Robot gets rid of weeds automatically and without herbicides | Hacker News Reader

Robot gets rid of weeds automatically and without herbicides

spectrum.ieee.org

193 pointsscmoore70 comments

This is cool but I have to disagree with this phrase from the article.... "Given the scale of farming today, treating weeds chemically is really the only practical way for humans to keep them under control".

It's the easiest way to keep weeds under control but not the only practical way. (Source: I worked for the weed science department (yes, they had one at my school) while at university.)

Here are some other methods for reducing weeds:

1) Before planting, till and water the field causing weeds to germinate. Then harrow the field killing all the weeds. Do this multiple times if needed.

2) Good old fashioned cultivation as was done before the herbicide period. (The article on the robot was posted a few days ago and in response I posted the below... it has a lot of pictured of weed control devices which may be interesting to someone working on robotic weed control....https://archive.org/stream/SteelInTheField/Steel%20in%20the%...)

3) Crop spacing. Space crops so they out-compete the weeds (this is already usually done).

4) Keep fields clean. Keep the ditch-rows clean. Don't let weeds go to seed. After a period of time the bank of weed seeds in the soil is reduced and there are less weeds to control

I know herbicides are faster and cheaper (if we don't consider externalized costs). But they aren't the only "practical" way to eliminate weeds. It does take good management and more effort to eliminate or reduce herbicide use though. I personally think it's very worth it. Oh, and I'm excited about robotics. I don't know about this device, but I do think field robotics is the future.

There is another approach to weed control. Don't do anything. Let weeds come up if they want to.

I remember a crusty old guy in Florida showing me his watermelon field that was full of weeds. I said something about it and he said the weeds actually shaded the watermelons keeping them from sunburning and he had no intention of removing them. I don't know if this is necessarily true or if he just didn't feel like doing anything about it but apparently he didn't think the weeds were causing economic harm and there were a lot of watermelons in spite of the weeds.

Funny. Masanobu Fukuoka in One Straw Revolution argues for a similar approach in orchard maintenance, if I recall correctly: allowing all sorts of plants to grow below the trees and provide ground cover.

When growing plants such as carrots, as mentioned in the parent article, the crops are competing with the weeds for space, sunlight, and nutrients. In the orchard this is not an issue, and the ground cover can be beneficial to the crop.

In carrots (which are densely planted like four rows to a bed) weeds sometimes do come up in the bed between plants. They usually aren't many because the carrot tops get so dense they smother most weeds out. You can't cultivate those weeds with a tractor (without destroying the carrots) and I don't think they have a roundup resistant carrot. So it's people walking the rows with hoes from what I've seen, or some other herbicide carrots are immune too. The device in the article might be especially good for situations like this.

Oh, absolutely. One Straw Revolution isn't a weeds-are-good book. It's a description of less intrusive methods to maintain crop health.

For rice plantations, he does try to ensure weeds don't grow. I don't remember the exact methods advocated, but I believe it was placing straw all over the ground, and for some crop he grew clover in the downtime between harvest season and growing season, I think. I don't recall too much, though.

I have countless weeks / months experience in dealing with manual weed removal. At times when I was younger I spent 14+ hours a day out in the field destroying weeds with a hand hoe.

One of the main crops I was doing it for was squash. The squash plant is pretty broad and the hand hoe allowed you to get close in under the plant. That's something this technique couldn't handle.

As someone working on minimum wage, I could get through a pretty large area in a day. Sometimes there would half a dozen of us in a gang. I'm not sure how much a device like this would eventually cost but I suspect for the same money you could buy a lot of minimum wage manual labour.

Either way, cool prototype!

There's a research project being done on the viability of hand picking radish plants out of wheat and lupin crops on broadacre farms here in Western Australia. Some farmers already do it, but once the results come out, I'm wondering home many more will start.

The architecture of the ROS system is worth looking at if you haven't seen it. Everything has a URL and processes communicate using YAML messages by publishing or osubscribing to topics. (Its very simple but a bit more liberating than REST!)

http://wiki.ros.org/ROS/Tutorials/UnderstandingNodes

http://wiki.ros.org/ROS/Tutorials/UnderstandingTopics

http://wiki.ros.org/ROS/Tutorials/UnderstandingServicesParam...

