strong-artificial-intelligence.com 

Strong AI
Evolutionary Algorithms
Neural Networks
Bio Computing
Artificial Life
Agents
Cellular Automata
Fractals
Schulers.com
Login Form
Username

Password

Remember me
Password Reminder
No account yet? Create one

Evolutionary Algorithms
Softbots as Testbeds for Machine Learning - Etzioni (1992) PDF Print E-mail
Written by Administrator   
Friday, 21 April 2006

If you want to think about thinking, you have to think about thinking about something." --- Seymour Papert A softbot (software robot) is a program that interacts with a software environment by issuing commands and interpreting the environment's feedback. Because softbots are much easier to build than physical robots, softbots are an attractive substrate for machine-learning and agentarchitecture research. To illustrate this point, we consider Rodney, a UNIX 1 softbot under development at...

Using Genetic Algorithms to Learn Reactive Control.. - Ram, Arkin, Boone.. (1994) PDF Print E-mail
Written by Administrator   
Friday, 21 April 2006

This paper explores the application of genetic algorithms to the learning of local robot navigation behaviors for reactive control systems. Our approach evolves reactive control systems in various environments, thus creating sets of "ecological niches" that can be used in similar environments. The use of genetic algorithms as an unsupervised learning method for a reactive control architecture greatly reduces the effort required to configure a navigation system. Unlike standard genetic...

Evolving Robot Behaviors - Schultz, Grefenstette (1994) PDF Print E-mail
Written by Administrator   
Friday, 21 April 2006


This paper discusses the use of evolutionary computation to evolve behaviors that exhibit emergent intelligent behavior. Genetic algorithms are used to learn navigation and collision avoidance behaviors for robots. The learning is performed under simulation, and the resulting behaviors are then used to control the actual robot. Some of the emergent behavior is described in detail. INTRODUCTION The field of robotics offers an endless supply of difficult problems, requiring an equally impressive...

An Evolutionary Approach to Learning in Robots - Grefenstette, Schultz (1994) PDF Print E-mail
Written by Administrator   
Friday, 21 April 2006

Abstract: Evolutionary learning methods have been found to be useful in several areas in the development of intelligent robots. In the approach described here, evolutionary algorithms are used to explore alternative robot behaviors within a simulation model as a way of reducing the overall knowledge engineering effort. This paper presents some initial results of applying the SAMUEL genetic learning system to a collision avoidance and navigation task for mobile robots.

Evolution of Subsumption Using Genetic Programming PDF Print E-mail
Written by Administrator   
Friday, 21 April 2006

Abstract: this paper, we use the genetic programming paradigm to evolve a computer program that exhibits emergent behavior and enables an autonomous mobile robot to follow the walls of an irregularly shaped room. The evolutionary process is driven only by the fitness of the programs in solving the problem

Google
 
Web news.schulers.com
www.strong-artificial-intelligence.com schulers.com