Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Farming robot kills 100k weeds per hour with lasers

freethink.com

Post reply on HN
Print view View original

51–60 of 483 posts

Re: Farming robot kills 100k weeds per hour with lasers

#51

Post by the_mitsuhiko »

retro64 wrote: post #26

This is very cool. Not knowing anything about it though it looks massive and overbuilt (with smallish wheels, but likely just fine for the time of year it's put to use). Anyone care to speculate why it needs such a large body? The width is a given because it needs to span the rows, but why a giant cube?

My guess is because it can. Size is not a concern for farming and it being large aids cooling and helps to store more energy. Apparently it has a 75l Diesel tank for instance.

Re: Farming robot kills 100k weeds per hour with lasers

#52

Post by defaultname »

gus_massa wrote: post #40
cmrdporcupine wrote: post #20

I want to see details on power source and energy usage. That's where I'm a bit skeptical. To do the 20 acres they're talking about you'd need one hell of a huge battery, assuming it's electric. Even just to move the thing. Then add power draw for the laser on as well. Also seems odd to have it be something that is self-powered and autonomous rather than just something you pull behind a tractor on the three point hitc…

The video looks like a mix of cgi graphics with unrelated real videos, so I guess they don't have a real machine yet.

https://www.youtube.com/watch?v=EJigArURZWU

(Video of an operating unit)

There is nothing particularly unbelievable about the device, and it seems, as such innovations tend to be, quite obvious.

Re: Farming robot kills 100k weeds per hour with lasers

#53

Post by MauranKilom »

cmrdporcupine wrote: post #20

I want to see details on power source and energy usage. That's where I'm a bit skeptical. To do the 20 acres they're talking about you'd need one hell of a huge battery, assuming it's electric. Even just to move the thing. Then add power draw for the laser on as well. Also seems odd to have it be something that is self-powered and autonomous rather than just something you pull behind a tractor on the three point hitc…

Maybe it's because the robot needs different amounts of time for different patches of soil? As in, it kinda needs to go its own pace to a) ensure it has enough time to detect and kill all weeds (which depends on weed density, presumably - the video shows it only killing one at a time) and b) maybe it has to stop to ensure it hits the right thing because it can't handle moving targets (not clear from the video)?

No idea if this is something that modern tractors could accommodate already or whether it would need some annoying human-in-the-loop stop and go.

Re: Farming robot kills 100k weeds per hour with lasers

#56

Post by motohagiography »

Given where ML and CV are today, I'd bet on open source models trained on weeds within 3-5 years. This company can scale, but their unit price is going to plummet. Also, it sounds like they're using cameras, where it's concievable that other future sensors could be more efficient. An iteration of this with higher resolution cameras and small flying drones seems like an intuitive next step.

This is a super interesting problem because the confusion matrix (fp/fn/tp/tn) rate that makes this economical is going to be variable across both crops, and market demand.

If there suddenly there was a demand jump for peas, you could afford to use a model with less accuracy, because you are optimizing betwee a sunk labor cost and margin on your yield. You could literally tune your detection parameters based on futures price data, since if if prices were high, you could optimize compute on your model. Anyway, spoken as a total outsider, but what a cool and interesting set of problems.

Re: Farming robot kills 100k weeds per hour with lasers

#57

Post by throwaway09223 »

cmrdporcupine wrote: post #20

I want to see details on power source and energy usage. That's where I'm a bit skeptical. To do the 20 acres they're talking about you'd need one hell of a huge battery, assuming it's electric. Even just to move the thing. Then add power draw for the laser on as well. Also seems odd to have it be something that is self-powered and autonomous rather than just something you pull behind a tractor on the three point hitc…

The energy usage should be minimal - it doesn't take much power to burn a leaf.

If you pull it behind a tractor, you need to hire someone to drive the tractor. This defeats the purpose of an autonomous weeding system.

Re: Farming robot kills 100k weeds per hour with lasers

#59

Post by te_chris »

underseacables wrote: post #48

There is a reckoning coming when agricultural robots will overtake manual labor. This is going to lead to a giant calamity of agricultural workers, specifically migrant workers, who are suddenly going to be without a job. I love the robots, I think it’s great, but we should be prepared for a human concern that WILL come.

Nah, you're overdoing it. A lot of farming is already automated, and across the so-called 'Advanced Economies' the replacement rate for workers is too low anyway. We're heading for a demographic crunch with too few workers, especially as all the ageing boomers need care too.

for more: https://blogs.lse.ac.uk/businessreview/2020/09/18/the-great-...

Re: Farming robot kills 100k weeds per hour with lasers

#60

Post by damsta »

I like it. It is huge, expensive, hard to get, probably requires perfectly leveled field, but it is only third generation and one step closer to reduce dangerous chemicals used on crops. They sold out all of their bots they had available for 2021 delivery, so hopefully they can work on next generations that will be cheaper and more accessible.
Post reply on HN