Hacker News new | past | comments | ask | show | jobs | submit login
Small robots may kill the tractor and make farming efficient (wired.co.uk)
235 points by jelliclesfarm on Nov 11, 2018 | hide | past | web | favorite | 196 comments

If anyone is interested, I’ve designed a totally open source 3D printable off road robot that is meant as a software development platform for farming robotics. I’m currently working on improving the longevity of the gearboxes and on a camera based vision system using reinforcement learning.

Some videos:

https://youtu.be/LIkX7wniYh0 https://youtu.be/cU_0M1_TvD0 https://youtu.be/DXPmqCd0r04

The whole robot and software is licensed CC0 and BSD respectively. Onshape and github links are on the site I promote in the videos.

Would any of you want to build something like this? What would you use it for? Anything you would want that this one is missing?

Have you looked at OpenTorque actuator?


Not sure how appropriate the form factor is for you, but maybe you can at least find some useful ideas for your own gearbox design.

Hey that’s killer! I’ll have to dig in to it more, thanks for the link!

I would love to build something like this just for general personal experimentation including a kid. I basically want something that is:

- somewhat large (about this rover size) so it can drive around a typical residential yard mixed in with occasional obstacle

- sturdy enough to carry payloads like 1/2 gallon of water or so, survive a kid sitting on it, etc.

- relatively water resistant. Doesn't need to survive falling into a pool, but operating during light rain and especially dew would be great. Needs a payload housing that would protect hosted electronics from getting wet.

I'm not even sure how much the suspension is needed, I feel as long as the wheels are independently driven and relatively large that would be OK.

Mission #1: chase away squirrels and rabbits

Mission #2: shoot them with a water jet/acorn launcher :-)

Mission #3: real-time video feed and remote control to explore the woods at night

For waterproof electronics, I've had success building with these types of cases, just drill holes for wires going out, and seal them up with Sikaflex. With the transparent ones you can have an OLED display on the inside for status etc. They're usually found in your Home Depot style shop:


That looks awesome! Here's a comment I wrote earlier about the topic:

I've been thinking about a suite of robots on the residential level that could not only mow the grass and edge it, but also shovel snow, and perhaps eventually prune plants and pick the harvest. If a base, plus a suite of attachments, could be affordable at less than $5k retail, I would buy it.

Awesome! That price might be hard to achieve any time soon. Mostly because the engineering team will be very expensive, so the price will have to be many multiples of the unit cost for some time. Such a thing might be possible at a $20k price in five to ten years, and a service company could offer that work on contract to many different households.

As robotics matures as a field, the engineering costs to accomplish this will go down, as will per unit costs. Maybe in 20 years time such a multi bot could be available. It’s hard to predict the future and probably of questionable merit. That said I’ve become much more pessimistic about timelines for robotics as I’ve continued to work in the industry.

My hope though is that open source robotics can keep pace with the industry as time goes on, just as open source operating systems have kept pace with their closed source counterparts. That way people will have options when the technology does become feasible.

Why, in particular have you become more pessimistic about the timelines for robotics? I've also been headed this way, but it's as a complete outsider of the field simply extrapolating directionality comparing promises to deliverables with the former exponentially outpacing the seemingly linear, at best, progress of the latter. Interestingly the same is also true of many other fields from genetics, to AI, to molecular nanotechnology. The latter being a radical example of something going from 'the next big thing to revolutionize society' to all but disappearing in a period of < 10 years.

Thanks for the insightful comment. If you ever want to hop on a call and talk about micro-farming and robotics, I'm all for it.

Also, after some thinking... what's the current price of just the parts?

About $1500 including batteries. $400 of that is motor controllers, which could be reduced to $130 using Odrive instead of VESC for motor controllers. This is for the remote control version. If you want it self driving, consider the cost of a beefy mobile computer and sensors. I am currently working on a reinforcement learning system that will use cameras and the $1300 NVIDIA Jetson Xavier computer for autonomy.

What about something like this, but without the person controls? https://bealoving.com/products/electric-scooter

Ah, this seems to be a scam, according to the actual manufacturer: https://www.atr-orbiter.net/

Thanks again!

Stop growing grass, plant bushes, and clover. Don't use gasoline lawnmowers. Lawns are very silly things.

If you don't care about energy costs, you could put a hotwater system under your driveway, I've seen a few of these now.

I think one major issue is getting people from the city to the farms during harvest time. It's a problem of coordination and transport.

Oh I know. I have a food forest, and aquaponics system, and some fence gardens. But I can't get rid of the grass (yet) because of the HOA (I did plant clover in it).

I'm just saying this would be a good space to start, if the robotics dev economics made sense: the market is there.

Nice how it is always other people's things that are silly. Lawns are silly in places like Las Vegas, but maybe not particularly silly in a place like Michigan or New Jersey.

My parents' NJ lawn needs a lot of maintenance -- they use a lawn service that mows the law every 7 - 10 days, fertilizes a few times a year, maintains the sprinklers, does some kind of regular weed control, and took care of a mole problem last summer.

Still seems silly.

Laws might seem to need a lot of maintenance, but unless you live in a desert and have the native vegetation that hardly grows(cactus, yucca, and mesquite like bushes), any landscaping besides a field of rocks will likely require more maintenance.

You could let your yard go back to the wild and that would be cool by me, but where I live people who replace their lawn go with mix of bushes, flowers, and trees with paths and other landscape features that require a lot more man hours in pruning, trimming, leafblowing, etc to keep looking good.

I don't live in the dessert, during the drought a couple years ago, our HOA replaced the lawn areas with some sort of low maintenance native bushes and flowers along with some sort of native grass that doesn't need to be cut.

So now instead of a weekly visit by a landscape crew of 3 to cut and maintain the lawn, we have a bi-weekly visit by a single person to do some light weeding and raking.

If you do it right, it can work out well. I just don't seem to see that in the East Bay where I live. I do my own gardening and cutting grass is easy. Pruning bushes and shrubs is a lot more time consuming per square foot in my experience but I would only mow once a month.

Yeah, I mean, in CT ours grew whether we wanted it or not. the choice was grass or trees, and its not great when trees grow literally right up to your house. if you wanted a buffer it either had to paved, gravel, or grass.

