An Analysis of the Genetic Evolution of a Ball-Beam Robotic Controller Based on a Three Dimensional Look up Table Chromosome

  • Mark Beckerleg
  • John Collins
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 170)


This chapter describes how a robotic controller based on a 3-dimensional lookup table was used to control a ball balancing beam system. The evolved motion of the beam and the corresponding chromosome is analysed. The 3 system states of the ball and beam were translated by the lookup table into a motor speed and direction which maintained the ball in balance. The ball-beam states included the ball position, ball speed, and beam position. The reproduction method used 2-point crossover with a mutation rate of 2 percent. The selection method was tournament, and the population size was 100 individuals. Successful evolution was achieved on 4 lookup tables, each containing different maximum motor speeds. Each evolved lookup table was able to maintain the ball in balance for more than 5 minutes.


Artificial intelligence Ball balancing beam Ball-beam Evolvable robotics Evolution Evolving lookup tables Genetic algorithms Lookup table-based controllers Metaheuristic optimization Robotics 


  1. 1.
    Beckerleg, M, Collins J (2011) Evolving a three dimensional lookup table controller for a curved ball and beam system, lecture notes in engineering and computer science: proceedings of The World Congress on Engineering and Computer Science 2011, WCECS 2011, San Francisco, 19–21 Oct 2011, pp 360–366Google Scholar
  2. 2.
    Ka C, Nan L (1987) A ball balancing demonstration of optimal and disturbance-accomodating control. Control Syst Mag IEEE 7(1):54–57CrossRefGoogle Scholar
  3. 3.
    Gordillo, F et al (2002) On the ball and beam problem: regulation with guaranteed transient performance and tracking periodic orbits, in proceedings of the international symposium on mathematical theory of networks and systems University of Notre DameGoogle Scholar
  4. 4.
    Dadios EP et al (2000) Vision guided ball-beam balancing system using fuzzy logic. In: Industrial Electronics Society, IECON. 26th Annual Confjerence of the IEEEGoogle Scholar
  5. 5.
    Iqbal J et al (2005) Implementing ball balancing beam using digital image processing and fuzzy logic. In: Electrical and computer engineering, Canadian conferenceGoogle Scholar
  6. 6.
    Ng, KC, Trivedi MM (1996) Neural integrated fuzzy controller (NiF-T) and real-time implementation of a ball balancing beam (BBB). In: Proceedings IEEE international conference on Robotics and automation. Google Scholar
  7. 7.
    Eaton PH, Prokhorov DV, Wunsch DC II (2000) Neurocontroller alternatives for fuzzy ball-and-beam systems with nonuniform nonlinear friction. Neural Netw IEEE Trans 11(2):423–435CrossRefGoogle Scholar
  8. 8.
    Tettamanzi, AGB (1995) An evolutionary algorithm for fuzzy controller synthesis and optimization. In: IEEE international conference on systems, man and cybernetics, intelligent systems for the 21st century.Google Scholar
  9. 9.
    Hoe Sung (2001) A self-organized fuzzy controller for wheeled mobile robot using an evolutionary algorithm. Ind Electron IEEE Trans 48(2):467–474CrossRefGoogle Scholar
  10. 10.
    Bianco R, Nolfi S (2003) Evolving the neural controller for a robotic arm able to grasp objects on the basis of tactile sensors, 2829 edn. Lecture notes in computer science 375–384Google Scholar
  11. 11.
    Kim K-J, Cho S-B (2001) Dynamic selection of evolved neural controllers for higher behaviors of mobile robot. In: Proceedings 2001 IEEE international symposium on computational intelligence in robotics and automation, 2001. Google Scholar
  12. 12.
    Yi Z, Xiuxia Y (2004) Design for beam-balanced system controller based on chaos genetic algorithm. In: Information acquisition: proceedings, international conferenceGoogle Scholar
  13. 13.
    Pedersen, GKM, Butz MV (2010) Evolving robust controller parameters using covariance matrix adaptation: proceedings of the 12th annual conference on genetic and evolutionary computation, ACM, Portland, pp 1251–1258Google Scholar
  14. 14.
    Lund HH, Hallam J (1997) Evolving sufficient robot controllers. In: Evolutionary computation, IEEE international conferenceGoogle Scholar
  15. 15.
    Lund HH (2001) Co-evolving control and morphology with LEGO robots. In: Proceedings of workshop on morpho-functional machinesGoogle Scholar
  16. 16.
    Chavoya A, Duthen Y (2006) Using a genetic algorithm to evolve cellular automata for 2D/3D computational development. In: Proceedings of the 8th annual conference on genetic and evolutionary computation, ACM, Seattle, pp 231–232Google Scholar
  17. 17.
    Greenfield G (2008) Evolved look-up tables for simulated DNA controlled robots. In: Proceedings of the 7th international conference on simulated evolution and learning, Springer-Verlag, Melbourne, pp 51–60Google Scholar
  18. 18.
    Z, RY et al (2002) Evolving FPGA-based robot controllers using an evolutionary algorithm, in first international conference on artificial immune systemsGoogle Scholar
  19. 19.
    Beckerleg M, Collins J (2007) An analysis of the chromosome generated by a genetic algorithm used to create a controller for a mobile inverted pendulum. Studies in computational intelligence. 76Google Scholar
  20. 20.
    Currie J, Beckerleg M, Collins J (2008) Software evolution of a hexapod robot walking gait. In: 15th international conference on Mechatronics and machine vision in practice, M2VIP 2008. Google Scholar
  21. 21.
    Beckerleg M, Collins J (2008) Evolving electronic circuits for robotic control. In: 15th international conference on mechatronics and machine vision in practice. Auckland, New ZealandGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2013

Authors and Affiliations

  1. 1.School of EngineeringAUT University, New Zealand. AUT City CampusAucklandNZ

Personalised recommendations