On the Origin of Environments by Means of Natural Selection

Authors

  • Moshe Sipper

DOI:

https://doi.org/10.1609/aimag.v22i4.1597

Abstract

The field of adaptive robotics involves simulations and real-world implementations of robots that adapt to their environments. In this article, I introduce adaptive environmentics -- the flip side of adaptive robotics -- in which the environment adapts to the robot. To illustrate the approach, I offer three simple experiments in which a genetic algorithm is used to shape an environment for a simulated khepera robot. I then discuss at length the potential of adaptive environmentics, also delineating several possible avenues of future research.

Downloads

Published

2001-12-15

How to Cite

Sipper, M. (2001). On the Origin of Environments by Means of Natural Selection. AI Magazine, 22(4), 133. https://doi.org/10.1609/aimag.v22i4.1597

Issue

Section

Articles