Advertisement

An Experimental Autonomous Articulated Robot that can Learn

  • Ahmed S. Mohamed
  • William W. Armstrong
Conference paper

Abstract

An important feature of any intelligent autonomous robot is the capability of acquiring knowledge about its environment and learning from its previous experiences. Long response times for reasoning and decision-making have to be avoided. Consequently the process of knowledge acquisition as well as the type of internal knowledge representation have to be designed very carefully with respect to processing time and performance requirements. This paper proposes a multi-legged autonomous articulated robot that maintains nested hierarchical production rules capable of embodying learned knowledge and enabling control using a knowledge-based control system. The proposed robot merges methodologies taken from computer numerical control (mathematical methods in robotics, and biomechanics) with methodologies taken from motor learning (knowledge-based processing as studied in artificial intelligence and behavioural psychology). Both methodologies act together to provide a control system that functions somewhat like human procedures for perception, planning and motion execution. The robot’s actions and most internal operations of its acquisition, planning and decision making are monitored through a color graphics simulation.

Keywords

Motor Learning Computer Numerical Control Learning Controller Small Obstacle Numerical Controller 
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. Aho, J. Hoperaft, and J. Ullman, The Design and Analysis of Computer Algorithms, Addison-Wesley, Reading, Mass. 1974.Google Scholar
  2. [2]
    W. Armstrong,Recursive Solution to the Equations of Motion of an N-Link Manipulator,Proceedings Fifth World Congress on the Theory of Machines and Mechanisms American Soc. of Mech. Eng.,1979Google Scholar
  3. [3]
    W. Annstrong,M. Green,The Dynamics of Articulated Rigid Bodies for Purpose of Animation,Proceedings of Graphics Interface’85 ‚1985Google Scholar
  4. [4]
    W. Armstrong,M. Green,R. Lake Near-Real Time Control of Human Figures Models,Graphics Interface-86,1986Google Scholar
  5. [5]
    W. Armstrong,T. Marsland,M. Olafsson J. Schaeffer,Solving Equations of Motion On a Virtual Tree Machine,SIAM J. Sc. Stat. Comput., 8, 1987Google Scholar
  6. [6]
    J. Barhen,Hypercube Ensembles: An Architecture For Intelligent Robots•Computer Architecture For Robots and Automation J. Graham,1987Google Scholar
  7. [7]
    R. Brooks, A Robust Layered Control System for a Mobile Robot, IEEE Journal of Robotics and Automation, RA-2(1), April 1986.Google Scholar
  8. [8]
    R. Brooks, J. Connell, and A. Flynn, A Mobile Robot with Onboard Parallel Processor and Large Workspace Arm, AAAI-86, August 1986.Google Scholar
  9. [9]
    A. Bundy,B. Silver,D. Plammer,An Analytical Comparison of Some Rule-Learning Programs,Artificial Intelligence, 27, 1985Google Scholar
  10. [10]
    P. Cohen,E. Feigenbaum,The Handbook of Artificial Intelligence,HeirisTech Press, Stanford Calif.,1981Google Scholar
  11. [1.
    ]Remotely Manned Systems- Exploration and Operation in Space,Proceedings of the First National Conference,Pasadena, CA,E. Heer,California Inst. of Technology,1973Google Scholar
  12. ]H. Kasahara,S. Narita,Parallel Processing of a Robot Arm Control Computation on a Multiprocessor system, IEEE Jour. Rob. & Aut.,RA_1, number 2, 104, 1985Google Scholar
  13. [13]
    A. Mohamed,A Learning Apprentice System For Locomotion Control of Articulated Bodies,A Ph.D. thesis in preparation.,1988 208Google Scholar
  14. [14]
    ]R. Nigam,C. Lee,A Multiprocessor-Based Controller for the Control of Mechanical Manipulators, IEEE Jour. Rob. & Aut.,RA-1, number 4, 173, 1985Google Scholar
  15. [151D.
    Norman, Twelve Issues for Cognitive Science, Cognitive Science 4, (1980).Google Scholar
  16. ]R. Schmidt,H. Zelamik,B. Haukins J. Frank J. Quinn Motor Output Variability: A Theory for the Accuracy of Rapid Motor Acts Psychological Review 86, 1979Google Scholar
  17. [17]
    R. Smith,T. Mitchell ,R. Chestek ,B. Buchanon ,A Model for Learning Systems ,Proceeding 5th UCAI ,cambridge, MA ,1977Google Scholar
  18. [18]
    )D. Payton, An Architecture for Reflexive Autonomous Vehicle Control, IEEE Robotics and Automation Conference, San Francisco, April 1986.Google Scholar
  19. [19]
    Rich, Artificial Intelligence, McGraw-Hill, Reading, 1983.Google Scholar
  20. [20]
    J. Wilhelms ,B. Barsky ,Using Dynamic Analysis for the Animation of Articulated Bodies such as Human and Robots ,Proceedings of Graphics Interface’85 ,1985Google Scholar

Copyright information

© Springer-Verlag Berlin, Heidelberg 1989

Authors and Affiliations

  • Ahmed S. Mohamed
    • 1
  • William W. Armstrong
    • 1
  1. 1.Department of Computing ScienceThe University of AlbertaAlbertaCanada

Personalised recommendations