Advertisement

Line-Crawling Robot Navigation: A Rough Neurocomputing Approach

  • J. F. Peters
  • T. C. Ahn
  • M. Borkowski
  • V. Degtyaryov
  • S. Ramanna
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 116)

Abstract

This chapter considers a rough neurocomputing approach to the design of the classify layer of a Brooks architecture for a robot control system. This paradigm for neu­rocomputing that has its roots in rough set theory, works well in cases where there is uncer­tainty about the values of measurements used to make decisions. In the case of the line-crawling robot (LCR) described in this chapter, rough neurocomputing works very well in classifying noisy signals from sensors. The LCR is a robot designed to crawl along high-voltage transmission lines where noisy sensor signals are common because of the electro­magnetic field surrounding conductors. In rough neurocomputing, training a network of neurons is defined by algorithms for adjusting parameters in the approximation space of each neuron. Learning in a rough neural network is defined relative to local parameter ad­justments. Input to a sensor signal classifier is in the form of clusters extracted from con­vex hulls that “enclose” similar sensor signal values. This chapter gives a fairly complete description of a LCR that has been developed over the past three years as part of a Mani­toba Hydro research project. This robot is useful in solving maintenance problems in power systems. A description of the locomotion features of a line-crawling robot and the basic architecture of a rough neurocomputing system for robot navigation are given. A brief description of the fundamental features of rough set theory used in the design of a rough neural network is included in this chapter. A sample sensor signal classification ex­periment using a recent implementation of rough neural networks is also given.

