Fractal branching ultra-dexterous robots

If you're into AI and robots, then you no doubt know who Hans Moravec is. He pretty much has set out to make better-than-human machines. I'm not really a robot guy, so I honestly didn't know too much about Hans and his work. Thanks to Jim Gray for tuning me into this. Really brilliant stuff. ( Maybe Hans will help me design TOS: Thinking Operating System :) )

Here's a quote from one of his papers on bush robots that nicely generalizes the notion of fractal hands:

"Once upon a time, the most complex animal was a worm. The stick-like shape was poorly adapted for manipulation and even locomotion. Then these stick-like animals grew smaller sticks, called legs, and locomotion was much improved, although they were still poor at manipulating. Then the smaller sticks grew yet smaller sticks, and hands, with manipulating fingers were invented and precise manipulation of the environment became possible.

Generalize the concept. Visualize a robot that looks like a tree, with a big stem, repeatedly branching into thinner, shorter and more numerous twigs, finally ending up in vast numbers of microscopic cilia. Each intermediate branch would have several degrees of freedom of sensed and controlled motion. Though each branch would be a rigid mechanical object, the overall structure would have an organic flexibility because of the huge numbers of degrees of freedom. At the outer extremes, the machine would have an enormous number of individually positionable and naturally swift manipulators, coordinated for simultaneous execution of otherwise unimaginable tasks by signals and power from the central regions."

Yes, I see.

Check out more of these papers on Bush robots. Enjoy.

Comments

[ikari]

Yeah, robots is another interesting topic :) Generally because of what I read about it these days.
Once upon a time we wanted to make a robot that will be able to achieve some simple tasks on his own.
Then, we wanted to give him a human shape and a better program.
Then we wanted to replace the program by neurotic network.
We came back to the robot's movement - lately scientists made a robot with muscles instead of electric elements...
And now I heard that they made a robot with brain cells to be used as its CPU.

Where is it going? Seems like scientists' goal is to make some kind of a human, eventually better than us. Will robotics and biology change into one? :)

(PS. Pardon my English, I feel like i've made some mistakes here :))

[Carmine]

ikari, making intelligent, thinking machines to the extent that they are creative and speculative is something these guys are working on and truly believe will be achieved in 50 years or so. Remember HAL from 2003 A Space Odyssey? Well, "he's" already been conceived. Now, we just need to wait out the term phase ( 9 months for a human, 50-75 years for HAL ;) )

[ikari]

I guess the number of parents is proportional to the term phase length? :)
And what about all the things that people are scared about? Robots are made to be better than us, better, smarter, faster, more precise. It's people who made them and it's people who made the business. And what is the business rule number one? Employ only the best and most efficient employees. Machines, that is. In the 20th century many people lost their job and had to find a new one because they were replaced by machines.
Up to this day machines were replacing people mostly in production halls to produce large amount of goods faster and more precisely. And of course to calculate lots of data fast and exactly. But what will happen when we'll finally make good AI systems? Every employer would like to have highest profits, most intelligent and infallible employees. So if he can afford it, he'll replace us.
Maybe in 100 years the only human professions will be computer designers and programmers? All other can be easily done by machines.
Have you seen "Animatrix - The Second Renaissance"? If we'll be able to teach machines abstract thinking - maybe they will design new, better AI on their own. That'll make mankind useless. We will either see what is really important in life and manage to make machines serve us, or just be the "worse ones", maybe even try to start a war with them and eventually lose (they're gonna be better than us, right?)