Will development of good AI routines be beneficial for developing an UAV?

[Skarphol]

Hi!

I was reading a piece on UAV (unmanned aerial vehicle) and UCAVs the other day, and started thinking: Would a company who developes UAVs and UCAVs be interrested in the AI that Oleg and similar developers are creating for games like SOW?
Is there any similarities?
I would suppose so; does anyone know?

Skarphol

(By the way; the russian airforce does not field UAV's, the russian army use Israel-built UAV's. Maybe Oleg has been delayed in development of SOW because he has been drafted by the russian airforce to program UAVs?? That last part is only speculative and not backed by any facts, rumors or post on obscure forums what so ever)

[SlipBall]

Hi!

I was reading a piece on UAV (unmanned aerial vehicle) and UCAVs the other day, and started thinking: Would a company who developes UAVs and UCAVs be interrested in the AI that Oleg and similar developers are creating for games like SOW?
Is there any similarities?
I would suppose so; does anyone know?

Skarphol

(By the way; the russian airforce does not field UAV's, the russian army use Israel-built UAV's. Maybe Oleg has been delayed in development of SOW because he has been drafted by the russian airforce to program UAVs?? That last part is only speculative and not backed by any facts, rumors or post on obscure forums what so ever)



I might be getting your question wrong, so sorry if that's the case. But I think that all the UAV's use a camera and a guy sitting in a comand center with a joystick, gps, guages and the like.

[Skarphol]

OK, I'm thinking of UAV's that travel autonomiously 'on their own'. They are getting an assigned area to monitor and then they just go there and survey that area, regardless of weather etc. Not necessarily military activity, but monitoring of pollution etc.
I think there are planes that actually flies themselves.
But of course, there are a lot of UAV, like Predator etc. that are 'flown' by personell on the ground. Not by joystick, but they are given orders as to where to go, where to direct their cameras etc.

Skarphol

[Letum]

Autonomous vehicles don't face the same challenges as AIs in games.

The main challenge for real autonomous vehicles is situational awareness.
In a game this isn't a problem as the program tells the AI what is a enemy/friend/plane/bush/ground/runway. Real world AIs struggle with this kind of thing a lot.

Flight routines are simple compared to these challenges.

[Valtyr]

Being that I am trained to pilot (Small)Suav's myself I can tell you it would have to be some smart AI to do all the piloting. Whem the UAV is in the air for a routine patrol for example, often times you spot people or points of interest all of a sudden, sometimes you fly over a spot on a hunch. A AI could not react to a hunch because well, it doesn't have that capabilty. However UAV's can use waypoints and such to fly on autopilot, loiter and hold altidude. Forgive the horrible spelling, i'm writing this on my phone.

[Feuerfalke]

Different goals and different problems.

In contrast to the real world, a plane in a game flies in a virtual environment. Everything put into the game is calculated and therefore for terms of simplicity transfered into the AI-routines as necessary. No need to adopt to unknown territory or obstacles.
A simple example: When Flak fires at an AI-plane, it can be noted by simply setting a variable, telling the AI it is under fire. Another example is the spider-sense in IL2 that warns an AI pilot as soon as a fighter is in a given distance. In the real world, the AI would have to be able to interpret sensors to even identify such a threat and out of the masses of information gained from the sensors and that is a difficult task.

On the virtual battlefield, the AI also tries to incorporate human behavior. SoW will even incorporate fear, fatigue, aggressiveness, skill, etc. That's exactly the points you want to eliminate for autonomous RL planes.

[Bobb4]

Different goals and different problems.

In contrast to the real world, a plane in a game flies in a virtual environment. Everything put into the game is calculated and therefore for terms of simplicity transfered into the AI-routines as necessary. No need to adopt to unknown territory or obstacles.
A simple example: When Flak fires at an AI-plane, it can be noted by simply setting a variable, telling the AI it is under fire. Another example is the spider-sense in IL2 that warns an AI pilot as soon as a fighter is in a given distance. In the real world, the AI would have to be able to interpret sensors to even identify such a threat and out of the masses of information gained from the sensors and that is a difficult task.

On the virtual battlefield, the AI also tries to incorporate human behavior. SoW will even incorporate fear, fatigue, aggressiveness, skill, etc. That's exactly the points you want to eliminate for autonomous RL planes.
You know this site is going down hill when we move from talking IL2/SOW to UAV's :rolleyes:

[Feuerfalke]

Lol ;)

[Skarphol]

Weeelll, there isn't too much to talk about on this site anyway, reading the same repeated questions over and over again is boring and futile, and besides; there is a lot of people with insight into aviation hanging around here, so I gave it a go.

I guess you guys are right about different problems and different solutions with UAV development and AI developent.

I'm really curious about the AI in BOB. I think IL-2 must have had some of the better AI behaviour in a flightsim, but I haven't spent much time on other flightsims, though. Just som AEW and MSCFS..

Skarphol

[Igo kyu]

I'm really curious about the AI in BOB.
Me too.

I think IL-2 must have had some of the better AI behaviour in a flightsim, but I haven't spent much time on other flightsims, though. Just som AEW and MSCFS..

Skarphol
Maybe, but they are really poor at turn fights. In a turn fight, the guy behind drives, the guy in front keeps turning until the guy behind gives up. The Il*2 AI don't do that, if they are in front they change turn direction straight across the following planes fire. The guy in front has an option between blacking out, and dying, the guy behind has an option between blacking out and losing the chase, so the guy in front can turn harder.

