Jump to content

Robot Intelligence


KFC

Recommended Posts

what Sort of inteligence?

I`ve done alot work with neural cybernetics, specificaly for Robots, and I can tell you now, that using little PIC chips, won`t add up to much in the way of IQ points :)

you may want to explore Fuzzy Logic as an adjunct.

the way I would do something like that IF that was all the parts I ha to play with, would be to assign one chip per task, with plenty of feed back, Motility, endeffectors, senses etc...

so that each Single item can "look after itself" independantly.

from there you`de have a PIC as a priority discriminator for over rides of the Goal seeker PIC.

 

I`ve used this method myself a few times and to great effect, with plenty of emergent behaviour as a result :)

Link to comment
Share on other sites

I think YT is a robot from the future. it explains so so much. YT2095 is just his model number.

 

Yes your right it would explain a lot :rolleyes:

 

Back on topic, robot intelligence is still a young subject, unless your inteling to pay bilions for one of those really advanced ones from Japan that is :)

 

As whas asked earlier, you'll need to state more exactly what your looking for :)

 

Cheers,

 

Ryan Jones

Link to comment
Share on other sites

for a start all sensors should be On and Active at all times anyway, except where they are heavy power users.

each part should be capable of working with reasonable autonomy with on the bare essentials in way of instruction(s) (so you don`t pull the goal seeker program down with needless calculations).

for example, you want to move forwards, but the left side is higher than the right side, naturaly it`ll want to travel downwards in an arc as it moves forwards, therfore without need for top down error correction, the mobility component must be able to sense the difference in rate between each side and either Steer or speed up one side to compensate for this drift, thus maintaining a Straight line, the only time it should send intructions Upline should be to state Task complete, OR on obsicle/collision, then feedback goes directly to the priority discriminator and is rated (voted on) as to it`s problem causing potential when offset against the Goal seeker program.

contingent instruction would then be sent back to the mobility component and action taken.

 

a Modular system keeps the overheads low, and less likely to tie up a system.

Link to comment
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now
×
×
  • Create New...

Important Information

We have placed cookies on your device to help make this website better. You can adjust your cookie settings, otherwise we'll assume you're okay to continue.