ROS is being rewritten right now - 2.0 alpha is out.

http://design.ros2.org https://github.com/ros2/ros2

I don't see it detecting any actual weeds? The detection is just targets and the demonstration of punching the weeds is stationary. Which leaves out the key challenge - distinguishing between weed & crop.

I agree, but to be fair, you could even skip that and just have a remote pilot looking at the rolling video feed and clicking on targets. It still beats having people actually walking under the sun and ruining their backs to pull out weed, or blanketing with herbicide.

I'm not so sure punching is a great solution though. Weed is incredibly good at reforming from very very small bits left standing.

> you could even skip that and just have a remote pilot looking at the rolling video feed and clicking on targets.

Then you could use that video to train a network to find weeds and get rid of the operator. You could also test the network a part of the same dataset to see how well it finds the right spots.

This will create weed breeds that look more and more indistinguishable from the crops.

Funny enough, this has may have already happened - Darnel was probably domesticated around the same time as wheat, and now it looks pretty much like wheat. There's a chance that humans accidentally swept it up when they domesticated wheat. The problem is that Darnel is psychotoxic and ingestion in the worst case can lead to a coma.

Possibly locked review: http://link.springer.com/chapter/10.1007%2F978-3-642-13145-5...

To get "more and more" you have to have a weed that triggers a partial response from the machine.

This works with a chemical - i.e. an accidental low dose, but I don't see how that would happen with this machine.

If, you had a weed that was so close to the crop it was only sometimes recognized then yes, but weeds mostly look nothing at all like the crop.

beats ... I hope that was intentional.

Seriously though, you're right, even if it requires a human in the loop it's still a huge benefit. Farms could even use remote workers to do the identification.

This seems like the easiest way to get it working now. In fact, you could do the inverse at some point in the crop cycle - get workers/robots to identify the viable crops, and from that point on stamp everything else remotely plant-like out.

Humans are too slow. If this can be done at all, it can be done far faster than a human can do it.

Kill them with fire! http://www.thermalweedcontrol.com/index.html

The problem of automated plant identification has been examined [0, 1] with good results. In [0] the classification is performed on footage from an uncontrolled agricultural setting, and the authors achieved a correct classification rate of 65% on tomato plants. Given that modern industrial agriculture is monoculture you only need to positively detect one variety of plant in an area. To avoid crop destruction due to incorrect categorization the robot could be used as a first pass and restricted to punching plants that are classified with a high degree of confidence. This could still reduce the amount of human labor necessary to tend to the field, but it might not reduce it by a degree that makes the robot a sensible economic solution. It may fail to reduce the labor needed, but I do not think that is likely.

I wonder how the performance of plant recognition degrades over the course of the crop cycle, if at all. We see in the video that some leaf matter remains after the weed is driven into the ground, and this leftover matter will influence classification during the robot's next pass. Unless the leaf matter is removed between passes it will accumulate throughout the crop cycle.

In [0] the researchers note that one reason they chose to deal with seedlings is that there is relatively little plant leaf occlusion at that stage. In [1] an end user is relied on to take a photo with a light, untextured, background and does not at all deal with partial plant leaf occlusion. That paper is not applicable to the uncontrolled field scenario.

I also found [2] while writing this comment, but have yet to read it. It boasts even better results (>90% correct for corn, 73.1% correct for tomatoes in an uncontrolled setting)than [0]

[0] http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.42....

[1] http://neerajkumar.org/papers/nk_eccv2012_leafsnap.pdf

[2] http://www.mdpi.com/1424-8220/11/6/6270/pdf

I wonder if there is an opportunity with GMOs to aid automated plant identification. For instance, insert a green fluorescent protein gene in your crop, and design a robot that senses the fluorescence.

Multispectral imaging can identify weeds and separate different types of plants.[1] Humans have only 3 color sensors, but there's no reason you can't have far more. Some birds have 21. It's easy and cheap to do, although you need a camera with a special per-pixel filter instead of the usual RGB filter.