And paving in places with a lot of precipitation has some unpleasant side-effects.

You might be interested in working with groups such as Open Source Ecology https://www.opensourceecology.org/

I poked around a bit but wasn't able to find out what the nominal/design specs of the v2 robot are. Is this designed for slow movement through a farm field? What kind of payload, battery life, range, etc.? You've got all these videos and that forum, but a blog post about the project, your intentions and so forth, would be interesting.

The suspension and driving action are very impressive!

Thanks! Yeah there’s lots of missing pieces here as this is all a side project for me on top of a day job and social life (hah). I talk about my intentions in the “Rover Reveal” video (https://youtu.be/LIkX7wniYh0). This is for me an exploration in long service life 3D printed robotics as well as a software development platform for outdoor robotics.

You can also read an essay that explains my motivations for working on this kind of thing more broadly:


What material(s) are you printing the gearboxes out of currently? Nylon would give you a lot better longevity than most other thermoplastics, especially if you can SLS instead of FDM. It also looks like you're using straight cut gears in the current CAD files - you might want to try switching to a helical gear system if possible to increase torque and decrease wear.

If you can SLS, why not go with metal? Sintered metal gears (not 3D printed but "old-school" sintered) are basically the standard way to make gears for power tools etc. nowadays.

The cost differential is at least a full order of magnitude. Nylon SLS machines are available at a $10K price point. Metal (usually titanium) SLS machines are typically well over $100K. Cost of material is also usually an order of magnitude difference. The former is something you might see in a makerspace or college lab, but the latter is going to be restricted to corporate production environments for some time.

I assumed we were talking about someone buying gears from a 3D printing service. Then the cost increase for metal SLS seems negligible compared to the increase in robustness. If you're considering forking out $10K for a printer, OTOH, it means that you'll be running it for larger production runs, and then you might as well just get some molds made for traditional powder metal sintering. Especially when you factor in labour costs.

Very cool! Thanks for posting this. I've been looking for a fun 3d print / electronics projects. Thanks for posting videos too as it's much easier to quickly see what you're doing.


Many crops would not need so many pesticides if they were grown in close proximity to the other plants they naturally occur with... in some cases this is because other plants attract predator insects that keep other insects at bay... humans could never farm this way because harvesters just chop everything down at once...

But a robot capable of recognizing all the plants could tell... and could selectively harvest just what is needed.

I suspect this is a very difficult problem however just because of how varied individual plants can be... telling plants apart can be hard even for trained humans.

I suspect this is a very difficult problem however just because of how varied individual plants can be... telling plants apart can be hard even for trained humans.

Actually, it's not. Despite all the hype surrounding deep learning, tasks like telling similar looking plants apart is precisely what's it's good at. In fact, it will probably be better than most humans at this task. Moreover, it's simple to implement. You take off the shelf model (e.g. ResNet-50) trained on ImageNet, and finetune it on a dataset of specific plants you want it to recognize (~1000 examples of each plant). Then you can run that model on an iPhone (or even on much cheaper hardware)

A much harder problem is to make the robot move through the terrain without getting stuck. But even there, looking at what Boston Dynamics is doing, it seems like we are not that far off.

Robots with legs are probably not an option, they are both costly in production and energy usage. Something more akin to https://farm.bot but on a larger scale would probably work better. Maybe a hybrid solution like a CNC bot built on top a frame with wheels that could simply drive around a field and work on different quadrants would be a way forward.

I am currently making a suspended robot to work on that exact problem. I hope to achieve what Farm Bot does but on a much higher scale. I live in Japan where most of the fields are ricefields. Wheels or legs are not really an option under these extremely muddy conditions.

Would love to hear more about this

I wish this post happened a week later! We are currently making a website, it should have been online last week but we missed the deadline. I have a small working prototype (2x2m area), I am currently changing some parts so that it can be made 100% with off-the-shelf parts. Next step is trying it on a 10x10m area and then see how far it can go.

Without making it particularly sturdy, it was able to lift 4 kg and has a pretty good movement repeatability even if totally "blind" (I am currently working on its vision system), two things that drone would have a hard time duplicating in outdoor conditions.

I can PM you later when we have all the things set up if you want. Or we can just chat here.

I'm building something similar but for litter collection.

In order to make the system mobile I'm making a sort of tiny tractor that relocates the bases of the support struts (I use a tripod.) You can have separate symbiotic fleets of static "heads" (tripod+wirebot) that are moved by mobile "rovers".

This lets you optimize the system a little better, since most of the time the head units will be working and largely stationary, so a small fleet of rovers could be enough to handle a large fleet of processors.

For ricefields I think you might sink stepping stones in a triangle "grid", maybe concrete cones about a meter long and 10cm at the base, inverted and stuck in the mud. The distance between them would be fixed by the span of the suspended robot.

You would also want "vascular" conduits to transport material to and from the working heads. These aren't necessarily physical tubes or conveyor belts, they could be made of simple cargo drones like streams of ants.

You could make bridge or rail units that fit between the stepping stones for temporary reconfigurable transport networks. (If your cargo drones are sure-footed and reliable these could be simple planks.)

Also, have you heard of Hangprinter? https://vitana.se/opr3d/tbear/ (I have no affiliation w/ it.) It's a "RepRap hanging from the ceiling"

Interesting! Actually my dream would be to make a system deployable by a fleet of drones. Rovers are actually complex to move, especially in an uncontrolled environment with lots of plants.

I don't think any rice farmer would like to put concrete blocks in their fields unless every task is reliably automated: they depend on machines to prepare, plant and harvest the rice and a stone in the middle of a ricefield would make these steps harder.

I know that there are several projects using wirebots for 3d printing. It usually allows for a bigger printing volume than regular CNC-like designs, and I think they must be able to have a high precision too. I am wondering what is the limitation there.

I had a similar idea of making a suspended robot farming robot (e.g. it may hang in between two fences of a backyard or between trees...)

Do you have any contact info?

Sure: info@fae-bot.org (the website is mostly a placeholder right now with old pictures of an early prototype)

Interesting, so how does the winch system work is it actually pulled and released from each pole base? Are they going to be modularized so they can pass tools along multiple such systems? Have you thought about harvesting and collecting?

