Autonomous AI-Guided Black Hawk Helicopter Tested to Fight Wildfires (yahoo.com) 36
Imagine this. Lightning sparks a wildfire, but "within seconds, a satellite dish swirling overhead picks up on the anomaly and triggers an alarm," writes the Los Angeles Times. "An autonomous helicopter takes flight and zooms toward the fire, using sensors to locate the blaze and AI to generate a plan of attack. It measures the wind speed and fire movement, communicating constantly with the unmanned helicopter behind it, and the one behind that. Once over the site, it drops a load of water and soon the flames are smoldering. Without deploying a single human, the fire never grows larger than 10 square feet.
"This is the future of firefighting." On a recent morning in San Bernardino, state and local fire experts gathered for a demonstration of the early iterations of this new reality. An autonomous Sikorski Black Hawk helicopter, powered by technology from Lockheed Martin and a California-based software company called Rain, is on display on the tarmac of a logistics airport in Victorville — the word "EXPERIMENTAL" painted on its military green-black door. It's one of many new tools on the front lines of firefighting technology, which experts say is evolving rapidly as private industry and government agencies come face-to-face with a worsening global climate crisis...
Scientific studies and climate research models have found that the number of extreme fires could increase by as much as 30% globally by 2050. By 2100, California alone could see a 50% increase in wildfire frequency and a 77% increase in average annual acres burned, according to the state's most recent climate report. That's largely because human-caused climate change is driving up temperatures and drying out the landscape, priming it to burn, according to Kate Dargan Marquis, a senior advisor with the Gordon and Betty Moore Foundation who served as California's state fire marshal from 2007 to 2010.... "[T]he policies of today and the technologies of today are not going to serve us tomorrow."
Today, more than 1,100 mountaintop cameras positioned across California are already using artificial intelligence to scan the landscape for the first sign of flames and prompt crews to spring into action. NASA's Earth-observing satellites are studying landscape conditions to help better predict fires before they ignite, while a new global satellite constellation recently launched by Google is helping to detect fires faster than ever before.
One 35-year fire service veteran who consults on fire service technologies even predicts fire-fighting robots will also be used in high-risk situations like the Colossus robot that battled flames searing through Notre-Dame Cathedral in Paris...
And a bill moving through California's legislation "would direct the California Department of Forestry and Fire Protection to establish a pilot program to assess the viability of incorporating autonomous firefighting helicopters in the state."
"This is the future of firefighting." On a recent morning in San Bernardino, state and local fire experts gathered for a demonstration of the early iterations of this new reality. An autonomous Sikorski Black Hawk helicopter, powered by technology from Lockheed Martin and a California-based software company called Rain, is on display on the tarmac of a logistics airport in Victorville — the word "EXPERIMENTAL" painted on its military green-black door. It's one of many new tools on the front lines of firefighting technology, which experts say is evolving rapidly as private industry and government agencies come face-to-face with a worsening global climate crisis...
Scientific studies and climate research models have found that the number of extreme fires could increase by as much as 30% globally by 2050. By 2100, California alone could see a 50% increase in wildfire frequency and a 77% increase in average annual acres burned, according to the state's most recent climate report. That's largely because human-caused climate change is driving up temperatures and drying out the landscape, priming it to burn, according to Kate Dargan Marquis, a senior advisor with the Gordon and Betty Moore Foundation who served as California's state fire marshal from 2007 to 2010.... "[T]he policies of today and the technologies of today are not going to serve us tomorrow."
Today, more than 1,100 mountaintop cameras positioned across California are already using artificial intelligence to scan the landscape for the first sign of flames and prompt crews to spring into action. NASA's Earth-observing satellites are studying landscape conditions to help better predict fires before they ignite, while a new global satellite constellation recently launched by Google is helping to detect fires faster than ever before.
One 35-year fire service veteran who consults on fire service technologies even predicts fire-fighting robots will also be used in high-risk situations like the Colossus robot that battled flames searing through Notre-Dame Cathedral in Paris...
And a bill moving through California's legislation "would direct the California Department of Forestry and Fire Protection to establish a pilot program to assess the viability of incorporating autonomous firefighting helicopters in the state."
