complex maze (pt 1)

Home | Videos | Contact Us   




Robot navigating in a complex maze using large maps (pt 1)



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 navigating a complex maze using large maps.  There are no sound during parts of the video because I wanted to show the viewers what the robot is thinking while playing the game.  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.

In games like Metroid or Castlevania or Zelda, the player has to navigate in a massive environment.  Maps are provided to the player so that he doesn't get lost. In this video, i'm trying to demonstrate how the robot thinks while navigating in a large environment using maps.

As you can see, the robot is analyzing the map, making personal observations, debating where to go, making decisions on how to do searches and so forth.  At the same time, he is mentally remembering general or detailed parts of the map to do his navigation.

Navigation in an unknown environment is just one small task the robot has to do.  A real robot with human level intelligence can do multiple tasks simultaneously.  He can:


1.  navigate in an unknown environment 

2.  kill/avoid enemies.

3.  follow rules of the game.

4.  do recursive goals.

5.  use logic to determine next goals.

6.  use common sense to solve problems.

7.  generate ideas to solve problems.

8.  predict the future for selective objects.

9.  generate strategies to defeat multiple enemies.

10.  manage multiple tasks at the same time.

11.  find optimal routes to travel so that repeated travel is brought to a minimal.


In one scene, the player was stuck and didn't know what to do.  He needed to raise the elevator in order to go to the top level.  The robot tried 3 ideas before solving the problem.  This ability to generate ideas to solve problems is very important to human intelligence.  It shows the robot can adapt and change so that a problem can be solved.



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

Copyright 2006 (All rights reserved)