I use a winch based on a stepper motor. Everything is modular so that it is easy to make a robot with just 3 wires or with 8 for 6 DOF experiments.

Passing tools among a neighboring system is going to be hard as there is a "dead zone" bordering the rectangle drawn by the pole but there may be a way to smartly cross the wires so that two system may share an area where they could pass around tools.

Harvesting is actually, counter-intuitively, a low priority task IMO. This is usually a single day of work, and this is the one with the highest stake, where things going wrong can jeopardize your whole harvest. People will want to be present for it I think.

What needs to be automated first are the tedious tasks that need to be done repeatedly : weeding, monitoring, watering.

About harvesting, a farmer friend proposed something interesting: just pass bags/baskets from the field's side to the place when the human is inside the field. Ricefields are very muddy and if you work in the middle of one, doing back and forth to the border is really tedious.

Congratulations! Please use the email address in my profile and feel free to put me on any email list you have.

hey I'm also interested in this. Mind shooting me an email when the website is ready? hello [at] myusername.com

See my comment above, the original steam trackers were too heavy to put on a field, so they used a system of wires to pull machinery around. Two trackers drive in tandem down the sides of a field, with a wire between them. The machinery suspended from the wire.

You could put it on a radial track built like center pivot irrigation systems. Maybe even on the same construction if you already have that.

This is a billion dollar business, if it can be made to ride on existing systems.

Imagine being able to plant, weed, and harvest strawberries from a center pivot. Huge.

I'm betting you'd still need to install a new track designed for the purpose, but you might be able to clamp it on to the existing framework. Irrigation stuff is below and would be tough to move around, maybe the robots dangle off the side?

Legged are impractical now and for the near future, but I suspect the cost will decline substantially within 10 years.

Why does it help to be trained on imagenet first? Also are there any tutorials to teach you how to do what you’re describing?

It’s called transfer learning. The base layers of a model trained on imagenet are general enough that they’re helpful for the specific task of processing plants. The benefit is imagenet has much more training data which is why you’d train on that first and then fine-tune the model with your specific data. Fast.ai is a great beginner friendly resource.

It’s a hard problem I know BASF has invested a lot of money working on this very problem.

> humans could never farm this way

... at scale. Humans do farm this way -- I've seen fancy shade-grown coffee being grown in what looks like a jungle. But it requires a huge amount of manual labor, right now.

I think we'll get there at making machines do this. Deciding whether a leaf is one of the 4 crops you're growing, or not, sounds much easier than distinguishing all the close relatives of wild plants.

> Humans do farm this way


There are two different senses of "efficiency" in farming (or other production). One is the amount of food you get per unit of human labor input. Supporting a fully urbanized population requires this metric to be high.

But the other sense is the amount of food you get per unit of land input. A society that maximizes this metric will produce more food and have a higher population than a society maximizing the first one. But most of those people will be subsistence farmers who don't earn much more than the marginal extra food they provide by intensively caring for the land. This is why historically most of the population -- anywhere -- was rural peasants.

The grotesquely inefficient capitalist who uses a workforce of 10 people and 300 acres of land to produce the yield of 50 acres of land is part of a "wealthy" society -- everyone else has more food because of his very low need for labor. But it's also a very low-population society. In a more traditional society, all the land would be farmed efficiently and the population would be much larger, but non-farmers would have much less surplus to capture.

There are a lot of choices which go into all of this, too. One interesting story is about which poor countries tried to copy 20th-C US farming, and which did almost the opposite.

The first path was a mistake -- it looked modern, all those big machines, but was optimised for near-infinite land and very expensive labor. What poor countries typically had was the opposite: plenty of peasants and no room, and no diesel. So the winning strategy was actually closer to a million vegetable patches, with incentives, training, and transport to get this to the cities & export. An acre of vegetable patches can easily produce 100x the market value of an acre of wheat. Getting this right was a big part of how Taiwan & Korea for instance kick-started their growth. Getting it wrong was part of what killed the USSR -- if I remember right, they never even equalled the 1917 harvest.

interesting anecdote. any recommended sources?

Seeing Like A State goes into a fair amount of detail.

From my notes:

* Soviet collectivization. Inspired by huge mechanized farms in the US. Vision of doing for farming what assembly lines did for manufacturing. Both Soviet and US attempts to do so failed badly. Party resorted instead to martial law and grain seizures, creating peasant uprisings. Forcibly relocated peasants into standardized, pre-planned mega-farms which were ruled by agricultural specialists. Ignored local conditions, vastly over-simplified and over-abstracted different areas of land and differently-skilled populations. Pressure from above to deny failures led to plans quickly losing contact with reality. Peasants gained most of their food by farming their own private plots in their little free time. Peasants effectively became indentured slaves, stripped of any cultural institutions that might be a focal point for rebellion, and naturally responded with terrible productivity. More deaths from starvation that WW1 and civil war combined.

* Compulsory villagization in Tanzania. Similar story. Government (with support of the Western world) wanted to modernize the peasantry. Forcibly relocated peasants to standardized, pre-planned villages. (Was supposed to be voluntary, but top-down pressure for results led to initiative-taking). Peasants were moved vast distances, rendering their deep local knowledge worthless. (Peasants don’t come in standardized, fungible units). Forced to apply Western farming techniques which failed badly in the local climate and ecology. (The peasant practices of dense polycropping turn out to be much more effective in climates with high primary productivity than monocropping and ridging as is common in the West). Authorities heard reports of atrocities but insisted they were isolated cases.

* And again in Ethiopia. Lead to widespread famine.

"You should use wheat-growing techniques that do work for us, but don't work for you" isn't quite the same message as "you should grow wheat (using techniques that work equally well for us and for you) even though wheat is only economical for us because we have a lot of land and no people to farm it, whereas you have a lot of people but not so much land".

There are varying levels of communist madness, from "you must pursue this strategy, sub-optimal for conditions here" all the way to "you will stay in this barbed-wire pen until you all starve". In the 60s/70s Tanzania was further along this line than was Russia.

For downvoters (who perhaps don't like my swipe at commies): my point here is that not all of these were honest if misguided attempts to improve farm productivity.