[1] http://www.bioone.org/doi/abs/10.1614/WT-07-104.1?journalCod...

Imagining the consumer reaction to green-glow-in-the-dark crops made me smile.

I imagine if the robot is the one who planted the original crops it would know exactly where they should be. Any other growth is defined as a weed.

Exactly. You don't even need the robot to plant it; crops are planted in rows. Tractors and combines today already track exactly where the plants are planted down to sub-inch accuracy (http://farmindustrynews.com/accurate-inch -- other source, my family farm).

Parts of my family are in the bedding plant / greenhouse business. One cool technology is the transplanting machine. This transfers seedlings from "plug trays" to "flats" and replaces an assembly line of ladies doing this work. Here is one design:

http://www.hamilton-design.co.uk/transplanter.html

The ones they actually used were the "Harrison Transplanter".. could not find a video, but here is one http://bid.sheridanauctionservice.com/images/lot/3471/347193...

Harrison is neighbor of ours who worked at Brookhaven National Labs but then became an entrepreneur. He sold a bunch of them.

This is the kind of thing where robotics is really exciting. It does an end run around every problem with pesticide use by taking it out of the equation entirely.

Cool prototype.

...now make one that mounts on a front 3pt hitch and you might actually sell one.

No need for a special robot when a different piece of equipment with its own power source has to go down the field anyway

Getting rid of weeds will be a continuous task. Farmers don't want to run tractors down rows any more than they have to, nor will they want to run a full sized tractor full-time.

What do you envision having it mounted on that will drive at the speeds mentioned in the article? It's not like you can throw It on the front of your regular dual wheel or track machine and operate efficiently at those speeds.

I was amused by "A Bosch Start-Up" on the side of the machine. Now everything is a start-up.

I was just at the Lean Startup conference, and a lot of the headline speakers were from big companies like GE and Intuit. A large portion of the audience was from names I recognized as well. Being a startup is immensely fashionable.

If large companies can figure out how to house innovation, it would solve some major problems that they have. But our current model of management is basically inimical to true innovation, so personally I'm skeptical.

Yeah, the "start-up" label is subject to cargo-culting.

It's a good example of how play in the future will also go the way of jobs.

Why garden when your neighbors will have amazing gardens cheaply designed and looked after by robots.

And it'll be smart, it'll know exactly how many weeds to leave so it doesn't look to perfect, exactly when to plant and pollinate, order things online when needed.

The journey is as much fun as the end product. Usually moreso in these cases.

This is the problem, robots are killing the journey.

To take your point literally

Like jobs, at first it's great, highways, planes, easy to access information open up the world to everyone.

But it'll get to the stage where it's too easy. Adventures are getting harder to have. You no longer find that amazing restaurants, you yelp them and book months in advance.

In the future when you're chatting to someone about visiting county X and you realise they have only been there virtually it'll perhaps devalue your own journey, then perhaps you'll get what I mean.

You know people still walk right?

People tend to get play and competition mixed up, with disastrous consequences. Do what you enjoy doing, don't worry if it's better than anyone else.

Besides gardening, robots could clean up garbage. An army of small bots could clean up a forest in no time (or go underwater to clean up the shores).

That's brilliant.

What about using a laser to destroy the weeds?

I suspect this would result in rather superficial weed destruction, since the roots underground would be unharmed and would cause the weed to regrow a few days later. Unrooting the weeds definitely sounds more reliable to me.

> Unrooting the weeds definitely sounds more reliable to me.

The robot in the article just pushed the weed underground a few inches. I imagine that some weeds would just pop back after a week, and that the robot would just punch them down again.

So you now you have to run your fleet of robot weeders over the field twice? That seems like a waste of time and $ when you could achieve the desired result in a single pass. every extra pass is also more soil compaction.

Pushing the weeds below the surface is probably less disruptive to the surrounding crops than tearing out the roots. And since you have to run the machine constantly anyway to prevent new weeds from establishing themselves, just poking them down repeatedly will eventually starve them of sunlight and kill them, or at least prevent them from ever growing large enough to cause a problem.

