OPTIMISING A FLYING ROBOT - Controller Optimisation using a Genetic Algorithm on a Real-World Robot

Benjamin N. Passow, Mario Gongora

Abstract

This work presents the optimisation of the heading controller of a small flying robot. A genetic algorithm (GA) has been used to tune the proportional, integral, and derivative (PID) parameters of the helicopter’s controller. Instead of evaluating each individual’s fitness in an artificial simulation, the actual flying robot has been used. The performance of a hand-tuned PID controller is compared to the GA-tuned controller. Tests on the helicopter confirm that the GA’s solutions result in a better controller performance. Further more, results suggest that evaluating the GA’s individuals on the real flying robot increases the controller’s robustness.

References

  1. Bagnell, J. and Schneider, J. (2001). Autonomous helicopter control using reinforcement learning policy search methods. volume 2.
  2. Bouabdallah, S., Becker, M., and Siegwart, R. (2007). Autonomous miniature flying robots: coming soon!- research, development, and results. Robotics & Automation Magazine, IEEE, 14(3):88-98.
  3. Coyle, S. (1996). The art and science of flying helicopters. Arnold, Hodder Headline Group.
  4. De Moura Oliveira, P. (2005). Modern heuristics review for pid control systems optimization: A teaching experiment. In Proceedings of the 5th International Conference on Control and Automation, pages 828-833.
  5. Fleming, P. and Purshouse, R. (2002). Evolutionary algorithms in control systems engineering: a survey. Control Engineering Practice, 10(11):1223-1241.
  6. Haupt, R. and Haupt, S. (2004). Practical Genetic Algorithms. Wiley-Interscience.
  7. Holland, J. H. (1975). Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control and Artificial Intelligence. University of Michigan Press.
  8. Ludington, B., Johnson, E., and Vachtsevanos, G. (2006). Augmenting uav autonomy. Robotics & Automation Magazine, IEEE, 13(3):63-71.
  9. Mamdani, E. H. (1974). Application of fuzzy algorithms for simple dynamic plant. IEE Proceedings on Control Theory and Applications, 121:1585 - 1588.
  10. Perhinschi, M. (1997). A modified genetic algorithm for the design of autonomous helicopter control system. In Proceedings of the AIAA Guidance, Navigation and Control Conference, pages 1111-1120.
  11. Puntunan, S. and Parnichkun, M. (2002). Control of heading direction and floating height of a flying robot. In Industrial Technology, 2002. IEEE ICIT'02. 2002 IEEE International Conference on, volume 2, pages 690-693, Bangkok, Thailand.
  12. Sanchez, E., Becerra, H., and Velez, C. (2005). Combining fuzzy and pid control for an unmanned helicopter. In Annual Meeting of the North American Fuzzy Information Processing Society, pages 235-240, Unidad Guadalajara, Mexico.
  13. Shim, H., Koo, T., Hoffmann, F., and Sastry, S. (1998). A comprehensive study of control design for an autonomous helicopter. In Decision and Control, 1998. Proceedings of the 37th IEEE Conference on, volume 4, pages 3653-3658, Tampa, Florida, USA.
  14. Skogestad, S. and Postlethwaite, I. (1996). Multivariable Feedback Control: Analysis and Design. Wiley.
  15. Smith, C. (1979). Fundamentals of Control Theory, volume 86. Chemical Engineering.
Download


Paper Citation


in Harvard Style

N. Passow B. and Gongora M. (2008). OPTIMISING A FLYING ROBOT - Controller Optimisation using a Genetic Algorithm on a Real-World Robot . In Proceedings of the Fifth International Conference on Informatics in Control, Automation and Robotics - Volume 4: ICINCO, ISBN 978-989-8111-31-9, pages 151-156. DOI: 10.5220/0001496901510156


in Bibtex Style

@conference{icinco08,
author={Benjamin N. Passow and Mario Gongora},
title={OPTIMISING A FLYING ROBOT - Controller Optimisation using a Genetic Algorithm on a Real-World Robot},
booktitle={Proceedings of the Fifth International Conference on Informatics in Control, Automation and Robotics - Volume 4: ICINCO,},
year={2008},
pages={151-156},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001496901510156},
isbn={978-989-8111-31-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fifth International Conference on Informatics in Control, Automation and Robotics - Volume 4: ICINCO,
TI - OPTIMISING A FLYING ROBOT - Controller Optimisation using a Genetic Algorithm on a Real-World Robot
SN - 978-989-8111-31-9
AU - N. Passow B.
AU - Gongora M.
PY - 2008
SP - 151
EP - 156
DO - 10.5220/0001496901510156