Some, like in Ethiopia, were closer to ethnic cleansing -- deliberately moving people (esp from Tigray IIRC) who were violently unhappy with the government, to less fertile places where they didn't understand how to farm, especially with new crops to boot. But by claiming this was a modernisation scheme was excellent PR, people like those, and the resulting famine was seen primarily as a great tragedy, and brought in lots of aid money.

How Asia works by studwell. It’s also a Bill Gates book recommendation.

This is a great book, and easy to read.

For russia I also like Yegor Gaidar, there's a book but the summary is http://www.aei.org/feature/the-soviet-collapse/

I wonder if the Communists just got bad timing. I am not saying Capitalism isn't better - but maybe they could have made it if they'd had robotics.

Communism and capitalism will hopefully be made irrelevant by advanced robotics. A post-scarcity economics does not care much about structure of ownership of the means of production.

Regrettably, there is no such thing as post-scarcity society. The exponential nature of biological reproduction ensures that no matter how much carrying capacity one builds, it will be filled to the brim in a geological blink of an eye.

Hopefully a society that is liberated from the burden of work will devote much more time at understanding and solving its political problems and should see unchecked growth as an evil to fight. Especially if we also get very extended life expectancy.

There have been plenty of societies historically in which very little work was required in order to live normally.

What people did with the resulting free time was generally to make war on those nearby.

That's simply not true. Until recently agriculture was extremely labor intensive and only an elite caste could have free time.

You're thinking of agriculture north of the tropics.

But there have been many societies which

- didn't engage in agriculture at all, or

- engaged in tropical horticulture, which is low-effort

And those societies (plains Indians / Australian aborigines / sub-Saharan Bantu (they're farmers! But they're not labor-intensive farmers) / central Asian Turks and Mongols / etc. etc. etc...) are characterized by near-constant warfare.

Not all societies are ancestral to yours. Most aren't.

Do you have any source to your claim that these societies required little work?

And seriously, claiming that a society will engage in warfare by comparing it to an example that is as remote to it as possible in terms of technological development and culture (we do view warfare as negative, not all societies do and ours used to not do so) is not exactly convincing.

That pre-colonial farming in Africa required relatively few hours of labor is well-known. I don't have a great link but "female farming system" is a term to start from (seriously, I didn't make it up).

The reason, if I understand right, was that the limit on human population was set by disease not labor. In northern climates (where fewer of the diseases we evolved with thrive) instead the marginal farmer was on some stony hillside from which maximum effort could only just produce enough calories for winter.

I'm less sure whether such societies were involved in more warfare, it's possible (the men had time on their hands & soccer hadn't been invented...) but I don't know the data.

I also don't know how to extrapolate this to the future of our society.

> There are two different senses of "efficiency" in farming (or other production). One is the amount of food you get per unit of human labor input. Supporting a fully urbanized population requires this metric to be high.

> But the other sense is the amount of food you get per unit of land input. A society that maximizes this metric will produce more food and have a higher population than a society maximizing the first one.

Are you suggesting that the reason the US/Europe is not at the Malthusian limit / has a low population growth is because we don't grow enough food? You'll have to pardon my incredulity.

Your point is strictly true - we are growing less food than we theoretically could grow, but that seems beside the point: we still have an enormous surplus of food.

> Are you suggesting that the reason the US/Europe is not at the Malthusian limit / has a low population growth is because we don't grow enough food?

Population growth isn't being restricted by food availability. As to the other questions, I wouldn't want to argue causation in either direction. I'm pretty sure it goes in both.

If we started to reproduce at the level supported by our food production, we'd end up in the Malthusian equilibrium.

The west has been decoupled from Malthusian equilibrium for two to three centuries.

At earlier times, say 800 years ago, I think it can be argued that population densities in Europe were lower than in China because farming was optimized more for labor than for land -- plowing with horses is less work, but less food, per area, than planting rice by hand. But it's super-hard to figure out cause & effect obviously.

> but non-farmers would have much less surplus to capture

As someone who is grateful for computers, toilets, psychotherapy, punctual trains, and an efficient medical system... I am very grateful for our ability to produce food without high labor inputs.

Don't worry, it'll be substituted with agricultural robots soon enough and we can have the best of both worlds.

A lot of the permaculture/edible forest movements are dependent on cheap labor, usually of students coming to learn the techniques or volunteers into a more sustainable lifestyle.

I live close to both a rural hackerspace and a permaculture community. I am currently working on a suspended wirebot to help them automate the most tedious tasks. Pest removal, weeding, monitoring seem to be the low hanging fruits there.

> But a robot capable of recognizing all the plants could tell... and could selectively harvest just what is needed.

You don't even need a robot for this. The city of Edmonton, Alberta has deployed a fleet of small weeding machines to curb pesticide use -- to wit, specially-trained weed-eating goats.

Could you provide a link please? On pasture land I see the opposite problem - the animals eat the 'best' stuff (clover, grass) and leave the weeds (thistles, nettles, buttercups, ragwort etc). (Although partly this is because on pasture land, weeds are 'what animals do not eat' :)


Goats are known for their ability to consume a wide variety of plants, especially weeds and shrubs that other animals won't touch. These goats have been specially trained to target noxious weeds and are constantly watched by humans and dogs.

Unlike human, computer is exceptionally good at remembering stuff. No need for plant recognition when you can brute force remember where you planted each individual seed.

>Many crops would not need so many pesticides if they were grown in close proximity to the other plants they naturally occur with.

This is the strategy JM Fortier employs in his gardening technique. In my retirement I plan on attempting to implement the market garden (a smaller version).


>> humans could never farm this way because harvesters just chop everything down at once

Really? You think a mechanical harvester cannot be built that could handle two types of plants at once? Forget deep learning and imaging technology. Plant alternating rows and build a harvester to accommodate, straddle, one while working the other. No fancy vision tech needed.

It's certainly possible to build such a machine. But it would be more mechanically complex and expensive to build and operate than existing harvesters. And it would be locked into two specific crops which might not be the combination that farmers want next year. It's hard to see how machinery like that could ever be economically viable.

Possible? Try a standard farming technique called "intercropping". Often a single mechanical combine harvests both plants at once, with the crops separated from each other mechanically later. Other times the plants can be separated by height and harvested on subsequent passes.



