Advertisement

Machine Learning

, Volume 18, Issue 1, pp 81–108 | Cite as

Inferring finite automata with stochastic output functions and an application to map learning

  • Thomas Dean
  • Dana Angluin
  • Kenneth Basye
  • Sean Engelson
  • Leslie Kaelbling
  • Evangelos Kokkevis
  • Oded Maron
Article

Abstract

It is often useful for a robot to construct a spatial representation of its environment from experiments and observations, in other words, to learn a map of its environment by exploration. In addition, robots, like people, make occasional errors in perceiving the spatial features of their environments. We formulate map learning as the problem of inferring from noisy observations the structure of a reduced deterministic finite automaton. We assume that the automaton to be learned has a distinguishing sequence. Observation noise is modeled by treating the observed output at each state as a random variable, where each visit to the state is an independent trial and the correct output is observed with probability exceeding 1/2. We assume no errors in the state transition function.

Using this framework, we provide an exploration algorithm to learn the correct structure of such an automaton with probability 1−δ, given as inputs δ, an upper boundm on the number of states, a distinguishing sequences, and a lower bound α>1/2 on the probability of observing the correct output at any state. The running time and the number of basic actions executed by the learning algorithm are bounded by a polynomial in δ−1,m, |s|, and (1/2−α)−1.

We discuss the assumption that a distinguishing sequence is given, and present a method of using a weaker assumption. We also present and discuss simulation results for the algorithm learning several automata derived from office environments.

Keywords

Automata inference noisy outputs distinguishing sequences map learning spatial representation 

