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

231–240 of 483 posts

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

#231

Post by gus_massa »

defaultname wrote: post #52
gus_massa wrote: post #40

Earlier quoted context omitted.

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.

It's driving on asphalt in a parking lot. Do they have a video of the device following the grooves over mud? (It would be not surprising, because other automated tractors can do that.)

It would be more interesting to see a video where they fire the lasers. Can it aim while moving? Can it aim while the engine is on and everything is vibrating?

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

#232

Post by danbruc »

pitaj wrote: post #149
danbruc wrote: post #109

Earlier quoted context omitted.

No, the price increase will be much smaller than the wage increase because the wage increase only goes to the fraction of the population that does the work while the price increase applies to the entire population.

If you raise the base cost of production in a low margin case like agriculture, then the price of the good must increase or they would be running at a loss.

Of course, but if everyone pays $1 more then the wages can increase by $10 assuming 10% of the population works in agriculture which still leaves them $9 better off. My point was just that a wage increase is not nullified by the price increase as long as not everyone is working in the fields.

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

#233

Post by JUNGLEISMASSIVE »

motohagiography wrote: post #56

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…

Whether it's open source or scalable is irrelevant if the technology actually works as advertised, and can be applied to pest control in addition to weeds.

The incentive is just too great for Bayer, Syngenta, Monsanto, BASF and Corteva (Dow / DuPont) to lobby this technology to oblivion.

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

#234

Post by hu3 »

esrh wrote: post #101
piyh wrote: post #81

Earlier quoted context omitted.

Drones do not seem like a logical step for me. I'm not a laser expert, but seems like the energy storage needed to kill hundreds to thousands of something with light is heavier than flying would realistically allow. Wheels and tracks are what farming is built around, no need to literally reinvent the wheel here.

To me that message implied weed recognition and marking with drones followed by destruction with the cube.

That's my understanding too but what about precision?

Both the drone and the ground robot would need milimiter precision geolocation to coordinate otherwise the laser can miss the weed.

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

#235

Post by NullPrefix »

AlstZam wrote: post #207
pitaj wrote: post #156

Earlier quoted context omitted.

Paying people to walk through fields picking weeds doesn't sound scalable or sustainable to me.

It was for the last 11 000 years. With variabilities, but based on demographic only it was pretty scalable and sustainable.

A lot of slave labor was involved in the last 11 000 years.

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

#237

Post by 1970-01-01 »

stonemetal12 wrote: post #144
1970-01-01 wrote: post #96

If they can make it a little bit more robust, there would be a huge market for removing toxic plants. I was just quoted over $1000 to remove poison ivy from a 500 sq ft. wooded area of property. My satisfaction was not guaranteed.

This most likely wouldn't be safe for poison ivy removal. Burning poison ivy creates a toxic cloud. As much as poison ivy isn't fun, poison ivy in your throat and lungs is even less fun.

The robot has nobody near it. Toxic clouds would burn with no ill effect to humans.

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

#238

Post by NullPrefix »

noxer wrote: post #190

I still think the idea of having a certain type of weed intentionally planted along the crops is better. A symbiosis that prevents unwanted plants to grow. Also the weed whatever it is can be used to feed animals or turn it into some kind of fuel Or it can stay and prevents the solid form going bad in the time where nothing grows. We could probably use high-tech robots to identify the different plans and harvest one…

I have a feeling that this robot would allow to care for multiple plants growing in symbiosis

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

#239

Post by aurizon »

It should be doable to have a number of flying mirror platforms with scan and ID done centrally and once located kill pulses can be sent down. These kills could come via another platform at another time once the weed location is known and memorised. It is even possible for a small fixed wing drone(with 10x the flight duration) to be used. The ID process is a light task and can be readily moved from field to field. The laser killer with the needed wattage can be trucked from field to field, and use a similar flying mirror set to aim/kill from the prelocated targets. From what I read about mosquito killing, the tech is capable AND plants are not even moving targets. That said, many moths and flying beetles are large targets and could be targeted and killed to deal with many pests.

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

#240

Post by Minor49er »

erikpukinskis wrote: post #192
Minor49er wrote: post #188

Earlier quoted context omitted.

Instead of a laser, I wonder if it would make sense to use positioned lenses and have the robot focus the sun's rays on each weed to burn it out. Though that probably would cause fires and would only be usable during certain hours of the day.

Why would the fire danger be different than the laser?

I could easily be wrong on this, but my understanding is that a laser is highly focused to one spot. A lens would have a wider spread and would also heat up the area surrounding the target to the point that it could ignite.
Post reply on HN