A robot with computer vision could easily tell apart maize from soy from squash (different colors, react under polarized light differently, leaf size, plant structure, etc). The real problem is that 1. squash has limited commercial value. 2. corn grows to 8' tall while soy is only a couple feet. The corn would block all the sun from the soy. When you plan a field full of corn it all grows at a uniform rate so each stalk gets an even amount of sun, rain. If you want the advantage of both crops, you rotate every year or two. That way the soy can perform nitrogen fixation with various bacteria and produced essentially free nitrogen fertilizer for your corn.

I suspect that a robot capable of doing that would nearly as expensive as a human doing it.

The first one would be far more expensive than a human. The 100th one would be far cheaper.

More like the 100th. generation ...

It would also be incredibly slow. You might cover a few acres per hour and would need dozens of these operating in tandum to cover a large farm.

Or a robot simply removes the pests one by one. If you’ve got enough robots it shouldn’t be a problem.

Once you're making your robots fight insect/animal pests, it's probably more efficient to attract natural predators. They're like highly-optimized, self-maintaining, self-constructing robots already.

This is the awful irony of a lot of these farm robots. Like the pollination robots, for example. Maybe I'm just being shortsighted, but it seems like we already have pollination robots, called bees. Native bees don't even require a hive or beekeeper.

But, apparently, it would appear "not using neonicotinoids" is a lot harder than "designing & manufacturing millions & millions of tiny robot bees"

Bees are not always efficient pollinators and they can also be most costly.

More costly than building thousands of tiny robots or pollinating plants by hand?

You need to consider the costs of all these robots. Farmers would in razor thin margins.

how fast and of what size must such a robot be so that it becomes cost efficient?

There are existing prototypes of laser systems for killing fast moving insects such as mosquitos. Imagine a device on a fence pole covering the surrounding acre.

There are plenty of slow moving pests, weeds and the like as well.

Or we could eat less fresh fruit, buy more fruit for baking and already canned fruit.

Where do you think that canned and baking fruit comes from? It's grown just the same.

Presumably, canned fruit could involve less organic waste as the canner can use ugly fruit that consumers may reject for long enough that it spoils.

I don't know enough to guess whether this is more energy 'efficient', given that we need glass or metal containers, in this case.

Yes, but there's probably less loss & spoilage in the supply chain for canned/frozen/dried/etc.

Same pest/weed control, though, and that's what we were talking about.

How about putting different plants in different rows, e.g. plant A in even rows, plant B in odd rows.

If you're cash crop is plant A, then plant B needs to be cheaper than spraying herbicides and the cash value of all the plant A you could have grown instead.

Unless there are laws against spraying those herbicides.

And laws could be drafted once it becomes known that these types of method are feasible.

I believe this is called intercropping, although both plants A and B are meant to be harvested.


I definitely agree with your point, there may not be a need for a high tech solution to that problem.

I would be curious what ratio of producing vs protecting rows a farmer would need. Perhaps it’s less than alternating rows, not harming yield as drastically. Perhaps 1/4 or 1/5 would do.

I need a club to talk about this asap

I am currently building a suspended wirebot, I have a prototype that is starting to run nicely, hopefully the website is coming up soon. I'd love to talk about farming automation experiments (that's actually the acronym of our project: FAE), the needs, the dead ends, etc...

Wirebot are cool but invasive (no offense) IMO. I'd be happy with a bunch of wood based rovers. Some tiny helpers to ease and accelerate grabbing fruits/plants. Things super simple but that could turn farming into painless cute thing (if possible, I'm mostly daydreaming).

That's an interesting perspective. Why do you feel them invasive? I have the opposite perception as rovers have the risk of running over valuable plants. Maybe my perception is skewed by the fact that I am surrounded by ricefields and that wheels big enough to work in that muddy soil will basically destroy the field...

Maybe I have the wrong picture but I thought wirebots required 4 poles and diagonal wires, which would clutter the view and feel like band aids over the field (no offense, again, I do not know how it is in reality).

Yeah I didn't mean big machines, don't laugh but I have wood+lego (small, simple blocks, cute) in mind when I think about automating farming with devices. Slightly larger, not toy size, but nothing like the usual farming scale utilities.

Hard to communicate this over text (especially since i'm only imagining). I'll draw some stuff one day.

The company is fairly interesting, if seemingly early, but this article is atrocious. It repeats itself all over, it’s riddled with broken grammar, weird sentence structure, and a few typos, and the “name all our products like people” thing only adds to the confusion.

Came here to say this. A less confusing overview of the robots can be found at the company’s site.


Those all seem like renders to me.

From their crunchbase profile it says they've got 1.2 million pounds in funding, but need double that ++ to get started:


Those are definitely all renders. I've worked on my share of prototype robotics. To get to the degree of polish they present, you'd need a heavy industrial behind you (see Fanuc or Mitsubishi or similar).

Yea, hit or miss with wired. On the topic, this is one of those things that looks good to a non-farmer, but tractors are big and heavy for reasons.

I encourage the idea; but I don’t think the manual tractor is going anywhere soon.

Farming as a service won't work for smaller landholders (less than 1000 hectares) people on smaller farms have money to spend 2 or 3 times a year that is when they make investments that they can write off on tax (buying a tractor) all these agtech startups pushing farming as a service fundimentaly don't understand farming as a business.

Small scale farming often doesn’t work as a business. The economics of modern day commercial agriculture support only the big farmer. These technologies, unless they get super cheap, will drive more and more farm consolidation.

I think there's a possible future where small scale farming takes off because it makes small-scale farming profitable and leads to fragmentation of the agriculture market. It would be great to be able to choose from more types of bananas and tomatoes and potatoes and carrots and other fruits and vegetables.

I don't want cheaper food, I want better food.

> I don’t want cheaper food, I want better food.

Say what you want about Big Ag, but the very fact that this is a reasonable position (and it is reasonable) is a tremendous testament to our progress as a species.

