Robustness analysis of evolutionary controller tuning using real systems

Authors:
Mario A. Gongora;Benjamin N. Passow;Adrian A. Hopgood
Affiliations:
Centre for Computational Intelligence, De Montfort University, Leicester, UK;Institute of Creative Technologies, De Montfort University, Leicester, UK;Faculty of Technology, De Montfort University, Leicester, UK
Venue:
CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Year:
2009

Citing 5
Cited 0

Noise and the Reality Gap: The Use of Simulation in Evolutionary Robotics

Proceedings of the Third European Conference on Advances in Artificial Life
Flying over the reality gap: From simulated to real indoor airships

Autonomous Robots
Learning for control from multiple demonstrations

Proceedings of the 25th international conference on Machine learning
Intelligence without reason

IJCAI'91 Proceedings of the 12th international joint conference on Artificial intelligence - Volume 1
A fuzzy gain-scheduler for the attitude control of an unmanned helicopter

IEEE Transactions on Fuzzy Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

A genetic algorithm (GA) presents an excellent method for controller parameter tuning. In our work, we evolved the heading as well as the altitude controller for a small lightweight helicopter. We use the real flying robot to evaluate the GA's individuals rather than an artificially consistent simulator. By doing so we avoid the "reality gap", taking the controller from the simulator to the real world. In this paper we analyze the evolutionary aspects of this technique and discuss the issues that need to be considered for it to perform well and result in robust controllers.