Co-evolving complex robot behavior

Authors:
Esben Hallundbæk Østergaard;Henrik Hautop Lund
Affiliations:
The Maersk McKinney Moller Institute for Production Technology, University of Southern Denmark, Odense M., Denmark;The Maersk McKinney Moller Institute for Production Technology, University of Southern Denmark, Odense M., Denmark
Venue:
ICES'03 Proceedings of the 5th international conference on Evolvable systems: from biology to hardware
Year:
2003

Citing 9
Cited 3

Issues in evolutionary robotics

Proceedings of the second international conference on From animals to animats 2 : simulation of adaptive behavior: simulation of adaptive behavior
Competitive co-evolutionary robotics: from theory to practice

Proceedings of the fifth international conference on simulation of adaptive behavior on From animals to animats 5
Tracking the Red Queen: Measurements of Adaptive Progress in Co-Evolutionary Simulations

Proceedings of the Third European Conference on Advances in Artificial Life
Running Across the Reality Gap: Octopod Locomotion Evolved in a Minimal Simulation

Proceedings of the First European Workshop on Evolutionary Robotics
Blurred Vision: Simulation-Reality Transfer of a Visually Guided Robot

Proceedings of the First European Workshop on Evolutionary Robotics
How Co-Evolution can Enhance the Adaptive Power of Artificial Evolution: Implications for Evolutionary Robotics

Proceedings of the First European Workshop on Evolutionary Robotics
Competitive Environments Evolve Better Solutions for Complex Tasks

Proceedings of the 5th International Conference on Genetic Algorithms
Coevolving Predator and Prey Robots: Do "Arms Races" Arise in Artificial Evolution?

Artificial Life
Evolving mobile robots in simulated and real environments

Artificial Life

Ideal Evaluation from Coevolution

Evolutionary Computation
Adaptive learning application of the MDB evolutionary cognitive architecture in physical agents

SAB'06 Proceedings of the 9th international conference on From Animals to Animats: simulation of Adaptive Behavior
Bootstrapping aggregate fitness selection with evolutionary multi-objective optimization

PPSN'12 Proceedings of the 12th international conference on Parallel Problem Solving from Nature - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

Reports on evolutionary robotics systems have so far been on evolving controllers that make simple robots do simple tasks in simple environments. In this paper we try to stress the evolutionary robotics approach by evolving a controller for a more complex task, namely Khepera robot soccer, and evaluate evolved controller performance against hand-coded controllers. We present a system that uses competitive coevolution to develop robot controllers for the task. The system is described, and performance of the system is documented. Co-evolution is tested against single-population evolution, and it is concluded that co-evolution has the ability to produce more robust individuals with respect to opponent strategies.