Small scale farming absolutely does work as a business and the vast majority of farms (world wide) are in the sub 1000 hectare range. If you are talking sub 100 acre hobby farms then yeah they aren't a profitable main source of income (excluding some market garden operations)

What about fish farming and aquaculture. People pay a premium for sustainable fish, a good pound of sustainable fish can set me back $20-$30. Maybe there is enough of a profit margin in such fields, and they don't have to be big.

Most farms in the world are in the sub one hectare range. And their owners aren’t hobbyists.

We don't think of farm spending in terms of tax write offs. That is how large farms work, not small farms. We buy small tools. Small machines. If we need a big machine to do something on our property, we barter for it or simply pay someone to handle it who does own the equipment. The assumption that all types and sizes of farms work under the same business model is simply untrue.

For instance, combines are often a hired service http://www.hpj.com/archives/wheat-harvesting-becomes-way-of-...

I'm not sure where you are in the world but in my country we absolutely do spend the vast majority of profit from harvest or the sale of stock reinvesting in farm infrastructure because when you do that it's a tax deduction if we didn't 30 % of your profit would go in tax. small farms may not buy large items but everyone that runs a farm does something similar in my country. I don't know how much these guys intend to charge a month but I know that the smart tag people for cattle want $5 a month a head for what is good data but the price makes it completely non viable.

Some of the alternative models being espoused now, especially those involving a higher fraction of perennials, would have the farmers producing upward of a dozen crops per year. There are probably more opportunities under a new model than you think.

And there are more repayment models than per use, monthly and yearly.

Background grew up on the country side.

I think robotic farming with less pesticide spray will be the future! There seem to be an ever increasing size increase of tractors. Many of these tractors runs proprietary software John Deere which makes them hard to self service. Robots can run from solar/bio energy generated locally at the farm.

I think there will be a movement of build your own open source robots at farms. Farmers are very inventive and good at making things!

> I think there will be a movement of build your own open source robots at farms.

As a farmer, as much as the techie in me would love nothing more, I struggle to see it. There is a pretty large chasm between hobbyist-level tools and industrial-level tools, and it is a stretch to, quite literally, bet the farm on the former. Proven tools with timely service and support are essential to getting the work done in time.

Robotics is already big in agriculture and has been for decades. As someone once said "technology is developed by military, adopted by agriculture, and then the rest of the world is finally exposed to it." If you can dream of a way to robotize agriculture, it is quite likely already commercially available. Any farmers who do happen to come up with a novel idea to improve agriculture will be undoubtedly looking at commercialization to raise the necessary capital to develop such a machine.

There is unquestionably a long history of farmers bringing innovations to the industry, and undoubtedly will continue to be, but they are not exactly projects that you slap together in your free time from open source materials. Those who have something to build put forth serious investment, and often requiring outside investment, to make them a reality.

That said, I could definitely see popularity among gardeners, where the scale is tiny and the practice is already a hobby.

I think a new startup will "innovate" how farming is done using robots. After that the technology will become mainstream.

I think you're 20-30 years late, to be honest. Robots have already taken over farming and their use has been mainstream for decades. There are still some niche areas which have room for improvement on the robotic front, but innovation in those areas will remain niche products.

What will be transformative is changes to the legal framework that will relieve human operators from overseeing the robots that do exist, without fear of legal repercussions should things go wrong (and they will; farm equipment breaks constantly given the harsh environment it has to operate in).

I was thinking about swarms of small robots that use machine learning to do intelligent work and come with innovative solutions, like the ones in the article:

Use of lasers to kill unwanted plants instead of herbicides,

Planting symbiotic plants near each other,

Providing a interface "like farmville" but the actions are executed by robots, on a real farm

Assuming that we can overcome the legal issues to allow a swarm of robots take over the farm, you have left me curious to know what the value proposition of a swarm of robots is over one large robot?

Given the large cost of repairs, can a swarm of robots compete on cost? If my one big robot breaks down, I fix it once and it's good to go. When my swarm of robots start to break down, I have to fix the same thing n number of times.

How about transport? Lots of farmers around here have farms which are 50+ miles apart. Right now they can hop into their one robot and drive it to the next farm. Does the swarm need to be loaded onto a trailer and trucked to the next farm? Autonomous on-road operation on country roads definitely isn't coming any time soon.

Don't get me wrong, the idea is neat. But it has to actually be better than the alternatives to see adoption.

> what the value proposition of a swarm of robots is over one large robot?

Doing complex detailed work which could innovate the way farming is done ex: 1)not using chemicals, by killing weeds/bugs using robot/symbiotic approach 2)plant plants together (symbiotic plants, complementary vegetables: roots and plants) 3)using the land to plant more crops more densely

> Given the large cost of repairs, can a swarm of robots compete on cost? If my one big robot breaks down, I fix it once and it's good to go. When my swarm of robots start to break down, I have to fix the same thing n number of times.

I think cost will be an issue this swarms being much more expensive. However they won't break all at once ant you would always have a working fleet. Also the quality would be better, because the same unit would be used everywhere small scale and large scale.

>How about transport? Lots of farmers around here have farms which are 50+ miles apart. Right now they can hop into their one robot and drive it to the next farm. Does the swarm need to be loaded onto a trailer and trucked to the next farm? Autonomous on-road operation on country roads definitely isn't coming any time soon.

I think that this "startup" will have the logistics sorted by having a large area of land in one piece

>Don't get me wrong, the idea is neat. But it has to actually be better than the alternatives to see adoption.

Definitely. And that would require a very advanced robot. And maybe we already have the technology. But it would need enormous resources poured into it to make such an advanced product that offers all the benefits. And I don't know if the benefits are real/worth it.

Many of these tractors runs proprietary software John Deere which makes them hard to self service.

...and what's stopping the same from happening to farming robots? In fact I'd say it's even easier, since there's no existing notion that they have to be easily serviceable, unlike tractors.

I think there is an immense opportunity for open-source here. So many techies are yearning to get back in touch with nature, and contribute to the planet. Using your spare time and expertise to develop robofarmer software helps from both angles. Not only software - the hardware could be open sourced too! Seems like the perfect opportunity for 3D printed components and small machines.

The next Red Hat could come along and get paid to implement and support it all.

>> Robots can run from solar/bio energy generated locally at the farm.

