCs is that actually finding a usefully performant one that is completely blob-free is almost impossible). Open hardware means very little if it isn't running an upstream kernel and userland.

The software does explicitly support Jetson for example, and I'm sure the stack would run on Intel if you want it to.

The Mainline kernel for this particular board is _almost_ there 6.20 or so I expect. Armbian support is good.

Framework? Maybe?

Framweork have done the best they can within the confines of Intel licensing, still a long way from being able to fabricate it though

https://github.com/FrameworkComputer/Framework-Laptop-13/tre...

In a few years we'll all be using more open RISCV stuff of course.

Your discord link doesn't seem to work. One basic question: As a hardware noob, where do I start? Maybe having a minimal getting started guide could really help.

Nevertheless, the initiative looks cool!

Australia's been working with various types of robotics in agriculture since 1980 at least [1], these days, for open field work there are several families of solution in developmental progress.

One leading contender is SwarmFarm Robotics, based out of Queensland.

* https://advance.qld.gov.au/innovation-in-queensland/innovati...

* https://www.swarmfarm.com/

For interest, here's a recent opinion / demonstration from an unassociated Australian farmer considering a purchase.

The farm is Tom’s Brook, a grain farm located in Esperance in Western Australia. It’s a family operated business growing a mixture of Wheat, Barley and Canola on 4500 hectares (11 200 Acres). Sizewise is pretty much bang on the average W.Australian grain acerage.

Seeing a Swarm Bot in Action (20 min) - https://www.youtube.com/watch?v=ljEKN7CsjnM

The unit pair in action here, autonomous tractor pulling intelligent boom spray, has had 10,000 acres of operation prior to this customer demonstration.

Unloaded weight ~ 3.5 metric tonne, loaded approx 5 tonne.

Runs at about 13 hectares per hour, max speed 10 km/hour.

Advantages of "intelligence" during operation are reduced spray usage (basic green on dirt detection, and green shape on mixed green patterns) and weather patience (happy to sit idle until wind and humidity are optimal)

70 odd Comments include feedback from other farmers already using such agribots, eg:

  Just rolled over 12,000 hrs on our swarmbot.  4 years, 3000hr a year, doesn't get into the shed much.

The first 12 minutes are Vendor + Farmer discussing bot in action, remaining eight minutes is farmer and hands discussing pros and cons.

--

[1] Robot Sheep Shearing (1985) https://www.youtube.com/watch?v=6ZAh2zv7TMM

Very cool! shameless self promotion but check out greenwave-monitor[1] for the 'Diagnostics TUI'. I'll get it into the buildfarm soon.

[1] https://github.com/NVIDIA-ISAAC-ROS/greenwave_monitor

Nice, thanks! looks like a good one..

Looks great for a prototype. Has any modeling, simulation, or analysis been done of its off-road performance, i.e. mobility, GO/NOGO, motive efficiency, maneuverability on deformable terrain? This is critical for agricultural applications.

Has any stress analysis been done on the frame? Looks to me like it could use a couple more triangles to reinforce those rectangles.

Have you designed a skid-steering controller for it? Off-road skid steering can be quite variable obviously depending on terrain properties.

Rosys (a middleware layer https://github.com/zauberzeug/rosys) has rosys.driving.Odometer and rosys.driving.Steerer it's essentially a differential drive kinematic model.

Hoping RTK dual-F9P moving-base setup (M4 in the roadmap) largely sidesteps the worst of this — NAV-RELPOSNED gives us a real heading vector independent of wheel odometry, and the robot_localisation EKF can weight RTK heavily and odometry lightly when GNSS quality is good.

The current simulation is underdeveloped but can be found here https://github.com/samuk/caatingarobotics/tree/jazzy/src/agr...

The frame will almost certainly need more triangles

What's your payload? Where are the seeds? How are they deposited?

Recommend going to a farm right now to see how this works in production. For the most part, you can autonomously sow using GPS. But the farmer just rides along.

Payload is whatever you (or your startup) want it to be.

For me personally mechanical between row weeding is step one, then laser in-row weeding.

1. These on some linear actuators: https://www.getearthquake.com/products/fusion-drill-powered-... (they work surprisingly well)

2. Beyond that for in-row weeding a engraving laser on a Delta: https://github.com/Agroecology-Lab/Open-Weeding-Delta/tree/m...

Or if I'm feeling rich by then this third party weeder looks pretty good https://github.com/Laudando-Associates-LLC/LASER

3. For Seeding my salad crop https://reagtools.co.uk/collections/jang

4. Harvesting my salad crop https://reagtools.co.uk/products/quick-cut-greens-harvester

I live on a farm, I have sold salad commercially, these are largely tools I already use and own, just moved about by motors rather than muscles.

