Advertisement

A Non-computationally-intensive Neurocontroller for Autonomous Mobile Robot Navigation

  • Andrés Pérez-Uribe
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 109)

Summary

This chapter presents a neurocontroller architecture for autonomous mobile robot navigation. The main characteristic of such neurocontroller is that it is non-computationally-intensive. It provides a learning robot with the capability to autonomously categorize input data from the environment, to deal with the stability-plasticity dilemma, and to learn a state-to-action mapping that enables it to navigate in a workspace while avoiding obstacles. The neurocontroller architecture is composed of three main modules: an adaptive categorization module, implemented by an unsupervised learning neural architecture called FAST (Flexible Adaptable-Size Topology), a reinforcement learning module (SARSA), and a short-term memory or a planning module, intended to accelerate the learning of behaviors. We describe the use of our neurocontroller in three navigation tasks, each involving a different kind of sensor: 1) obstacle avoidance using infra-red proximity sensors, 2) foraging using a color CCD camera, and 3) wall-following using a grey-level linear vision system.

Keywords

Mobile Robot Obstacle Avoidance Swiss Federal Institute Adaptive Resonance Theory Blue Flower 
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.
    A. E. Alpaydin, Neural Models of Incremental Supervised and Unsupervised Learning, Swiss Federal Institute of Technology-Lausanne, Lausanne, EPFL,Thesis 863(1990)Google Scholar
  2. 2.
    R.C. Arkin, Reactive Robotic Systems, Handbook of Brain Theory and Neural Networks,MIT Press, 1995, M.A. Arbib, 793–796Google Scholar
  3. 3.
    R.C. Arkin,Behavior-Based Robotics, The MIT Press, 1998, Cambridge, MAGoogle Scholar
  4. 4.
    A.G. Barto and R.S. Sutton and C.W. Anderson, Neuronlike Adaptive Elements That Can Solve Difficult Learning Control Problems, IEEE Transactions on Systems, Man and Cybernetics 13 (5) 834–846 (1983)CrossRefGoogle Scholar
  5. 5.
    R.A. Brooks, Intelligence Without Reason Massachusetts Institute of Technology 1991 A.I. Memo 1293Google Scholar
  6. 6.
    J. Bruske and I. Ahrns and G. Sommer, An integrated architecture for learning of reactive behaviors based on dynamic cell structures, Robotic and Autonomous Systems, 1997, 22, 87–101CrossRefGoogle Scholar
  7. 7.
    M. Dorigo, Editorial Introduction to the Special Issue on Learning Autonomous Robots, “IEEE Transactions on Systems, Man and Cybernetics” 1996 June 361364Google Scholar
  8. 8.
    D. Floreano Reducing Human Design and Increasing Adaptability in Evolutionary Robotics Evolutionary Robotics, T. Gomi (ed) AAI Books, 1997Google Scholar
  9. 9.
    B. Fritzke Unsupervised ontogenic networks E. Fiesler and R. Beale (eds) Handbook of Neural Computation Institute of Physics Publishing and Oxford University Press 1997 C2.4:1—C2. 4: 16Google Scholar
  10. 10.
    S. Grossberg Adaptive pattern classification and universal recoding: I. Parallel development and coding of neural feature detectors Biological Cybernetics 1976 21 117–158Google Scholar
  11. 11.
    S. Grossberg, Adaptive pattern classification and universal recoding: II. Parallel development and coding of neural feature detectors, Biological Cybernetics 1976 23 187–202MathSciNetMATHCrossRefGoogle Scholar
  12. 12.
    M.I. Jordan and S. Russell Computational Intelligence R.A. Wilson and F. Keil (eds) The MIT Encyclopedia of the Cognitive Sciences, The MIT Press 1999 lxxiii—xcGoogle Scholar
  13. 13.
    K-team Khepera User Manual K-Team SA, Lausanne, Switzerland, Version 4. 06 November 1995Google Scholar
  14. 14.
    Khepera K2D Video Turret User Manual K-Team SA Lausanne, Switzerland Version 1. 1 December 1995Google Scholar
  15. 15.
    K-team Khepera K213 Vision Turret User Manual K-Team SA Lausanne, Switzerland Version 1. 0 November 1995Google Scholar
  16. 16.
    B.J.A. Kröse and J.W.M van Dam Adaptive state space quantization for reinforcement learning collision-free navigation“ Proceedings of the 1992 IEEE/RSJ International Conference on Intelligent Robots and Systems” 1327–1332 1992Google Scholar
  17. 17.
    L. Kuvayev and R. Sutton Approximation in Model-Based Learning Proceedings of the ICML’97 Workshop on Modelling in Reinforcement Learning 1997 Vanderbilt UniversityGoogle Scholar
  18. 18.
    J.L. Lin and T.M. Mitchell“Reinforcement learning with hidden states”From Animals to Animats: Proceedings of the Second International Conference on Simulation of Adaptive Behavior (SAB92)“ ”J-A. Meyer and H.L. Roitblat and S.W. Wilson“ 281–290 1992Google Scholar
  19. 19.
