Advertisement

Fuzzy Inference Integrating 3D Measuring System with Adaptive Sensing Strategy

  • Koji Shimojima
  • Toshio Fukuda
  • Fumihito Arai
  • Hideo Matsuura
Part of the International Series in Intelligent Technologies book series (ISIT, volume 3)

Abstract

This chapter deals with a 3-D measurement system applied to a curved metal surface carving system, and a sensor integration method based on fuzzy inference and adaptive sensing strategy. The measurement system consists of two different sensors. One is a LED displacement sensor, while the other is a vision system. The LED displacement sensor’s spot-light is used as a part of the vision system based on the active stereo sensing method. In addition, the LED displacement sensor’s outputs are used for calibrating camera parameters. Therefore, we can calibrate the camera parameters easily. Then, we use neural networks to compensate the output of the image processing for some errors, such as camera parameter’s error and lens distortion. By utilizing the neural networks, we can use a vision system accurately. We use a sensor integration method based on the fuzzy set theory. Fuzzy inference’s input consists of information on the change in the sensor output and the position change of the sensor system, together with the environmental data of measurement. Vision system can be used under various environmental condition, but it takes long time. The LED displacement sensor can obtain the information quickly, but it can only be used in limited environmental condition. In order to measure the object quickly and accurately, the sensor integration system has an adaptive sensing strategy. The sensing strategy depends on a relation between the state of the object, e.g. color, temperature, etc., and the sensor specification. The proposed system is shown to be effective through extensive experiments.