[zapatista]

Being that I am trained to pilot (Small)Suav's myself I can tell you it would have to be some smart AI to do all the piloting. Whem the UAV is in the air for a routine patrol for example, often times you spot people or points of interest all of a sudden, sometimes you fly over a spot on a hunch. A AI could not react to a hunch because well, it doesn't have that capabilty. However UAV's can use waypoints and such to fly on autopilot, loiter and hold altidude. Forgive the horrible spelling, i'm writing this on my phone.

hiya Valtyr,

why are those unmanned drones not used more extensively in afghanistan ?

when you look at documentaries like "ross kemp in afghanisthan" (a brittish reporter with a camera crew embedded with UK troops), you can see the infantry soldiers are in constant danger of ambush, and once they engage the enemy it is a very defensive procedure for them where they call in artillery support from their fire bases or need to call in fast air to drop laser guided munitions on a specific building or suspected taliban position (with a high risk of friendly fire)

on the rare occasion those brittish troops were able to get a helicopter to provide support, the whole tactical situation changed and the engaged taliban stopped fighting to try and not attract attention to their position and suffer the wrath of a well armed attack helicopter (and there seemed to be a significant lack of availability in helicopters to provide support for infantry foot patrols)

it would seem to me that a handfull of armed drones (both as small armed planes or helicopters) accompanying those foot patrols would immediately significantly change the situation on the ground for the infantry soldiers and make them more effective and reduce casualties, but i never heard of any mention of them for use in those situations. it cant only be an issue of high cost, these same infantry men often seem to fire multiple javelin shoulder held missiles on a patrol (at 50.000 $ per unit i believe). using these armed drones in much higher numbers would seem to me to be the next level in fighting tools that a modern army needs

any thoughts why they are not yet used in high numbers in day to day ground operations like that ?

[zapatista]

Weeelll, there isn't too much to talk about on this site anyway, reading the same repeated questions over and over again is boring and futile, and besides; there is a lot of people with insight into aviation hanging around here, so I gave it a go.l

dont pay any attention to the moaners, its an interesting topic

afaik the artificial intelligence routines used in autonomous unmanned vehicles are based on neural networks first studied in simple biological organisms/creatures, and trying to get an engineered robot to even replicate some of those basic behaviors is extremely complex

if you simply need a drone like that to map a certain area, it is not to difficult. the same principle is already used in agriculture where you can have farm equipment (like tractors, harvesters etc..) cover a particular field while guided by gps, and the equipment is fully controlled by an onboard computer, it is being used like that and does work well

the problem that arises with a drone having to move in 3 dimensional space (not that much harder) and that it has to analyse and "understand" what it sees and then respond to unpredictable events is the hard bit. to determine what events are a trigger is part of the problem, but the processes involved in the human brain assessing what it sees in similar situations is incredibly complex, and hard to copy effectively with artificial intelligence routines so far

[Bobb4]

Moaning has its virtues... It lets off steam.
However to your point why unmanned drones are not use more in patrol type engagements.
Logistics pure an simple.
Having a drone for every unit makes no sense and unlike a plane with a human element who can act on hunches a drone is just a flying camera with a few heat sensors.
What you saw in Ross Kemps Afganistan was war, pure and simple.
Having been in similiar situations however not with said armies, technology helps a lot but it is always the grunt on the ground that takes the objective.
As for operational budget, let's just say the grunt on the ground does not give a sh%t how much a javlin costs.
How much do you think it costs just to keep the fast movers on standby... $10 000 and when they unload a smart bomb, well add +/-$20.000 to the bill.

[KG26_Alpha]

UAV's can be more than just frontline recon & tac sits, they can do more logistics also in unfriendly areas.

From> Flight Global

The US Marine Corps has announced plans to audition multiple unmanned aircraft by next February to perform the resupply mission.

The solicitation released on 17 April by the Marine Corps Warfighting Laboratory (MCWL) addresses one of the few airborne mission areas still not served by unmanned aerial systems (UAS).

The most likely competitors for the emerging mission area include the Lockheed Martin/Kaman unmanned K-MAX, Boeing Unmanned Little Bird, Boeing A160 Hummingbird and the Northrop Grumman RQ-8B Fire Scout.

Northrop Grumman RQ-8B Fire Scout
© Northrop Grumman
RQ-8B Fire Scout is a contender for a resupply mission

The MCWL will require the demonstrator aircraft to deliver between 4,535kg (10,000lb) and 9,070kg of cargo up to 150nm within a 24hr period. The aircraft should be able to hover in ground effect/hover out of ground effect at 3,658m (12,000ft), and fly with a full cargo load up to 4,572m.

The Lockheed/Kaman team confirms that it will respond to the MCWL offer. The team formed in early 2007 specifically to unlock the market for unmanned aerial resupply.

The team has acquired a total of three K-MAX and one Burro helicopters on the commercial market to adapt into unmanned demonstrators.Lockheed staged a demonstration of the unmanned K-MAX for the army last April at Fort Eustis, Virginia, carrying two sling loads weighing 680kg.

The same aircraft also demonstrated carrying 2722kg in November to a Marine audience at Quantico, Virginia. Although the USMC demonstration is moving forward, military officials remain skeptical about the concept of routine unmanned aerial re-supply.

Tim Owings, the army’s deputy UAS programme manager, told Flightglobal in February that unmanned aircraft would be an ideal solution to resupply troops in active combat.

However, Owings was still dubious that an unmanned aircraft could replace manned cargo helicopters for routine resupply missions. “You have to really make a case at that point of cost effectiveness, I believe,” Owings said. “I think the jury is still out on if that can be done or not.”