Keywords

Mobile Robot Sensor Signal Obstacle Avoidance Decision Class Rough Measure 
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].
    M. Banerjee et al., Rough fuzzy MLP: Knowledge encoding and classification, IEEE Trans. on Neural Networks, vol. 9, no. 6, 1998, 1203–1215.CrossRefGoogle Scholar
  2. [2].
    B. Chakraborty, Feature subset selection by neuro-rough hybridization. In: W. Ziarko, Y. Yao (Eds.), Proc. of the Second Int. Conf. on Rough Sets and Current Trends in Computing (RSCTC’00), Banff, Canada, 16–19 Oct. 2000, 481–488.Google Scholar
  3. [3].
    L. Han, R. Menzies, J.F. Peters, L. Crowe, High voltage power faul detection and analysis system: Design and implementation. In: Proc. of the Canadian Conference on Electrical & Computer Engineering (CCECE’99), 1999, 1253–1258.Google Scholar
  4. [4].
    L. Han, J.F. Peters, S. Ramanna, R. Zhai, Classifying faults in high voltage power systems: A rough-fuzzy neural computational approach. In: N. Zhong, A. Skowron, S. Ohsuga (Eds.), New Directions in Rough Sets, Data Mining, and Granular Soft Computing, Lecture Notes in Artificial Intelligence, vol. 1711. Berlin: Springer Verlag, 1999, 47–54.CrossRefGoogle Scholar
  5. [5].
    P.J. Lingras, Fuzzy-rough and rough-fuzzy serial combinations in neurocomputing, Neurocomputing: An International Journal, vol. 36, Feb. 2001, 29–44.MATHCrossRefGoogle Scholar
  6. [6].
    P.J. Lingras, Rough neural networks. In: Proc. of the 6th Int. Conf. on Information Processing and Management of Uncertainty in Knowledge-based Systems (IPMU’96), Granada, Spain, 1996, p1445–1450.Google Scholar
  7. [7].
    P.J. Lingras, Comparison of neurofuzzy and rough neural networks, Information Science: An International Journal, vol. 110, 1998, 207–215.Google Scholar
  8. [8].
    S. Mitra, P. Mitra, S.K. Pal, Evolutionary modular design of rough knowledgebased network with fuzzy attributes, Neurocomputing: An International Journal, vol. 36, Feb. 2001, 45–66.Google Scholar
  9. [9].
    H.S. Nguyen, M. Szczuka, D. Slezak, Neural networks design: Rough set approach to real-valued data. In: Proc. of PKDD’97, Trondheim, Norway. Lecture Notes in Artificial Intelligence 1263, Berlin, Springer-Verlag, 1997, 359–366.Google Scholar
  10. [11].
    T. Nguyen, R.W. Swiniarski, A. Skowron, J. Bazan, K. Thagarajan, Applications of rough sets, neural networks and maximum likelihood for texture classification based on singular decomposition. In: Proc. of the Third International Workshop on Rough Sets and Soft Computing, San Jose, CA, U.S.A., 10–12 Nov. 1994, 332–339.Google Scholar
  11. [12].
    S.K. Pal, P. Mitra, Rough Fuzzy MLP: Modular Evolution, Rule Generation and Evaluation, IEEE Trans. on Knowledge and Data Engineering [to appear].Google Scholar
  12. [13].
    S.K. Pal, L. Polkowski, A. Skowron (Eds.), Rough-Neuro Computing: Techniques for Computing with Words. Berlin: Springer-Verlag, 2002.Google Scholar
  13. [14].
    S.K. Pal, J.F. Peters, L. Polkowski, A. Skowron (Eds.), Rough-Neuro Computing: An Introduction. In [18], 16–43.Google Scholar
  14. [15].
    W. Pedrycz, L. Han, J.F. Peters, S. Ramanna, R. Zhai, Calibration of software quality: Fuzzy neural and rough neural computing approaches, Neurocomputing, vol. 36, Feb. 2001, 149–170.MATHCrossRefGoogle Scholar
  15. [16].
    J.F. Peters, S. Ramanna, A. Skowron, M. Borkowski: Wireless agent guidance of remote mobile robots: Rough integral approach to sensor signal analysis. In: N. Zhong, Y.Y. Yao, J. Liu, S. Ohsuga (Eds.), Web Intelligence, Lecture Notes in Artificial Intelligence 2198. Berlin: Springer-Verlag, 2001, 413–422.Google Scholar
  16. [17].
    J.F. Peters, S. Ramanna, M. Borkowski, A. Skowron: Approximate sensor fusion in a navigation agent, in: N. Zhong, J. Liu, S. Ohsuga and J. Bradshaw (Eds.), Intelligent agent technology: Research and development. Singapore: World Scientific Publishing, 2001, 500–504.Google Scholar