Keywords

Vision System Camera Calibration Intelligent Robot Camera Parameter Multisensor Integration 
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]
    F.M. Proctor, R.J. Norcross, K.N. Murphy, “Automating Robot Programming in the Cleaning and Deburring Workstation of the AMRF,” SME, Technical Paper, pp.1/11, (1989).Google Scholar
  2. [2]
    K. Kashiwagi, K. Ono, E. Izumi, T. Kurenuma, K. Yamada, “Force Controlled Robot for Grinding,” IEEE Int’l Workshop on Intelligent Robots and Systems(IROS’ 90), pp.1001/1006, (1990).Google Scholar
  3. [3]
    T. Fukuda, K. Shimojima, F. Arai, H. Matsuura, “Multisensor Integration System based on Fuzzy Inference and Neural Network,” J. of Information Sciences, Vol. 71, No.1 and 2, pp. 27/41, (1993).Google Scholar
  4. [4]
    T. Fukuda, K. Shimojima, F. Arai, H. Matsuura, “A Multi-Sensor Integration System with Fuzzy Inference and Neural Network,” Pacific Rim Int’l Conf. on Artificial Intelligence 90(PRICAI’ 90), pp. 859/864, (1990).Google Scholar
  5. [5]
    K. Shimojima, T. Fukuda, F. Arai, H. Matsuura, “Fuzzy Inference Integrated 3-D Measuring System with LED Displacement Sensor and Vision System,” J. of Intelligent and Fuzzy System, Vol.1, No.l, pp. 63/72, (1993).Google Scholar
  6. [6]
    R.C. Luo, M.G. Kay, “Multi-sensor integration and fusion in intelligent systems,” IEEE Trans. on System, Man, and Cybernetics, Vol. 19, No.5, pp. 901/931, (1989).CrossRefGoogle Scholar
  7. [7]
    H. F. Durrant-Whyte, “Sensor models and multi-sensor integration,” Int’l J. Robot. Res., Vol. 7, No.6, Dec, pp. 97/113,(1988).Google Scholar
  8. [8]
    R. C. Luo, M. Lin, “Dynamic multi-sensor data fusion system for intelligent robots,” IEEE J. Robot. Automat., Vol. 4, No.4, pp. 386/396, (1988).CrossRefGoogle Scholar
  9. [9]
    Y. F. Zheng, “Integration of multiple sensors into a robotic system and its performance evaluation,” IEEE Trans. Robotics and Automat., Vol. 5, No.5, pp. 658/669 (1989).Google Scholar
  10. [10]
    J. M. Richardson, K. A. Marsh, “Fusion of multi-sensor data, Int’l. J. Robot. Res., Vol. 7, No.6, pp 78/96,(1988).Google Scholar
  11. [11]
    M. Abdlghafour, T. Chandra, M. A. Abidi, “Data fusion through fuzzy logic applied to feature extraction from multi-sensor images,” IEEE Int’l Conf. on Robotics and Automation, Vol.2, pp. 359/366, (1993).Google Scholar
  12. [12]
    T. Kanade, M. Okutomi, “A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment,” IEEE Int’l Conf. on Robotics and Automation, pp.1088/1095, (1991).Google Scholar
  13. [13]
    K. Sato, S. Inokuchi, “Three-dimensional surface measurement by space encoding range imaging,” J. of Robotic System, vol.2, no.1, pp.27/39, (1985).Google Scholar
  14. [14]
    R. Gutsche, T. Stahs, F.M. Wahl, “Path Generation with a Universal 3d Sensor,” IEEE Int’l Conf. on Robotics and Automation, pp. 838/843, (1991).Google Scholar
  15. [15]
    D.E. Rumelhart, J.L. McClelland, and The PDP Research Group, “Parallel Distribute Processing, The MIT Press, USA, (1986)Google Scholar
  16. [16]
    M.A. Abidi, “A regularized multi-dimensional data fusion technique,” Proc. of IEEE Int’l Conf. on Robotics and Automation, pp. 2738/2744, (1991).Google Scholar
  17. [17]
    T. Aono, M. Ishikawa, “Auditory-visual fusion using multi-input hidden markov model,” Proc. of the IMACS/SICE Int’l Symposium on Robotics, Mechatronics and Manufacturing System’92, pp. 1085–1090, (1992)Google Scholar
  18. [18]
    O. Basir, H.C. Shen, “Sensory Data Integration: A Team Consensus Approach,” Proc. of IEEE Int’l Conf. on Robotics and Automation, pp. 1683/1688, (1992).Google Scholar
  19. [19]
    O. Basir, H.C. Shen, “Aggregating interdependent sensory data in multi-sensor systems,” Proc. of 1993 IEEE/RSJ Int’l Conf. on Intelligent Robots and System, pp.377/383, (1993a).Google Scholar
  20. [20]
    O. Basir, H.C. Shen, “Goal-driven task assignment and sensor control in multi-sensor systems: a multicriteria approach,” Proc. of IEEE Int’l Conf. on Robotics and Automation, Vol. 2, pp. 559/566, (1993 b).Google Scholar
  21. [21]
    M. Beckerman, “A bayes-maximum entropy method for multi-sensor data fusion,” Proc. of IEEE Int’l Conf. on Robotics and Automation, pp. 1668/1674, (1992).Google Scholar
  22. [22]
    V. Berge-Cherfaoui, B. Vachon, “A multi-agent approach of the multi-sensor fusion,” Proc. of Fifth Int’l Conf. on Advanced Robotics, pp.1264/1274, (1991)Google Scholar
  23. [23]
    I.J. Cox, J.J. Leonard, “Probabilistic data association for dynamic worl modeling: a multiple hypothesis approach,” Proc. of Fifth Int’l Conf. on Advanced Robotics, pp.1287/1294, (1991)Google Scholar
  24. [24]
    F. Dessen, “Sensor integration using an event driven state estimator,” Proc. of Intelligent autonomous system, pp. 897/906, (1989)Google Scholar
  25. [25]
    C. Duriev, H. Clergeot, “A statistical approach to geometric robot location including data fusion and error rejection,” Proc. of Intelligent autonomous system, pp.886/896, (1989)Google Scholar
  26. [26]
    H.F. Durrant-Whyte, B.Y.S. Rao, H. Hu., “Toward a fully decentralized architecture for multi-sensor data fusion,” Proc. of IEEE Int’l Conf. on Robotics and Automation, pp. 1331/1336, (1990).Google Scholar