    S. Mahadevan and J. Connell Automatic Programming of Behavior-based Robots using Reinforcement Learning Artificial Intelligence 1992 55 (2–3) 311365Google Scholar
  20. 20.
    D. McFarland 23. The com plex behaviour of honey-bees Animal Behaviour Addison Wesley Longman 1999 Harlow, England 421–433Google Scholar
  21. 21.
    J.R. Milian Rapid, Safe, and Incremental Learning of Navigation Strategies IEEE Transactions on Systems, Man and Cybernetics (Part B) 26 (3) 408–420 1996CrossRefGoogle Scholar
  22. 22.
    F. Mondada and E. Franzi and P. Ienne Mobile robot miniaturization: A tool for investigating in control algorithms Proceedings of the Third International Symposium on Experimental Robotics 1993 Kyoto, JapanGoogle Scholar
  23. 23.
    P.R. Montague and P. Dayan and C. Person and T.J. Sejnowski Bee Foraging in uncertain environments using predictive hebbian learning Nature 1995 377 725–728Google Scholar
  24. 24.
    A. Pérez-U and E. Sanchez The FAST Architecture: A Neural Network with Flexible Adaptable-Size Topology Proceedings of the Fourth International Conference on Microelectronics for Neural Networks and Fuzzy Systems Microneuro’96 IEEE 1996 Lausanne, Switzerland 337–340Google Scholar
  25. 25.
    A. Pérez-Uribe and E. Sanchez A Comparison of Reinforcement Learning with Eligibility Traces and Integrated Learning, Planning, and Reacting Computatio nal Intelligence for Modeling, Control and Automation 54 M. Mohammadian IOS Press Amsterdam 154–159 1999Google Scholar
  26. 26.
    A. Pérez-Uribe Structure-Adaptable Digital Neural Networks 4. Adaptive Categorization: from Biology to Hardware Swiss Federal Institute of Technology-Lausanne, Ph.D Thesis 2052 1999 33–62Google Scholar
  27. 27.
    A. Pérez-Uribe Structure-Adaptable Digital Neural Networks 6. A Neuro-controller Architecture for Autonomous Robots Swiss Federal Institute of Technology-Lausanne, Ph.D Thesis 2052 1999 95–116Google Scholar
  28. 28.
    Andrés Pérez-Uribe Structure-Adaptable Digital Neural Networks Swiss Federal Institute of Technology-Lausanne Thesis 2052 1999Google Scholar
  29. 29.
    L.A. Real Animal Choice Behavior and the Evolution of Cognitive Architecture Science 1991 253 980–986Google Scholar
  30. 30.
    G. Rummery and M. Niranjan On-line q-learning using connectionist systems Cambridge University Engineering Department 1994 CUED/F-INFENG/TR 166Google Scholar
  31. 31.
    E. Sanchez and M. Sipper and J.-O. Haenni and J.-L. Beuchat and A. Stauffer and A. Pérez-Uribe Static and Dynamic Configurable Systems IEEE Transactions on Computers 1999 48 (6) 556–564Google Scholar
  32. 32.
    S. Schaal and C.G. Atkeson Constructive Incremental Learning From Only Local Information Neural Computation 10 (8) 2047–2084 1998Google Scholar
  33. 33.
    C. Scheier Incremental Category Learning in a Real World Artifact Using Growing Dynamic Cell Structures Proceedings of the 4th European Symposium on Artificial Neural Networks ESANN’96 M. Verleysen (ed)1996 117–122Google Scholar
  34. 34.
    W. Schultz and P. Dayan and P. Read Montague A Neural Substrate of Prediction and Reward Science 275 (14 March) 1593–1599 1997Google Scholar
  35. 35.
    R.S. Sutton Learning to predict by the methods of Temporal Differences Machine Learning 3 9–44 1988Google Scholar
  36. 36.
    R.S. Sutton Integrated architectures for Learning, Planning, and Reacting based on approximating Dynamic Programming Proceedings of the Seventh International Conference on Machine Learning 216–224 Morgan Kaufmann 1990Google Scholar
  37. 37.
    R.S. Sutton and A.G. Barto Reinforcement Learning: An Introduction The MIT Press 1998Google Scholar
  38. 38.
    J. Tani Model-Based Learning for Mobile Robot Navigation from the Dynamical Systems Perspective IEEE Transactions on Systems, Man and Cybernetics (Part B) 26 (3) 421–436 1996Google Scholar
  39. 39.
    D.S. Touretsky and L.M. Saksida Operant Conditioning in Skinnerbots Adaptive Behavior 5 34–1997Google Scholar
  40. 40.
    C.J.C.H. Watkins and P. Dayan Q-Learning Machine Learning 8 279–292 1992Google Scholar
  41. 41.
    A. Watson Why Can’t a Computer Be More Like a Brain ? Science 277 (5334) 1934–1936 1997Google Scholar
  42. 42.
    S.D. Whitehead and D.H. Ballard Learning to Perceive and Act by Trial Machine Learning 7 (1) 45–83 1991Google Scholar
  43. 43.
    S. Zrehen Elements of Brain Design for Autonomous Agents Swiss Federal Institute of Technology-Lausanne Thesis 1373 Lausanne, EPFL 1995Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Andrés Pérez-Uribe
    • 1
  1. 1.Parallelism and Artificial Intelligence Group (PAI), Department of InformaticsUniversity of FribourgSwitzerland

Personalised recommendations