Evolving Controllers for Autonomous Agents Using Genetically Programmed Networks

  • Arlindo Silva
  • Ana Neves
  • Ernesto Costa
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1598)


This article presents a new approach to the evolution of controllers for autonomous agents. We propose the evolution of a connectionist structure where each node has an associated program, evolved using genetic programming. We call this structure a Genetically Programmed Network and use it to successfully evolve control systems with very different architectures, by making small restrictions to the evolutionary process. Experimental results of applying this method to evolve neural networks, distributed programs and rule-based systems capable of solving a common benchmark problem, the Ant Problem, are presented. Comparison with other known genetic programming based approaches, shows that our method requires less effort to find a solution.


Internal Node Autonomous Agent Recurrent Neural Network Correspondent Node External Node 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    P. Angeline, “Evolutionary Algorithms and Emergent Intelligence”, PhD Thesis, Ohio State University, 1993.Google Scholar
  2. 2.
    W. Banzhaf, P. Nordin, and M. Olmer, “Generating Adaptive Behavior for a Real Robot using Function Regression within Genetic Programming”, Genetic Programming 1997: Proceedings of the Second Annual Conference, pp. 35–43, Morgan Kaufmann, 13–16 July 1997.Google Scholar
  3. 3.
    R. Brooks, “Artificial Life and Real Robots”, Towards a Practice of Autonomous Systems: Proceedings of the First European Conference on Artificial Life, MIT Press, Cambridge, MA, 1992, pp. 3–10.Google Scholar
  4. 4.
    K. Chellapilla, “Evolutionary programming with tree mutations: Evolving computer programs without crossover”, Genetic Programming 1997: Proceedings of the Second Annual Conference, pages 431–438, Morgan Kaufmann, 13–16 July 1997.Google Scholar
  5. 5.
    D. Cliff, P. Husbands and I. Harvey, “Analysis of Evolved Sensory-Motor Controllers”, Cognitive Science Research Paper, Serial N° CSRP 264, 1992.Google Scholar
  6. 6.
    R. Collins and D. Jefferson, “Antfarm: toward simulated evolution”, Artificial Life II, Santa Fe Institute Studies in the Sciences of the Complexity, volume X, Addison-Wesley, 1991.Google Scholar
  7. 7.
    J. Donnart and J. Meyer, “A Hierarchical Classifier System Implementing a Motivationally Autonomous Animat”, Proceedings of the Third Int. Conf. on Simulation of Adaptive Behaviour, MIT Press/Bradford Books, pp. 144–153.Google Scholar
  8. 8.
    M. Dorigo and U. Schnepf, “Genetics-Based Machine Learning and Behaviour Based Robotics: A New Synthesis”, IEEE Transactions on Systems, Man, and Cybernetics, 23, 1, 141–154, January 1993.CrossRefGoogle Scholar
  9. 9.
    M. Dorigo and M. Colombetti, “Robot Shaping: Developing Autonomous Agents through Learning”, Technical Report TR-92-040, International Computer Science Institute, April 1993Google Scholar
  10. 10.
    D. Floreano and F. Mondada, “Automatic Creation of an Autonomous Agent: Genetic Evolution of a Neural-Network Driven Robot”, From Animals to Animats III, Proc. of the 3rd Int. Conf on Simulation of Adaptive Behaviour, MIT Press/Bradford Books, 1994.Google Scholar
  11. 11.
    J. Grefenstette and A. Schultz, “An Evolutionary Approach to Learning in Robots”, Proc. of the Machine Learning Workshop on Robot Learning, 11th International Conference on Machine Learning, July 10–13, 1994, New Brunswick, N.J., 65–72.Google Scholar
  12. 12.
    I. Harvey, P. Husbands and D. Cliff, “Issues in Evolutionary Robotics”, Proceedings of SAB92, the Second International Conference on Simulation of Adaptive Behaviour, MIT Press Bradford Books, Cambridge, MA, 1993.Google Scholar
  13. 13.
    M. Keith, “Genetic Programming in C++: Implementation Issues”, Advances in Genetic Programming, pp. 285–310, MIT Press, 1994.Google Scholar
  14. 14.
    J. Koza, “Genetic programming: On the programming of computers by means of natural selection”, Cambridge, MA, MIT Press, 1992.zbMATHGoogle Scholar
  15. 15.
    W. Langdon and R. Poli, “Why Ants are Hard”, Technical Report CSRP-98-04, The University of Birmingham, School of Computer Science, 1998.Google Scholar
  16. 16.
    W. Langdon, “Better Trained Ants”, Technical Report CSRP-98-08, The University of Birmingham, School of Computer Science, 1998.Google Scholar
  17. 17.
    S. Nolfi, D. Floreano et al, “How to Evolve Autonomous Robots: Different Approaches in Evolutionary Robotics”, Artificial Life IV, pp. 190–197, MIT Press/Bradford Books, 1994.Google Scholar
  18. 18.
    J. Pujol and R. Poli, “Efficient Evolution of Asymmetric Recurrent Neural Networks Using a PDGP-inspired Two-dimensional Representation”, Proceedings of EuroGP’98, First European Workshop on Genetic Programming, April 1998, Springer.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Arlindo Silva
    • 2
    • 1
  • Ana Neves
    • 2
    • 1
  • Ernesto Costa
    • 3
    • 1
  1. 1.Centro de Informática e Sistemas da Universidade de CoimbraCoimbraPortugal
  2. 2.Escola Superior de TecnologiaInstituto Politécnico de Castelo BrancoCastelo BrancoPortugal
  3. 3.Departamento de Engenharia InformáticaUniversidade de CoimbraCoimbraPortugal

Personalised recommendations