  17. [18].
    J.F. Peters, S. Ramanna, Z. Suraj, M. Borkowski, Rough neurons: Petri net models and applications. In [18], 474–493.Google Scholar
  18. [19].
    J.F. Peters, A. Skowron, Z. Surai, L. Han, S. Ramanna, Design of rough neurons: Rough set foundation and Petri net model, International Symposium on Methodologies for Intelligent Systems (ISMIS’2000). In: Z.W. Ras, S. Ohsuga (Eds.), Foundations of Intelligent Systems, Lecture Notes in Artificial Intelligence, vol. 1932. Berlin: Springer Verlag, 2000, 283–291.Google Scholar
  19. [20].
    J.F. Peters, A. Skowron, L. Han, S. Ramanna, Towards rough neural computing based on rough membership functions: Theory and Application, Rough Sets and Current Trends in Computing, Lecture Notes in Artificial Intelligence, vol. 2005, Berlin, Springer-Verlag, 2000.Google Scholar
  20. [21].
    J.F. Peters, L. Han, S. Ramanna, Rough neural computing in signal analysis, Computational Intelligence, vol. 1, no. 3, 2001, 493–513.MathSciNetCrossRefGoogle Scholar
  21. [22].
    Z. Pawlak, J.F. Peters, A. Skowron, Z. Suraj, S. Ramanna, M. Borkowski, Rough measures and Integrals. In: S. Hirano, M. Inuiguchi, S. Tsumoto (Eds.), Lecture Notes in Computer Science, 2002 [to appear].Google Scholar
  22. [23].
    L. Polkowski, A. Skowron, Rough-neuro computing. In: W. Ziarko, Y. Yao (Eds.), Proc. of the Second Int. Conf. on Rough Sets and Current Trends in Computing (RSCTC’00), Banff, Canada, 16–19 Oct. 2000, 25–32.Google Scholar
  23. [24].
    A. Skowron, Toward intelligent systems: Calculi of information granules. In: S. Hirano, M. Inuiguchi, S. Tsumoto (Eds.), Bulletin of the International Rough Set Society, vol. 5, no. 1/2, 2001, 9–30.Google Scholar
  24. [25].
    J.F. Peters, A. Skowron, J. Stepaniuk, Rough granules in spatial reasoning. In: Proc. Joint 9th International Fuzzy Systems Association (IFSA) World Congress and 20th North American Fuzzy Information Processing Society (NAFIPS) Int. Conf., Vancouver, British Columbia, Canada, 25–28 June 2001, 1355–1361.Google Scholar
  25. [26].
    A. Skowron, J. Stepaniuk, Information Granules: Towards foundations of granular computing, International Journal of Intelligent Systems, vol. 16, no. 1, Jan. 2001, 57–104.MATHCrossRefGoogle Scholar
  26. [27].
    A. Skowron, J. Stepaniuk, Information granules and approximation spaces. In: Proc. of the 7th Int. Conf. on Information Processing and Management of Uncertainty in Knowledge-based Systems (IPMU’98), Paris, France, 6–10 July 1998, 1354–1361.Google Scholar
  27. [28].
    A. Skowron, J. Stepaniuk, J.F. Peters, Hierarchy of information granules. In: L. Czala (Ed.), Proc. of the Workshop on Concurrency, Specification and Programming, Oct. 2001, Warsaw, Poland, 254–268.Google Scholar
  28. [29].
    A. Skowron, J. Stepaniuk, J.F. Peters, Extracting patterns using information granules. In: S. Hirano, M. Inuiguchi, S. Tsumoto (Eds.), Bulletin of the International Rough Set Society, vol. 5, no. 1/2, 2001, 135–142.Google Scholar
  29. [30].
    W. Ziarko, Y.Y. Yao (Eds.), Proc. Int. Conf. on Rough Sets and Current Trends in Computing (RSCTC’2000), Lecture Notes in Artificial Intelligence, vol. 2005, Berlin, Springer Verlag, 2001.Google Scholar
  30. [31].
    L.A. Zadeh, Fuzzy logic = computing with words, IEEE Trans. on Fuzzy Systems, vol. 4, 1996, 103–111.CrossRefGoogle Scholar
  31. [32].
    P. Wojdyllo, Wavelets, rough sets and artificial neural networks in EEG analysis. In: Proc. of RSCTC’99, Lecture Notes in Artificial Intelligence 1424,Berlin, Springer-Verlag, 1998, 444–449.Google Scholar
  32. [33].
    R.W. Swiniarski, Rough sets and neural networks application to handwritten character recognition by complex Zernike moments. In: [13], 617–624.Google Scholar