  27. [27]
    T. D’Orazio, M. Ianigro, E. Stella, F.P. Lovergine, A. Distante, ”Mobile robot navigation by multi-sensory integration,” Proc. of IEEE Int’l Conf. on Robotics and Automation, Vol. 2, pp. 373/379, (1993).Google Scholar
  28. [28]
    C. Ferrell, “Many sensors, one robot,” Proc. of 1993 IEEE/RSJ Int’l Conf. on Intelligent Robots and System, pp 399/406, (1993).Google Scholar
  29. [29]
    I. Gasparovic, “Integration of the multisensory information system,” Proc. of the Second Int’l Symposium on Measurement and Control in Robotics, pp. 125/136, (1992)Google Scholar
  30. [30]
    J.K. Hackett, M. Shah, “Multi-sensor fusion: a perspective,” Proc. of IEEE Int’l Conf. on Robotics and Automation, pp. 1324/1330, (1990).Google Scholar
  31. [31]
    G.D. Hager, S.P. Engelson, S. Atiya, “On comparing statistical and set-based methods in sensor data fusion,” Proc. of IEEE Int’l Conf. on Robotics and Automation, Vol. 2, pp. 352/358, (1993)Google Scholar
  32. [32]
    L. Hong, T. Scaggs, “Real-time optimal multiresolutional sensor/data fusion,” Proc. of IEEE Int’l Conf. on Robotics and Automation, Vol. 2, pp. 117/122, (1993).Google Scholar
  33. [33]
    K. Hughes, N. Ranganathan, “A model for determining sensor confidence,” Proc. of IEEE Int’l Conf. on Robotics and Automation, Vol. 2, pp. 136/141, (1993).Google Scholar
  34. [34]
    T. Kawashima, T. Nagasaki, Y. Aoki, “Sensor fusion system for model-based object tracking,” Proc. of the Second Int’l Symposium on Measurement and Control in Robotics, pp. 265/270, (1992)Google Scholar
  35. [35]
    A. Kosaka, A.C. Kak, “Data fusion an perception planning for indoor mobile robot navigation,” Proc. of the Second Int’l Symposium on Measurement and Control in Robotics, pp. 271/278, (1992)Google Scholar
  36. [36]
    R.C. Luo, M.G. Kay, W. Gary Lee, Multisensor integration and fusion: issues, approaches, and future trends,” Proc. of the IMACS/SICE Int’l Symposium on Robotics, Mechatronics and Manufacturing System’92, pp.1055/1063, (1992)Google Scholar
  37. [37]
    D. Matusmoto, T. Kimoto, S. Nagata, “A neural network approach to sensorimotor fusion,” Proc. of the IMACS/SICE Int’l Symposium on Robotics, Mechatronics and Manufacturing System’92, pp.1105/1110, (1992)Google Scholar
  38. [38]
    T. Moriizumi, T. Nakamoto, Odor sensing system using neural network pattern recognition,” Proc. of 1992 Int’l Conf. on Industrial Electronics Control and Instrumentation, pp. 1645/16479, (1992)Google Scholar
  39. [39]
    T. Moriwaki, V. Mori, “Sensor fusion for in-process identification of cutting process based on neural network approach,” Proc. of the IMACS/SICE Int’l Symposium on Robotics, Mechatronics and Manufacturing System’92, pp.245/250, (1992)Google Scholar
  40. [40]
    T. Mukai, T. Mori, M. Ishikawa, “A sensor fusion system using mapping learning method,” Proc. of 1993 IEEE/RSJ Int’l Conf. on Intelligent Robots and System, pp.391/396, (1993)Google Scholar
  41. [41]
    R.R. Murphy, “Robust sensor fusion for teleoperations,” Proc. of IEEE Int’l Conf. on Robotics and Automation, Vol. 2, pp. 572/577, (1993).Google Scholar
  42. [42]
    C. Olivier, O. Dessouble, “Heterogeneous sensors cooperation for an advanced perception system,“ Proc. of Fifth Int’l Conf. on Advanced Robotics, pp.1275/1280, (1991)Google Scholar
  43. [43]
    T. Oomichi, Y. Fuke, “Hierarchical navigation of legged robot for terrain based on sensor fusion,” Proc. of the IMACS/SICE Int’l Symposium on Robotics, Mechatronics and Manufacturing System’92, pp.1071/1076, (1992)Google Scholar
  44. [44]
    F. Ramparany, “Multisensor data fusion for robotic tasks,” Proc. of the IMACS/SICE Int’l Symposium on Robotics, Mechatronics and Manufacturing System’92, pp. 1091/1098, (1992)Google Scholar
  45. [45]
    A. Sabater, F. Thomas, “Set membership approach to the propagation of uncertain geometric information,” Proc. of IEEE Int’l Conf. on Robotics and Automation, pp. 2718/2723, (1991).Google Scholar
  46. [46]
    Y. Sakaguchi, K. Nakano, ”Active perception with intentional observation,” Proc. of the Second Int’l Symposium on Measurement and Control in Robotics, pp. 241/248, (1992)Google Scholar
  47. [47]
    K.T. Song, C.C. Chang, “Ultrasonic sensor data fusion for environment recognition,” Proc. of 1993 IEEE/RSJ Int’l Conf. on Intelligent Robots and System, pp.384/390, (1993)Google Scholar
  48. [48]
    A. Takahashi, M. Ishikawa, “Signal processing architecture with bidimensional network topology for flexible sensor data integration system,” Proc. of 1993 IEEE/RSJ Int’l Conf. on Intelligent Robots and System, pp 407/413, (1993)Google Scholar
  49. [49]
    H. Xu., “Effective fusion technique for disparate sensory data,” Proc, of 1991 Int’l Conf. on Industrial Electronics, Control and Instrumentation, pp.2535/2540, (1991)Google Scholar

Copyright information

© Kluwer Academic Publishers 1995

Authors and Affiliations

  • Koji Shimojima
    • 1
  • Toshio Fukuda
    • 1
  • Fumihito Arai
    • 1
  • Hideo Matsuura
    • 1
  1. 1.Department of Mechano-Informatics and SystemsNagoya UniversityFuro-cho, Chikusa-ku, HagoyaJapan

Personalised recommendations