Swatting to Swamping (Score:4, Insightful)
I predict "swamping" will become a thing. Someone will figure out how to trick these to dump water on their friends (or enemies).
Re: (Score:2)
Re: (Score:2)
what is the value? (Score:4, Insightful)
Of removing all humans from the loop? And what is the evidence to claim that the "policies of today and the technologies of today are not going to serve us tomorrow"? Sounds like bullshit to me, someone's got a profit motive to lie.
Re: what is the value? (Score:4, Insightful)
Adding storage ponds and tanks to refill fire fighting aircraft will reduce the amount of time to refill. More short trips is reduces the latency and increases the total amount of water you can deliver.
Obviously people who work on this stuff for a living know best, but just a quick bit of napkin math is making me question if making pilotless drones is really the best solution.
Re: (Score:3)
Fire spreads quickly. If the drones are always on standby (difficult proposition with humans to always have one waiting in the cockpit) waiting to take off immediately with a full load, that can mean the difference between a massive wildfire and a small spot fire that is quickly extinguished. Your back of napkin math is based on total volume of water delivered, but wildfires at the very start should roughly be modeled using a form of constrained exponential growth. Your model might be suitable for a large f
Re: (Score:2)
Getting a little water there now is much better than a lot more water later.
The key is to extinguish the fire before it spreads.
Re: (Score:2)
Re: (Score:1)
Plus a lot of the potential work in dropping things o
What is the value of a human life? (Score:3)
Seems like every wildfire now, aircraft with humans in them get grounded because some idiot flies their drone into the wildfire area in search of viral video. Either because there's an actual collision, or because a drone was spotted and it's not worth risking a human pilot in that area.
Like this: https://www.cbsnews.com/losang... [cbsnews.com]
If the firefighting aircraft are also drones, we can keep them fighting the fire while we go after the human idiots in the loop illegally flying their drones.
Re: (Score:3)
What is the value... Of removing all humans from the loop?
The point here is not really removing humans from the loop. What you are really doing here is setting a policy for how to handle potential disaster situations and you let an automatic system handle it. Humans make the policies, but then an automated system can go ahead and handle it without waiting for a human to approve it. However, humans still supervise the system and can override it or provide additional instruction or control as needed. If human overseers don't do anything though, the system just goes
Re: (Score:3)
Heavy capacity electric drones might also end up being better than a "Black Hawk" or other traditional helicopter
Agreed. A better option might be the K-Max intermeshed dual rotor helicopter. It has almost twice the external load capacity of some other helicopters and has already been tested with remote piloting. The sheer availability and parts accessibility of more common helicopters might be the reason they are testing with the Black Hawk. K-Max helicopter [wikipedia.org]
Heavy capacity electric drones, once hardened with heat shielding, might not have the lift capacity to make them suitable, even in swarms. But two or three lo
Re: (Score:2)
Of removing all humans from the loop?
Money.
It costs more to hire a human than to not hire a human. Duh.
someone's got a profit motive to lie.
Who's lying? I RTFA, and I didn't see anything in it that is a lie.
Re: (Score:3)
Fighting wildfires is extremely dangerous. It's low altitude flying, and any pilot will tell you, altitude is life. Fires also stir up wicked turbulence making it challenging to fly through. And you've got a crew of 2-3 people per aircraft who are really only a mechanical failure away from being put in danger - low altitude flying means if the engine fails there aren't many options. And while most firefighting aircraft are usually multiengine (usually - single engine aircraft do exist), an engine failure at
Re: (Score:3)
What is the value of removing all humans from the loop?
There are a lot of advantages:
Um, say again? (Score:5, Funny)
within seconds, a satellite dish swirling overhead ...
That sounds really dangerous. :-)
Except for the divers recovering water buckets (Score:2)
Without deploying a single human
Except for the divers at the lake where it refills buckets. They are needed for the occasional bucket that is ditched during a lift, to recover it and reconnect the rigging.
Re: (Score:2)
If something like this is used as a front line emergency response system, it may not be necessary for multiple trips and refills to even be made. The idea seems to be to detect potential wildfires when they are just small spot fires and put them out before they can become raging wildfires. So, an automated firefighting drone deployed from a potentially unmanned station may make a lot of sense for fast response.
