Advertisement

Self-Adapting Neural Networks for Mobile Robots

  • Ralf Salomon
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 109)

Summary

In the context of research on intelligence, autonomous agents and in particular mobile robots are to behave on their own without any human control. Unfortunately, the real world exhibits plenty of noise, uncertainties, sudden changes, etc, which all imposes significant challenges on the design of appropriate control architectures. This chapter starts off with an existing controller, known as the distributed adaptive control architecture and shows how significant improvements can be achieved by incorporating biological mechanisms, such as proprioception. The resulting controller requires much less preprogrammed design knowledge, exhibits more flexible adaptation capabilities, and is more fault tolerant with respect to environmental changes and sensor failures as its predecessors.

Keywords

Mobile Robot Learning Rule Autonomous Agent Collision Detector Sensor Reading 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Back, T., Schwefel, H.-P.: An Overview of Evolutionary Algorithms for Parameter Optimization. Evolutionary Computation 1 (1993) 1–23CrossRefGoogle Scholar
  2. 2.
    Brooks, R.: A robust layered control system for a mobile robot. IEEE Journal of Robotics and Automation 2 (1986) 14–23MathSciNetCrossRefGoogle Scholar
  3. 3.
    Brooks, R.: Elephants Don’t Play Chess. Robotics and Autonomous Systems 6 (1990) 3–15.CrossRefGoogle Scholar
  4. 4.
    Brooks, R.: Intelligence Without Reason. In: Mylopoulos, J., Reiter, R. (eds.): Proceedings of the 12th International Conference on Artificial Intelligence (IJCAI-91). Morgan Kaufmann, San Mateo, CA (1991) 569–595Google Scholar
  5. 5.
    Brooks, R.: Intelligence without representation. Artificial Intelligence 47 (1991) 139–159CrossRefGoogle Scholar
  6. 6.
    Clancey, W.: The Frame of Reference Problem in the Design of Intelligent Machines. In: Lehn (ed.), Architectures for Intelligence. The 22nd Carnegie Mellon Symposium on Cognition. Erlbaum, Hillsdale, NJ (1991) 357–423Google Scholar
  7. 7.
    Cliff, D., Husbands, P., Harvey, I.: Evolving Visually Guided Robots. In: Meyer, J.-A., Roitblat, H.L., Wilson, S.W. (eds.) From Animals to Animats 2: Proceedings of the Second International Conference on Simulation of Adaptive Behavior. MIT Press, Cambridge, MA (1992) 374–383Google Scholar
  8. 8.
    Etzioni, O., Weld, D.: A Softbot-Based Interface to the Internet. Communications of the ACM 37: 7 (1994) 72–76CrossRefGoogle Scholar
  9. 9.
    Floreano, D., Mondada, F.: Evolution of Homing Navigation in a Real Mobile Robot. IEEE Transactions on Systems, Man, and Cybernetics–Part B, 26: 3 (1996) 396–407CrossRefGoogle Scholar
  10. 10.
    Floreano, D., Mondada, F.: Evolution of Plastic Neurocontrollers for Situated Agents. In: Maes, P., Mataric, M., Meyer, J.-A., Pollack, J., Wilson, S.W. (eds.): From Animals to Animats 4: Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior. MIT Press, Cambridge, MA (1996) 402–410Google Scholar
  11. 11.
    Goldberg, D.E.: Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley Publishing Company (1989)Google Scholar
  12. 12.
    Harvey, I., Husbands, P., Cliff, D., Thompson, A., Jakobi, N.: Evolutionary Robotics: the Sussex Approach. Robotics and Autonomous Systems, Special Issues on “Practice and Future of Autonomous Agents ” 20:2–4 (1997) 205–224Google Scholar
  13. 13.
    Kandel, E., Schwartz, J., Jessel, T.: Essentials of Neural Science and Behavior. Appleton and Lange, Norwalk, CU (1995)Google Scholar
  14. 14.
    Khepera Users Manual Laboratoire de microinformatique, Swiss Federal Institute of Technology (EPFL), 1015 Lausanne, SwitzerlandGoogle Scholar