  33. [34].
    J. Komorowski, Z. Pawlak, L. Polkowski, A. Skowron, Rough sets: A tutorial. In: S.K. Pal, A. Skowron (Eds.), Rough Fuzzy Hybridization: A New Trend in Decision-Making. Berlin: Springer-Verlag, 1999, 3–98.Google Scholar
  34. [35].
    Z. Pawlak, Rough Sets: Theoretical Aspects of Reasoning About Data. Boston, MA, Kluwer Academic Publishers, 1991.MATHGoogle Scholar
  35. [36].
    Z. Pawlak, A. Skowron, Rough membership functions. In: R. Yager, M. Fedrizzi, J. Kacprzyk (Eds.), Advances in the Dempster-Shafer Theory of Evidence, NY, John Wiley & Sons, 1994, 251–271.Google Scholar
  36. [37].
    R.A. Brooks, A robust layered control system for a mobile robot, vol. RA-2, no. 1, March 1986, 14–23.MathSciNetGoogle Scholar
  37. [38].
    T. Gomi, Evolutionary Robotics. Ontario, Canada: AAI Books, 1997.Google Scholar
  38. [39].
    Z. Pawlak, J.F. Peters, A. Skowron, Z. Suraj, S. Ramanna, M. Borkowski, Rough measures: Theory and Applications. In: S. Hirano, M. Inuiguchi, S. Tsumoto (Eds.), Rough Set Theory and Granular Computing, Bulletin of the International Rough Set Society, vol. 5, no. 1/2, 2001, 177–184.Google Scholar
  39. [40].
    R.C. Gonzalez, R.E. Woods, Digital Image Processing, Prentice Hall, Upper Saddle River, New Jersey 07458, 2002.Google Scholar
  40. [41].
    P.R. Halmos, Measure Theory. London: D. Van Nostrand Co., Inc., 1950.MATHGoogle Scholar
  41. [42].
    R.W. Swiniarski, L. Hargis, Rough sets as a front end of neural networks texture classifiers, Neurocomputing, vol. 36, Feb. 2001, 85–103.MATHCrossRefGoogle Scholar
  42. [43].
    M. Swiniarski, F. Hunt, D. Chalvet, D. Pearson, Prediction system based on neural networks and rough sets in a highly automated production process. In: Proc. of the 12th System Science Conf., Wroclaw, Poland, 1995.Google Scholar
  43. [44].
    M. Swiniarski, F. Hunt, D. Chalvet, D. Pearson, Intelligent data processing and dynamic process discovery using rough sets, statistical reasoning and neural networks in a highly automated production systems. In: Proc. of the 1st European Conf. on Application of Neural Networks in Industry, Helsinki, Finland, 1995.Google Scholar
  44. [45].
    M. S. Szczuka, Refining classifiers with neural networks, International Journal of Intelligent Systems, vol. 16, no. 1, Jan. 2001, 39–55.MATHCrossRefGoogle Scholar
  45. [46].
    M. S. Szczuka, Rough sets and artificial neural networks. In: L. Polkowski, A. Skowron (Eds.), Rough Sets in Knowledge Discovery 2: Applications, Cases Studies and Software Systems. Berlin: Physica Verlag, 1998, 449–470.CrossRefGoogle Scholar
  46. [47].
    M.S. Szczuka, Refining classifiers with neural networks, International Journal of Intelligent Systems, vol. 16, no. 1, Jan. 2001, 39–56.MATHCrossRefGoogle Scholar
  47. [48].
    M.S. Szczuka, Rough sets and artificial neural networks. In: L. Polkowski, A. Skowron (Eds.), Rough Sets in Knowledge Discovery 2: Applications, Case Studies and Software Systems. Berlin: Physica-Verlag, 1998, 449–470.CrossRefGoogle Scholar
  48. [49].
    M.S. Szczuka, Rough set methods for constructing artificial neural networks. In: B.D. Czejdo, I.I. Est, B. Shirazi, B. Trousse (Eds.), Proc. of the 3rd Biennial Joint Conf. on Engineering Systems Design and Analysis 7, Montpellier, France, 1–4 July 1996, 9–14.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • J. F. Peters
    • 1
  • T. C. Ahn
    • 2
  • M. Borkowski
    • 1
  • V. Degtyaryov
    • 1
  • S. Ramanna
    • 1
  1. 1.Computational Intelligence Laboratory, Department of Electrical and Computer EngineeringUniversity of ManitobaWinnipeg, ManitobaCanada
  2. 2.Intelligent Information Control & System Lab, School of Electrical & Electronic EngineeringWon-Kwang UniversityIksan, Chon-BukKorea

Personalised recommendations