I am going to revisit a previous post for Rich to think about:

Now, Moving more into the subject of Self-Awareness. I was recently reading Scientific America when i noticed some articles on a very different way of doing programming.

It said that Scientist had made their robots self-aware. The way that they did it was:

Program the robot like you do normally. Preform an action after you have made a decision. Think about what choice you have made. Give yourself a score. You have either did well or made a mistake. The score will be graded, so the highest score is what you are looking for. They called it dividing it into two parts, the regular part and the new part that does nothing but "Think about what you have Thought about." They said by doing this it is like a human brain, two virtual hemispheres and a Algorithm connecting the two by generalizing and evolving.

This sort-of reminded me of a system that used Confidence levels after actions. each action would bump UP the CLevel or bring down the FLevel. Next time it made a choice, it would not make the same mistakes, Making the robot smarter the longer it operated.

It is very hard for me to put into words. If you had such an Algorithm it would be nice. This could be put on the wait list , maybe.

Hope that this helped.

Mel

I get the general idea, I think. But the thing with robots is, we can always program them not to make mistakes Not quite as fun to watch though... kinda like having a newborn baby that can walk.

by mistake, I meant like it was running into a wall and it learned not to go in that direction. Each time it would bump into the wall it would lower it's confidence level until it was zero. From that point on, if you told it to go in the direction of the wall, it would know already not to go there and choose another direction with more confidence. It would not be a mistake per say, just a way to Learn what NOT to do under different circumstances.

I know what you are getting at.

Take the ping roam script for an example. Remove the part where it knows which way to turn based on the sensor readings. Now we add in code to make it choose a random direction based on previous results, but while it does that it still records the sensor readings and checks confidence. To start with it will be bumping in to walls (unless it is lucky with it's guesses) but as it goes on it will learn that a high reading on the left will have a lower confidence if turning left and a higher for turning right, so it will eventually turn right more often...

Wow that is hard to explain, I may not have even explained it right... I guess the only way to explain properly is by making such a script...

But, like i said, we can program the robot not to make mistakes. If you want to. But mistakes make it seem more alive in my opinion I like mistakes

Someone once said that "Every Mistake is an opportunity to Learn something." and Bob Ross made a lot of "Happy Mistakes" in his paintings. I used to teach and I would tell my students not to be afraid to make mistakes. In fact, go out and make as many as you can in order to learn. They liked that.