Welcome to Gaia! ::

Skynet has three things that modern machines, no matter how advanced, do not: an overall strategy of conquest, an understanding of tactics, and a massive industrial base capable of supporting them.

There is no such thing as a universal fabricator. There are some pretty neat rapid-prototyping machines that could be adapted, to a limited degree, to mass-produce any object you'd care to name.

Yes, we have robots that are heavily armed and network-accessible. But the real threat is not from that network gaining sentience and turning its weapons against us; it is from our fellow human beings hijacking the network and turning its weapons against us.

There's a reason that almost every autonomous or semi-autonomous weapon has a manual override/self-destruct mechanism built into it. We've had too many cases of unexpected situations and random mechanical failures leading to disaster when a weapon fired on a target it wasn't supposed to. (One CWIS turret failed to register IFF signals from a friendly aircraft and fired on it. Another automated weapon, during a demonstration to a crowd, suffered a misfire and partial cookoff, leading it to turn around and fire at the spectators.)

And that is why every piece of powered equipment, whether it is a forklift or a cruise missile, has a Big Red Button(tm) to make it stop doing whatever it's doing, for safety's sake.
ExDxV
How robot will be able to feel real world without vision?

The vision is most important system of robot brain wink


MArkers are a common tool in robotics. However I would like to point out the only uniqyue feature of this one is it is capable of setthing markers based on a visual cue rather than a standard sensor. In any case 'seeing' is not the most important system in a robot brain. The ability to see would be nothing if it could not do anything with that information. Proccessing and programming are the most important. I am aguessing this works though the use of a laser designation software. This would allow the robot to see and mark locations in front of its 'line of sight' as it were and it would be able to process the sights seen as an electronic map memorized as it moves along. I am quite surprised they would try to make robots using this method becvause it is a very complicated method of doing something much more simple. Using advanced sinar systems it would be able to do all of what it can do in this with a greater level of detail and instantaneously. All it would need is a range finder and it would be able to have a perfect 3D map of an area.

Also robots do not 'feel' they have no nerves. Robots also do not need to see in the same way we do but simply know the information which in this case is the location of the objects in a room and the room itself.
It is a testing of the enhanced tracking algorithm that takes into consideration variable servo speed.

See here for more details.
Why does this equal Skynet, again? O_o
I just try to create machine that can see real world and I think that this solution is pretty possible because Mother Nature already made it a long time ago wink

The robot navigation in my experiments was also based only on machine vision with using of AVM algorithm.

See also "Twinky rover presentation".
ExDxV
I just try to create machine that can see real world and I think that this solution is pretty possible because Mother Nature already made it a long time ago wink

The robot navigation in my experiments was also based only on machine vision with using of AVM algorithm.

See also "Twinky rover presentation".


Cool.
chromealias's avatar

700 Points
  • Member 100
  • Gaian 50
Not even close. We're lucky if we ever see 'sentient' AI which, like us, are under the illusion of consciousness.
We Are Organisms's avatar

Cluttered Shapeshifter

chromealias
Not even close. We're lucky if we ever see 'sentient' AI which, like us, are under the illusion of consciousness.
how r we under the illusion of conciousness?
Fun with AVM Navigator

User Image - Blocked by "Display Image" Settings. Click to show.

It's little demo of object recognition and learning from motion with helping of AVM Navigator.

All object rectangle coordinates are available in RoboRealm pipeline from external variables:
NV_ARR_OBJ_RECT_X - left-top corner X coordinate of recognized object
NV_ARR_OBJ_RECT_Y - left-top corner Y coordinate of recognized object
NV_ARR_OBJ_RECT_W - width of recognized object
NV_ARR_OBJ_RECT_H - height of recognized object

So you can use it in your VBScript program.

See here for more details.
Alan
Hi,

I noticed in the youtube video that you jiggle the object (your face or the book) slightly during the learrning phase. Is this an advantage?

Cheers,

Alan


In fact the AVM algorithm is not invariance to rotation and you should show the object for memorizing to AVM search tree under different angles during training for further correct recognition.

See also an example of using of Canny module as background for AVM Navigator:

User Image - Blocked by "Display Image" Settings. Click to show.
mace_of_knowledge's avatar

Magnetic Genius

5,100 Points
  • Somebody Likes You 100
  • Invisibility 100
  • Popular Thread 100
No joke "skynet" is the name of an airforce comunication program, no idea what it does but get your tinfoil hats ready. burning_eyes

Quick Reply

Submit
Manage Your Items
Other Stuff
Get Items
Get Gaia Cash
Where Everyone Hangs Out
Other Community Areas
Virtual Spaces
Fun Stuff