FAQSearchEmail

humanlevelartificialintelligence.com   

  
 origami

Home | Videos | Contact Us   

 
Home
HLAI
UAI
Videos
Books
Patents
Notes
Donation

     
 

             

 Following instructions to make an origami using Human Level Artificial Intelligence

 

     

Note:  To make this website free to the public please click on an ad to support my sponsors or you can make a tax-deductable donation using Paypal (click on the donation icon on the left).

 

This video shows a robot following instructions step-by-step from a book to make an origami crane. There are no sound in the video because I wanted to show the viewers what the robot is thinking while following step-by-step instructions. The flashing text and freeze frames are the internal thoughts of the robot and not instruction text for the viewers. These internal thoughts describe the details of how the robot produce intelligence.

My robot doesn't use: planning programs/heuristic searches (used by MIT and Stanford University), Bayesian's probability theories for decision making, Bayesian's equation for induction and deduction, semantic networks for natural language understanding, predicate calculus, common sense systems, first-order logic, rule-based systems, genetic programming, or MACHINE LEARNING.

The robot required looking at each step in the instruction manual on the first try. In the second try, the robot only needed to look at the steps a few times (most of the steps are extracted from memory). After 3 tries, the robot is able to make the origami crane without the instruction manual. He uses data from memory to make the crane. From here on, the robot is able to make an origami crane from knowledge from its brain.

This skill is very important to learn processes. Using this method, the robot can make any origami object simply by following instructions in books. It also has to practice making the origami object so that this knowledge is stored in memory. After 2-3 tries following instructions from books, the robot can make an origami object simply by extracting a memory of the instructions.

This method can also be used to do things like: fixing a car, making lego objects, cooking food, fixing computers, building things, etc. I personally think that this skill is very important because most of the knowledge learned come from reading instructions from books or listening to instructions from teachers.

Another important note worth mentioning is that the robot uses logic and common sense to analyze and interpret visual instructions. Notice that the instruction manual in the video doesn't have words. The instructions are based on visual images. The robot has to identify what steps needs to be done. Some visual instructions are confusing and that is where logic comes in. The robot uses logic to identify exactly what the author is trying to convey.

Also, the pathways in the robot's brain store 5 sense data from the robot. Thus, when the robot is making the crane he is storing frame by frame in memory. The pathways store the linear steps the robot does in order to make the crane. This also means that when enough practice is had, the robot will have lots of movie sequences in memory on how to make an origami crane. In other words, the robot's pathways to make a crane can do things automatically and doesn't require instructions.

 

 

Home | HLAI | UAI | Books | Patents | Notes | Donation

Copyright 2006 (All rights reserved)