Knowledge-Based Position Estimation for a Multisensor House Robot

  • K. K. Ong
  • R. E. Seviora
  • P. Dasiewicz
Conference paper


This paper considers a knowledge-based approach to position estimation for mobile house or office robots. It deals with the robots which are, for cost reasons, equipped with inexpensive sensors only. These sensors have limited resolution and their readings are subject to distortion and errors. The approach presented exploits the stationary nature of major structural features and large objects (e.g. rooms, windows, beds) in the domain of movement of the robot. To reduce the real-time computational requirements, the knowledge of what each sensor would be expected to see is stored in a suitable representation in the robot database.

The paper presents a two blackboard architecture for the position estimator of the robot. During position estimation, specialist knowledge sources (sensor experts) interpret the readings from the sensors, generate position hypotheses and post them on the domain blackboard. Other knowledge sources control the scheduling of sensor experts and integration of their findings by using information recorded on the control blackboard.

A prototype position estimator has been implemented and evaluated on an experimental system consisting of a mobile robot with limited sensory capability (a Heath Hero-1 robot) controlled by a high performance personal computer (IBM PC/XT). The position estimation software has been implemented in GCLISP, a subset of Common LISP. The experimental testbed is described and initial position estimation results are discussed.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    H.P. Moravec, “Locomotion, Vision and Intelligence”, in M. Brady and R. Paul, eds., “Robotics Research: The First International Symposium”, MIT Press, Cambridge, Mass., 1984, pp. 215–224.Google Scholar
  2. [2]
    J.L. Crowley, “Navigation for Intelligent Mobile Robot”, IEEE Journal of Robotics and Automation, Vol. 1, No. 1, March 1985, pp.31–41.CrossRefMathSciNetGoogle Scholar
  3. [3]
    L.D. Erman et al., “The Hearsay-II Speech-Understanding System: Integrating Knowledge to Resolve Uncertainty”, ACM Computing Surveys, Vol. 12, No. 2, June 1980, pp. 213–253.CrossRefGoogle Scholar
  4. [4]
    R. Balzer et al., “Hearsay-III: A Domain-Independent Framework for Expert Systmes”, Proc. 1st National Conference on Artificial Intelligence, Aug. 1980, pp. 108–110.Google Scholar
  5. [5]
    H.P. Nii and E.A. Feigenbaum, “Rule-Based Understanding of Signals”, in D.A. Waterman and F. Hayes-Roth, eds., “Pattern-Directed Inference Systems”, Academic-Press, Orlando, Fla., 1978, pp. 483–501.Google Scholar
  6. [6]
    B. Hayes-Roth, “A Blackboard Architecture for Control”, Artificial Intelligence, Vol. 26, No. 3, July 1985, pp. 251–321.CrossRefGoogle Scholar
  7. [7]
    M.D. Rychener et al, “A Rule-Based Blackboard Kernel System: Some Principles in Design”, Proc. IEEE Workshop on Principles of Knowledge-Based Systems, Dec. 1984, pp. 59–64.Google Scholar
  8. [8]
    F. Hayes-Roth et al., eds., “Building Expert Systems”, Addison-Wesley Publishing Co., Reading, Mass, 1983, p. 146.Google Scholar
  9. [9]
    K.K. Ong, “LISP Implementation of Mobile Robot Controller”, MA.Sc. Project, Dept. El. Eng., University of Waterloo, 1985.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1986

Authors and Affiliations

  • K. K. Ong
    • 1
  • R. E. Seviora
    • 1
  • P. Dasiewicz
    • 1
  1. 1.Department of Electrical EngineeringUniversity of WaterlooWaterlooCanada

Personalised recommendations