If the robots are going to harvest the same amount of product, they are going to need at least similar amounts of power to today's machines. If they are airborne, and doing fancy AI things too, they will need far more power for every ton harvested. However it is harvested, by hand or by flying drone, the same weight of fruit has to make it from field to barn.

Using flying drones to harvest is not a plan I heard of yet..

Not efficient. But they are good for checking on your plants.

And if you do have a big solarfield and a small wind turbine as well, you probably can power your own machines.

I’ve been thinking about robots on the farm for a long time myself. I’ve always approached the idea from the view point of cheaply modernizing tractors first so that more farmers would benefit. My idea would be to take a platform that farmers already love: the desiel tractor and start adding more automation. There’s so much already invested in the three point hitch, hydraulics, pto, and other systems that it just makes sense to build on it. There’s several tasks that are perfect to build automation on. A big one where I’m from is hay harvesting it’s a four step process that could take days. Having the ability to get these task done async without involving help would be a boon to farmers.

I see modernizing tractors as a 4 step process.

1: add automation to existing tractors. Mountable kit that would cost less than $10k

2: replace said tractor with electric variant that has the same platform. Target price $30k

3: provide a way to charge based on solar power (most automation worthy farm task need to be done on a sunny day anyways) Target price would probably be in the $20k range.

4: Build smaller more specialized tractor replacements like what’s shown here. Shooting for a sub $20k platform average.

Seems like only a matter of time till Tesla has something on the burner for this. After pickup truck I think they are doing a electric bike then after that.....

> But how does the company plan to make money? The co-founders say they aren't going to tell the bots, but plan to provide them as a service through a subscription fee.

Is that a typo that should be "sell" instead of "tell", or are they making a little joke about protecting self-aware robots from the knowledge that they are being prostituted out for money?

Farms used a system of cables. The tracker, because it was too heavy, would only stay on the side and a cable and pulley system employed. The plough would be suspended from the cable and driven back and forth across the field. The tracker, and anchoring vehicle on the other side, would be slowly driven in parallel.



I think such a system would be easier to automate: cabling above a field, with an automated vehicle for spraying, harvesting, dealing with weeds.

My mum told me she remembered seeing this in wiltshire in the 1930s, and it was used for drainage pipe laying a lot too. The "mole" which is pulled through the ground laying the pipes has a huge amount of static resistance to overcome, the fowler engine had bloody huge anchors to stop it being pulled towards the mole.

If you see a steam-engine at a fairground or history society and it has a giant wheel under the boiler mounted horizontally, thats what its for: this kind of static engine work.

There were mobile threshers which used it too as a form of PTO using belts. The whole business was a convoy of about three trucks and associated labour. Steam trucks. Awesome!

I was hitchhiking in Yorkshire once back in the 1980s, on an "A" road (not a motorway) and a steam engine passed me by the other way. I was so tempted to cross the road and hitch a ride the wrong way...

If farming can be done more mechanically than chemically, it'll be better for the environment in the long run. We'll need less pesticides, and have less top-soil erosion.

The funny part is that mechanically is how it used to be done. A significant change from the shift towards chemicals was the enabling of processes like no-till and cover crops that help with soil erosion and other ecological factors.

I think it is important to remember that environmentalism is always loaded with trade-offs and there are many aspects to it as well. It brings to mind vicious yet silly lawsuits between plastic and wooden pallet makers over which was more environmentally friendly given variables like weight, fuel consumption, ecosystem impact, and biodegradability.

If you really want to be a smartass you can say with one hundred percent truth that styrofoam and plastic are better for carbon long-term compared to paper and cardboard which break down over time and release it into the atmosphere. (Ignoring the relative accounting of the manufacturing processes themselves for now.)

Aren’t paper and cardboard biodegradable compared to styrofoam and plastic? The atmosphere and soil know how to handle it.

Yeah the point was that biodegradability also eventually releases it to the atmosphere. Nonbiodegradability technically sequesters it until burnt but causes its own problems given things like microplastics.

pretty sure that LCA and sustainability analysis might not mandatorily (word?) support this. Mechanical processing needs a lot more passages and there is also a lot more soil resistance that has to be taken into account energy wise. If fossil fuels are used, climate change is a factor. mechanical processing also disturbs the soil, possibly destroying its natural balance. one really has to differentiate based on which chemical for which purpose shall be replaced by a mechanical method.

Farming is already incredibly efficient. Anyone who wants it to be even more efficient is just a huge company wanting to rid their supply chain of humans entirely.

Farming some things is efficient: wheat, soy, corn, etc. Most vegetables and fruit are still very, very labor intensive especially organic farms where you need a ton of labor just to deal with weeds.

Vegetable and fruit are below 1% of the agricultural production by mass. The major parts are cereals, oil grains and tubers.

Status quo modern farming is reliant on extremely large input of fossil fuels, there is plenty of scope for improvement in this regard.

At the moment modern agriculture is effectively making food out of oil.

Electric tractors/harvesters powered by solar on fallow fields?

The investment would be quite steep for a farmer that has already taken large loans in order to fund tractors. Many farmers simply don't have the margins. Some still drive around with 40 year-old machinery because buying modern equipment is too expensive.

I don't _like_ the proposed idea of farming as a service, but the fact is that I think it's one of the few ways we have to modernize small-scale farms in the less developed parts of the Western World.

You skipped right past petroleum fertilizer.

"Anyone who wants it to be even more efficient..."

...is a reasonable person, far as I can tell. Or is there an upper limit on desired efficiency?

touche. But I do believe there are upper limits on desired efficiency in some cases. I'm not a fan of eliminating jobs in all cases. In agriculture I'm not a fan of consolidation and I see the endgame as a few huge companies owning most of the farmland in the US (most of the land) and all those jobs going away. So I guess I'm not against efficiency so much as consolidation of power and ownership. Perhaps one day we'll all have our own robotic gardener, but I doubt it.

The limits of crop production (also) by Prof. Bugbee (don't remember the main author) might be a good starting point for venturing into this question.

There are fertile areas that don’t lend themselves to current technologies because they’re too hilly. So you could perhaps increase efficiency in those places without impacting efficiency in plains areas that are combine heaven.