References

  1. Angluin, D. (1978). On the complexity of minimum inference of regular sets.Information and Control 39:337–350.Google Scholar
  2. Angluin, D. (1987). Learning regular sets from queries and counterexamples.Information and Computation 75:87–106.Google Scholar
  3. Aslam, J.A., & Rivest, R.L. (1990). Inferring graphs from walks. InProceedings COLT-88.Google Scholar
  4. Bachrach, J.R. (1992). Connectionist modeling and control of finite state environments. Technical Report 92-6, University of Massachusetts at Amherst Department of Computer and Information Science.Google Scholar
  5. Basye, K., & Dean, T. (1989). Map learning with indistinguishable locations. InProceedings of the Fifth Workshop on Uncertainty in AI. 7–13.Google Scholar
  6. Basye, K., Dean, T., & Vitter, J.S. (1989). Coping with uncertainty in map learning. InProceedings IJCAI 11. IJCAII, 663–668.Google Scholar
  7. Basye, K., Dean, T., & Kaelbling, L. (to appear). Learning dynamics: System identification for perceptually challenged agents.Artificial Intelligence.Google Scholar
  8. Basye, K. (1992). A framework for map construction. Technical report, Brown University Department of Computer Science, Providence, RI.Google Scholar
  9. Dean, T., Basye, K., Chekaluk, R., Hyun, S., Lejter, M., & Randazza, M. (1990). Coping with uncertainty in a control system for navigation and exploration. InProceedings AAAI-90. AAAI. 1010–1015.Google Scholar
  10. Donald, B., & Jennings, J. (1991). Sensor interpretation and task-directed planning using perceptual equivalence classes. Technical Report CU-CS-TR, Cornell University Computer Science Department.Google Scholar
  11. Dudek, G., Jenkins, M., Milios, E., & Wilkes, D. (1988). Robotic exploration as graph construction. Technical Report RBCV-TR-88-23, University of Toronto.Google Scholar
  12. Gold, E.M. (1972). System identification via state characterization.Automatica 8:621–636.Google Scholar
  13. Gold, E.M. (1978). Complexity of automation identification from given sets.Information and Control 37:302–320.Google Scholar
  14. Goodwin, G.C., & Sin, K.S. (1984).Adaptive Filtering Prediction and Control. Prentice-Hall, Englewood Cliffs, New Jersey.Google Scholar
  15. Kaelbling, L., Basye, K., Dean, T., Kokkevis, E., & Maron, O. (1992). Robot map-learning as learning labeled graphs from noisy data. Technical Report CS-92-15, Brown University Department of Computer Science.Google Scholar
  16. Kearns, M., & Valiant, L.G. (1989). Cryptographic limitations on learning boolean functions and finite automata. InProceedings of the Twenty First Annual ACM Symposium on Theoretical Computing. 433–444.Google Scholar
  17. Kuipers, B.J., & Byun, Y.-T. (1988). A robust, qualitative method for robot spatial reasoning. InProceedings AAAI-88. AAAI. 774–779.Google Scholar
  18. Kuipers, B. (1978). Modeling spatial knowledge.Cognitive Science 2:129–153.Google Scholar
  19. Levinson, S.E., Rabiner, L.R., & Sondhi, M.M. (1983). An introduction to the application of the theory of probabilistic functions of a Markov process to automatic speech recognition.The Bell System Technical Journal 62(4):1035–1074.Google Scholar
  20. Levitt, T.S., Lawton, D.T., Chelberg, D.M., & Nelson, P.C. (1987). Qualitative landmark-based path planning and following. InProceedings AAAI-87. AAAI. 689–694.Google Scholar
  21. Moore, E.F. (1956). Gedanken-experiments on sequential machines. InAutomata Studies. Princeton University Press, Princeton, New Jersey. 129–153.Google Scholar
  22. Pitt, L., & Warmuth, M.K. (1989). The minimum consistent DFA problem cannot be approximated within any polynomial. InProceedings of the Twenty First Annual ACM Symposium on Theoretical Computing. 421–432.Google Scholar
  23. Rimey, R.D., & Brown, C.M. (1991). Controlling eye movements with hidden Markov models.International Journal of Computer Vision 7(1):47–65.Google Scholar
  24. Rivest, R.L., & Schapire, R.E. (1987). Diversity-based inference of finite automata. InProceedings of the Twenty Eighth Annual Symposium on Foundations of Computer Science. 78–87.Google Scholar
  25. Rivest, R.L., & Schapire, R.E. (1989). Inference of finite automata using homing sequences. InProceedings of the Twenty First Annual ACM Symposium on Theoretical Computing. 411–420.Google Scholar
  26. Rudich, S. (1985). Inferring the structure of a Markov chain from its output. InProceedings of the Twenty Sixth Annual Symposium on Foundations of Computer Science. 321–326.Google Scholar
  27. Schapire, R.E. (1991). The design and analysis of efficient learning algorithms. Technical Report MIT/LCS/TR-493, MIT Laboratory for Computer Science.Google Scholar
  28. Tzeng, W.-G. (1992). Learning probabilistic automata and Markov chains via queries.Machine Learning 8:151–166.Google Scholar
  29. Valiant, L.G. (1984). A theory of the learnable.Communications of the ACM 27:1134–1142.Google Scholar
  30. Whitehead, S.D., & Ballard, D.H. (1991). Learning to perceive and act by trial and error.Machine Learning 7.Google Scholar
  31. Widrow, B., & Stearns, S.D. (1985).Adaptive Signal Processing. Prentice-Hall, Englewood Cliffs, N.J.Google Scholar
  32. Yannakakis, M., & Lee, D. (1991). Testing finite state machines. InACM Symposium on Theoretical Computing. ACM Press. 476–485.Google Scholar

Copyright information

© Kluwer Academic Publishers 1995

Authors and Affiliations

  • Thomas Dean
    • 1
  • Dana Angluin
    • 2
  • Kenneth Basye
    • 1
  • Sean Engelson
    • 2
  • Leslie Kaelbling
    • 1
  • Evangelos Kokkevis
    • 1
  • Oded Maron
    • 1
  1. 1.Department of Computer ScienceBrown UniversityProvidence
  2. 2.Department of Computer ScienceYale UniversityNew Haven

Personalised recommendations