You would already need to run the weeder every few days to catch future weeds. Much of it would be about disrupting the weeds while crops get established.

If you run the robot every week, burning off the stem & leaves, the plant will eventually starve.

Around here, we have an invasive species called scotch broom. If you cut off the plant at ground level, it will grow back. But if you cut it off after it flowers, it'll die. Mowing it flat regularly will also kill it.

On the other hand, with a laser you could process huge areas at extreme speeds. Think 100 zaps a second.

> Think 100 zaps a second.

At very low power, not enough power to kill a plant that has lots of water in it.

Why do you assume low power? :)

While you're at it, attach it into a drone. Useful for animal herding and crowd control as well.

> Why do you assume low power? :)

Because outside of a lab, lasers with enough power to zap and destroy 100 plants per second don't actually exist?

(Not that I've done the math, but you really do need a lot of power.)

There are several technologies in startups that can kill weeds using custom levels/frequencies of light - it takes about 3 seconds per spot to kill a weed.

Lasers, especially fast ones will only handle superficial stuff.

This video of punching the weeds looks promising, but just a thought: maybe you could focus sunlight to burn them? :)

While it would be much more energy-efficient, such a process is bound to have a very low rate of weeds destroyed / minute.

It's a field, you have time. Also, maybe that means you need more of those robots? :).

Fire risk?

Microwaves and lasers:

http://www.swarmfarm.com/

So, HN, this looks like really fun and interesting stuff to work on. Any ideas on how a normal developer with a CS background can get into something like this? Either working for this company, or one like it... Or hobby projects that are within a normal person's budget.

Let me know if I should elaborate further and make an Ask HN out of this?

No idea how to get into this on the company side. Apparently hey use Robotics Operating System (ROS) quite extensively, so you could learn about that (http://www.ros.org/)

On the hobby side, check out farmbot http://farmbot.io/

I think eventually farming will be completely robotic and we'll have farm on our roofs. Household waste will be processed and used for it. Robots will harvest crops for us and even get them to market if we aren't around to eat them, probably selling to people in the neighborhood.

How many years until a robot like this will cut your grass, weed the lawn, and weed your flowerbeds?

Zero years for the first one.

* https://www.bosch-garden.com/gb/en/garden-tools/indego-home....

* https://www.deere.com/en_INT/products/equipment/autonomous_m...

How many years until we be stuck with this archaic and elitist concept of a lawn?

Grass where it serves some benefit such as a backyard at least serves a purpose. Front lawns in locations where they are ornamental are a blight.

The problem is that the standard American house is modeled after a farmhouse or country house, despite the fact that we all live in cities.

Townhouses don't have lawns: https://en.wikipedia.org/wiki/Townhouse And they're excellent building blocks of walkable neighborhoods.

For as long as I live where a lawn does not require a sprinkler. Think outside the box.

So we are all stuck with an outdated concept that originated from aristocratic landowners who wanted to show how much money they had by devoting a portion of their estate to not growing crops and just being manicured because you can do it without watering?

How very kind of you to epitomize the "get off my lawn" meme, but I'm not on your lawn. I'm not telling you to get rid of your lawn, but the concept as it exists now and it's popularization is at best wasteful, and in some cases actively causes problems with water availability in some areas. Some reform in the popularized concept of a front lawn would be beneficial to everyone.

Lawns look nice. Sounds like a good enough reason to keep them. We are not THAT overpopulated.

They also stop erosion, provide habitat for insects and animals and are pleasing to walk on.

I get having a lawn in a desert is a poor use of water, but for many houses and recreational areas, it's an excellent way to cover ground.

I have no problem with lawns that are used, but what percentage of front lawns do you think get any use? I'm full in support of rear lawns or front lawns that are used, but as a status symbol I think they are wasteful of land, resources and time. Parks are an excellent place for a grass, and I'm not complaining about those either.

Looking at the video, they seem to be using a Microsoft Kinect sensor.

Reply on news.ycombinator.com