  15. 15.
    Kohonen, T.: Self-Organization and Associative Memor. Springer-Verlag, Berlin, Germany (1989)Google Scholar
  16. 16.
    Lambrinos, D.: Navigating with an Adaptive Light Compass. In: Moran, F., Moreno, A., Merelo J.J., Chacon, P. (eds.): Proceedings of the Third European Conference in Artificial Life ECAL’95. Springer-Verlag, Berlin, Germany (1995) 602–613Google Scholar
  17. 17.
    Lambrinos, D., Scheier, C.: Building Complete Autonomous Agents: A Case Study on Categorization. In: Proceedings of the IEEE International Conference on Intelligent Robots and Systems IROS’96. IEEE Press (1996) 170–177Google Scholar
  18. 18.
    Maes, P.: Agents that Reduce Work and Information Overload. Communications of the ACM 37: 7 (1994) 31–40CrossRefGoogle Scholar
  19. 19.
    Maris, M. te. Boekhorst, R.: Exploiting Physical Constraints: Heap Formation through Behavioral Error in a Group of Robots. In: Proceedings of the IEEE International Conference on Intelligent Robots and Systems IROS’96. IEEE Press (1996) pp. 1655–1660Google Scholar
  20. 20.
    Newell, A., Simon, H.A.: Physical symbol systems. Cognitive Science 4 (1976) 135–183CrossRefGoogle Scholar
  21. 21.
    Nolfi, S., Parisi, D.: Learning to Adapt to Changing Environments in Evolving Neural Networks. Adaptive Behavior. 5: 3 (1997) 343–363CrossRefGoogle Scholar
  22. 22.
    Pfeifer, R.: Building “Fungus Eaters”: design principles of autonomous agents. In: Maes, P., Mataric, M., Meyer, J.-A., Pollack, J., Wilson, S.W.: (eds): From Animals to Animats 4: Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior. MIT Press, Cambridge, MA (1996) 3–12Google Scholar
  23. 23.
    Pfeifer, R., Scheier, C.: Sensory-Motor Coordination: the Metapher and beyond. Robotics and Autonomous Systems, Special Issue on “Practice and Future of Autonomous Agents.” 20: 2–4. (1997)Google Scholar
  24. 24.
    Pfeifer, R., Scheier, C.: Understanding Intelligence. MIT Press, Cambridge, MA (1999)Google Scholar
  25. 25.
    Pfeifer, R., Verschure, P.: Distributed Adaptive Control: A Paradigm for Designing Autonomous Agents. In: Varela, F., Bourgine, P. (eds.): Proceedings of the First European Conference on Artificial Life. MIT Press, Cambridge, MA (1992) 21–30Google Scholar
  26. 26.
    Rechenberg, I.: Evolutionsstrategie. Frommann-Holzboog, Stuttgart, Germany (1973)Google Scholar
  27. 27.
    Salomon, R.: Neural Networks in the Context of Autonomous Agents: Important Concepts Revisited. In: Dagli, C.H., Akay, M., Chen, C.L.P., Fernandez, B.R., Ghosh, J. (eds.): Proceedings of the Artificial Neural Networks in Engineering (ANNIE’96). ASME Press, New York, NY (1996) 109–116Google Scholar
  28. 28.
    Salomon, R.: Increasing Adaptivity through Evolution Strategies. In: Maes, P., Mataric, M., Meyer, J.-A., Pollack, J., Wilson, S.W. (eds.): From Animals to Animats 4: Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior. MIT Press, Cambridge, MA (1996) 411–420Google Scholar
  29. 29.
    Schwefel, H.-P.: Evolution and Optimum Seeking. John Wiley and Sons, Inc, New York, NY (1995)Google Scholar
  30. 30.
    Simon, H.A.: The Science of the Artificial, 2nd edn. The MIT Press, Cambridge, MA (1976)Google Scholar
  31. 31.
    Verschure, P., Kröse, B., and Pfeifer, R.: Distributed Adaptive Control: The Self-Organization of Behavior. Robotics and Autonomous Systems 9 (1992) 181–196CrossRefGoogle Scholar
  32. 32.
    Wooldridge, M.J., Jennings, N.R.,: Intelligent Agents: Theory and Practice. The Knowledge Engineering Review 10: 2 (1995) 115–152CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Ralf Salomon
    • 1
  1. 1.AI Lab, Department of Information TechnologyUniversity of ZurichZurichSwitzerland

Personalised recommendations