Growing corn or wheat is indeed super-efficient in its use of human labor. But pretty wasteful in topsoil, chemicals, energy. And other crops (like fruit, or herbs) are much more labor-intensive. So that's two directions where it would be great to get more efficient.

I'm sure they would have said the same thing when the Aquaduct was invented. Anyone who wants to stop companies from becoming more efficient should carefully analyze what they are trying to prevent, and fix that problem more directly.

>> Anyone who wants to stop companies from becoming more efficient should carefully analyze what they are trying to prevent, and fix that problem more directly.

Thanks. I reached the same conclusion in my response to another comment here. More efficient farming is good. What I foresee happening as a result may not be so good. You are right to suggest separating the issues.

Not a reason to make it more so (unless it creates more pollution or other regression)

There's a thread on Fast.ai about a similar project called Open Sprayer, "An autonomous land drone crop sprayer".

It was great to see deep learning being applied to real problems, read about some of the initial issues like struggling to train a model to detect weeds, and see him build and develop his prototype over the last year.



Any ideas how to get involved in projects like this?

Tractors dont just do one thing. They are quite a versatile piece of equipment.

Portable power plant ( PTO shaft is huge ), taking thousands of lbs of grain to the storage bin, and countless other tasks.

Yeah, a tractor is largely just an engine + weight(traction).

What attachments(front and back, PTO) are what make them useful. Their popularity is largely driven by the large variety of things you can do with them.

Our CUT(Compact Utility Tractor) does very little 'farming' at the moment. However all the other things it does(dirt work, leveling, moving 500lb hay bales, mowing/pasture upkeep) are why we have it around. When you look at the 3-point hitch, power take-off and SSQA just about anything you can do with dedicated equipment you can do with a CUT. The dedicated equipment may be faster but you only have to upkeep a single machine with a tractor.

Yes it's always funny and kind of scary to look at when the farmers in our area put a Tractor next to the fixed water pumps that are located on their fields and have them running without anyone nearby. The tractors are driving the water pumps directly and the shaft that connects them is usually exposed without any safeguards around it.

I worked for a farmer who was caught in one of those. It spun him around a few times. His right side his body was somewhat sideways after that. That happened to him when he was in his 40's

He was 87 yrs old and still farming hard when I worked for him

While the PTO shafts are "exposed" these days they're in a sheath that covers the whole length with guards on both ends. You still want to be really careful around them but things have become much safer.

That said, farm equipment still needs to be treated with a healthy amount of respect, being lax around any running machinery will easily get you killed.

I don't think that's the case here, I can see the whole shaft rotating, and also could easily touch the joints where it is connected at both ends. But the tech they are using is sometimes more than 20 years old I guess, so maybe new ones are required to have protections. Anyway, I am treating those things with a healthy kind of respect.

Yeah, sounds like it's an older PTO shaft. The newer ones are much, much safer but the guards make them an absolute pain to grease properly.

> exposed without any safeguards around it.

I get the idea that that's a bit of a theme. Its a bit like how the root user always has the ability to run `rm -rf *`

I put that to the test one time on a system I was going to wipe anyway... It didn't work.

The trend across the board seems to be: protect people from doing dangerous things without confirmation, because it's easier to protect them, than deal with complaints or fix the messes they make after the fact.

Really? I know `rm -rf /` doesn't work, but was pretty sure the star version did. Time to go burn a VM:)

I'll have to do the same thing again too, cause now I'm not so sure...

If I was younger, farming tech is definitely the place I'd be headed.

Imagine being able to change the world.

So, I'm not that young but how would a person living in an apartment in the city go about start learning this?

I mean I can kind of see the tech involved in this but actually putting into practice is probably going to be challenging due to the circumstances.

Go do some Farm-stay holidays and ask lots of questions. While there, ask around for other farms that will show you around. Talk to them, look for pain points, then go home and work on solutions. If you come up with something they agree would be helpful, let them be your beta testers (for free). You'll be helping real people in real ways, and might stumble on something that can change the industry.

I have family on farms, and friends who work in larger scale farming, and have spent plenty of time at both. They're always happy to hear about things that could make their lives easier, but most of the big startups are coming at this completely wrong and offering expensive over-complicated "solutions" that don't solve anything the real farmers really care that much about.

I don't know why I've never heard of farm-stay holidays until now. I'll have to find one which is more hands-on.

Many cities have community gardens where you can rent a small plot. Use that to learn the basics and test your prototype devices.

and stick it to big herbicide companies using lasers to kill weeds. Sounds cool imo.

I'm working on similar machines. The goal is to do farming that is better for the soil, uses less water and fertilizer, and doesn't use any pesticides (aside from beneficial insects).

The economics of farming are certainly tricky, but I think we can make it work. We may start out by operating our own farms.

If you're experienced in mechanical and electrical design and fabrication and want to help (in San Francisco), let me know (info at modularscience dot com).

"The company's own figures claim that Small Robot Company could cut chemicals and emissions by 95 per cent, increase revenues by up to 40 per cent and reduce costs up to 60 per cent."

They forgot to toss in figures for capital and return on investment, that would really seal the deal.

I am also building an open source small robot for the farm. www.opensprayer.com trying to design for a total build cost of £2000. The idea is to use machine learning to identify weeds in my grass fields and selectivity spray them.

While I suspect small robots would have a place in the future eventually I'm not entirely sure if tractors would be entirely replaced - I would expect bulk tasks to be handled by a tractor more efficiently. They certainly have the potential to be far more versatile as platforms however.

You're correct. Small robots aren't going to help you pull a road train out of a flooded track. I'd imagine though it would help offset large fleets of large vehicles, however.

Robots will eventually be doing everything in agriculture. Even warding off pests. That will enable farming happen in all kinds of impossible places, like on roofs and the side of buildings. They'll even be harvesting and selling produce.

We'll see very small vehicles on the road that humans can't even fit into, supporting a huge automated economy. Not just for farming but for manufacturing too.

Didn't read the article, but wow, if someone would build an asparagus harvester that could bring back fresh Sacramento Delta asparagus. The sh*t served in Bay Area restaurants and pathetically displayed in markets now is pathetic.

Guidelines | FAQ | Support | API | Security | Lists | Bookmarklet | Legal | Apply to YC | Contact