If the fire grows, the rest of the firefighting can be done the more traditional way. Or, also, th
Re: (Score:2)
Re: (Score:2)
There aren't really water tanks for helicopters, I think that's more for the dedicated fixed wing aircraft.
Certainly they typically use collapsible buckets in traditional firefighting. The idea of tanks was an alternative to the potential dangers and logistical issues you mentioned of an autonomous aircraft dipping one of those buckets into a lake or pond. I was considering a system where the autonomous craft that can sit in a remote hangar for years is either preloaded with water (or firefighting foam) where a tank would make more sense than a bucket since the contents would be prone to evaporation or even be u
Re: (Score:2)
Re: (Score:2)
Well, bear in mind that, as I said, the primary purpose would be to get the first loads of water/foam to the site of the fire as quickly as possible. Even if all the drone systems did was that first load, it could still make a major difference in heading off a fire before it grows into something that actually needs large volumes of water. So the idea would be that the drones sit with preloaded tanks at remote, probably unmanned, hangers spread out through the area you want to protect in a much more distribu
Re: (Score:2)
Well, bear in mind that, as I said, the primary purpose would be to get the first loads of water/foam to the site of the fire as quickly as possible.
I think that might be practical with actual commercial drones. A Blackhawk sitting around waiting for a fire just sounds like overkill, I think they'll be called in after the fact, like the old Hueys. Automated or manned they are just too expensive and capable to just have sitting around and waiting for a fire.
For that purpose, there could just be larger tanks onsite at the hanger locations.
These fires are often in wilderness locations, far from hangars. Hueys dipping in the lake. Landing on flat ground around the lakeshore when necessary. Breaks, food, face to face meetings, etc. Only f
Re: (Score:2)
I think that might be practical with actual commercial drones. A Blackhawk sitting around waiting for a fire just sounds like overkill, I think they'll be called in after the fact, like the old Hueys. Automated or manned they are just too expensive and capable to just have sitting around and waiting for a fire.
Oh absolutely. Ideally you want something that can sit for years and take off essentially instantly when needed. Conventional helicopters simply can't do that. Way too much maintenance required to stay flightworthy. Electric drones have way more potential to just be stored until they're needed.
These fires are often in wilderness locations, far from hangars. Hueys dipping in the lake. Landing on flat ground around the lakeshore when necessary. Breaks, food, face to face meetings, etc. Only flying back to a base for fuel. The idea being to maximize sorties/drops per flight hour, staying remote as long as the fuel lasts.
From conventional manned hangars, sure. When I say hanger here I'm not talking about a conventional manned hangar. I'm talking about prefab units that can be dropped in lots of remote locations and just left there unt
Military flight is thoroughly understood. (Score:2)
Automating aircraft and missile controls is ancient history, the word "autopilot" comes to mind.
Humans tire, stress, need to eat and excrete and unless sitting cockpit alert require scheduling or being on standby alert to begin their sortie. Flying is physically and mentally demanding when managed from the airframe. Meat in the seat limits permitted max G loads limits maneuverability. Meat at the base can be swapped out as expedient.
Remote operators are long proven on combat drones flying much more demandin
Re: Military flight is thoroughly understood. (Score:2)
That's why you hire more people than you strictly need. Lots of people on standby.
Jesus Christ (Score:3)
Don't put a $22m Firehawk in the hands of a black box AI system. I don't need any aircraft fires in my backyard forest.
Imagine reality (Score:2)
Re: (Score:2)
But computers will do a better job detecting 'anomalies' from space! Not fires, just anomalies that need water dumped on them.
A basic UH-60 probably costs around 6 million/unit. The operating costs are 2-4k/hr. Add all this tech in there and I bet the minimum cost will go up to 15 million.
I think what they're trying to sell is that an autonomous system will be able to outpace the current system at catching fires before they get out of hand.
The LA times sounds like they're selling the idea. Or at least they'
Project management for this initiative (Score:2)
Old School (Score:2)
I'm working on a satellite that, as soon as the fire is detected, it starts raining.
Re: (Score:2)
Already imagined (Score:2)
I already imagined it when I read Arc of A Scythe.