This is a smaller scale thing than arable. We're talking a step up from manual horticulture (which is actually what still feeds much of the world)

the docker-based reproducibility angle is really smart for academic agri-robotics. the biggest complaint i hear from researchers trying to replicate field robot experiments is that the software environment is always subtly different - different ROS versions, different CUDA, different model weights. if you can hand someone a docker compose and a BOM and they get identical behavior, that alone justifies the project.

for the vision pipeline, have you considered running inference on the ESP32-S3 directly for simple green-on-brown detection? YOLO is overkill for basic weed/crop discrimination and the latency of shipping frames over ethernet to the A55 adds up when you want real-time control of the weeding actuator. tflite micro on the ESP32 can do simple binary classification at 30+ fps.

I'm not sure how much more work is currently being done on a project I'd heard about in the past, but you might be interested in seeing if you can collaborate/learn from Open Source Ecology:

https://www.opensourceecology.org/

Wow nice to see the website has been updated in 2025. I followed it for years but it seemed to not get much updates.

Folks might also be interested in the Precious Plastic community which has a global network of "microfactories" built around a set of open-source machines made for recycling and reusing plastics

https://www.preciousplastic.com/

https://community.preciousplastic.com/map

Also as far as fundamental machines go, this 2d printer is expected to come out later this year

https://www.opentools.studio/

From a video somewhere in the page: "The aim is to make food production more sustainable and efficient" yet requires a web app. I'd hope that you can run the server side on a local machine and not require cloud connectivity.

The web app runs locally from the robot. No cloud. Once we reach autonomy (still some way away) you shouldn't have to use that much either.

Quite interested in running robot<>robot and robot<>Farm comms over https://reticulum.network/ but that's a side project off a side project..

Great name, if nothing else!

Thanks, bit conflicted about it TBH, it's primarily/initially a weeding robot, although I do dream of expanding it to do harvesting, and yes potentially sowing too down the line.

Strapping something like the Jang P6 to it is probably feasible https://reagtools.co.uk/collections/jang

For the harvester it would be a bolt on for https://reagtools.co.uk/products/quick-cut-greens-harvester or maybe https://reagtools.co.uk/products/babyleaf-harvester-80cm (I grow green salads)

We're gonna need it to play a midi of "Swing low sweet chariot" when the harvest cycle comes online.

And for weeding?

Initially keep it simple; Mechanical for between row weeding. I'll probably start strapping a couple of these to some linear actuators: https://www.getearthquake.com/products/fusion-drill-powered-... (they work surprisingly well)

Beyond that for in-row weeding a engraving laser on a Delta: https://github.com/Agroecology-Lab/Open-Weeding-Delta/tree/m...

Or if I'm feeling rich by then this third party weeder looks pretty good https://github.com/Laudando-Associates-LLC/LASER

I sometimes help out at a hobby vineyard of 0.7 hectare; weeding in the row is a lot of manual labour. Your platform seems like a good fit. I like tinkering and robotics, what kind of price point are you aiming for?

As cheap as possible, and no cheaper than that.

In my head it's £3-£5k, so by the time it's useful probably a bit more than that.

a simple ride on mower with a diy inter row disc (basically just a belt and pulley with a spring) may be enough. probably just get sonebody with a tractor and inter row disc weeder to do the job for you.

What's the plan for using an engraving laser in open air without blinding a neighbor? Does the bot fully roll over the target area before firing or something?

TBC, just trying to get the platform and mechanical weeding working for now

A joke that's whooshing over my head?

A robot that Sows seeds..

Aaaaaargh.

(╯°□°)╯︵ ┻━┻

Thank you.

I highly encourage you to go visit farms sooner rather than later, especially during the rainy seasons and winter when farmers are really at work preparing for the next season. The kind of conditions robots need to deal with in that environment is no joke.

I also notice you're using the BNO055 -- if you need an C++ I2C ROS driver for it I wrote one (https://github.com/dheera/ros-imu-bno055). I think the one in the ROS apt-get repository is written in Python but they claimed the package name before I did

Good advice on farms. I do live on a farm, so somewhat familiar with mud! Many of the worst problems are caused by moving 20ton tractors around IMHO, one of the problems small scale ag robotics may help with.

Will check out your Bno055 currently using the upstream one in Lizard

https://github.com/zauberzeug/lizard/blob/main/main/modules/... https://github.com/zauberzeug/lizard/blob/main/main/modules/...

Any review of that welcome too of course.

outside of sowing would you consider some open source drones like the new DJI with agriculture payload attached to it.

or some automated green house with open source designs.

love the name sowbot.

I did recently automate a greenhouse (heating, Hydroponics, fans, lights) it was just R&D rather than commercial so just used home assistant for it.

I did sketch out a slightly more 'professionalised' version, but haven't built it yet https://github.com/samuk/IoT-Greenhouse-Temperature-and-Irri...

I'd be pleasantly surprised if DJI had done anything open source, Ardupilot is pretty capable of course. I really want to automate the time consuming labour parts of horticulture, for me that's mostly weeding and to a lesser extent harvesting.

This is the future, good luck to you