Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Selection for Wandering Behavior in a Small Robot

Selection for Wandering Behavior in a Small Robot We have evolved artificial neural networks to control the wandering behavior of small robots. The task and environment were very simple—to touch as many squares in a grid as possible during a fixed period of time. A number of the simulated robots were embodied in a small Lego™ robot, controlled by a Motorola™ 6811 processor; and their performance was compared to the simulations. We observed that: (a) evolution was an effective means to program the robot's behavior; (b) progress was characterized by sharply stepped periods of improvement, separated by periods of stasis that corresponded to levels of behavioral/computational complexity; and (c) the simulated and realized robots behaved quite similarly, the realized robots in some cases outperforming the simulated ones. Introducing random noise to the simulations improved the fit somewhat (from r = 0.73 to 0.79). Hybrid simulated/embodied selection regimes for evolutionary robots are discussed. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Artificial Life MIT Press

Selection for Wandering Behavior in a Small Robot

Loading next page...
 
/lp/mit-press/selection-for-wandering-behavior-in-a-small-robot-h5NNUXYjXW

References (24)

Publisher
MIT Press
Copyright
© 1995 Massachusetts Institute of Technology
Subject
Articles
ISSN
1064-5462
eISSN
1530-9185
DOI
10.1162/artl.1994.2.1.101
Publisher site
See Article on Publisher Site

Abstract

We have evolved artificial neural networks to control the wandering behavior of small robots. The task and environment were very simple—to touch as many squares in a grid as possible during a fixed period of time. A number of the simulated robots were embodied in a small Lego™ robot, controlled by a Motorola™ 6811 processor; and their performance was compared to the simulations. We observed that: (a) evolution was an effective means to program the robot's behavior; (b) progress was characterized by sharply stepped periods of improvement, separated by periods of stasis that corresponded to levels of behavioral/computational complexity; and (c) the simulated and realized robots behaved quite similarly, the realized robots in some cases outperforming the simulated ones. Introducing random noise to the simulations improved the fit somewhat (from r = 0.73 to 0.79). Hybrid simulated/embodied selection regimes for evolutionary robots are discussed.

Journal

Artificial LifeMIT Press

Published: Jan 1, 1994

Keywords: Artificial Life; robots; evolution; genetic algorithms; evolutionary robotics; mobile autonomous vehicles

There are no references for this article.