Multi-Scale Adaptive Sampling with Mobile Agents for Mapping of Forest Fires

  • Muhammad F. Mysorewala
  • Dan O. Popa
  • Frank L. Lewis
Article
First Online:
Received:
Accepted:

Abstract

The use of robotics in distributed monitoring applications requires wireless sensors that are deployed efficiently. A very important aspect of sensor deployment includes positioning them for sampling at locations most likely to yield information about the spatio-temporal field of interest, for instance, the spread of a forest fire. In this paper, we use mobile robots (agents) that estimate the time-varying spread of wildfires using a distributed multi-scale adaptive sampling strategy. The proposed parametric sampling algorithm, “EKF-NN-GAS” is based on neural networks, the extended Kalman filter (EKF), and greedy heuristics. It combines measurements arriving at different times, taken at different scale lengths, such as from ground, airborne, and spaceborne observation platforms. One of the advantages of our algorithm is the ability to incorporate robot localization uncertainty in addition to sensor measurement and field parameter uncertainty into the same EKF model. We employ potential fields, generated naturally from the estimated fire field distribution, in order to generate fire-safe trajectories that could be used to rescue vehicles and personnel. The covariance of the EKF is used as a quantitative information measure for sampling locations most likely to yield optimal information about the sampled field distribution. Neural net training is used infrequently to generate initial low resolution estimates of the fire spread parameters. We present simulation and experimental results for reconstructing complex spatio-temporal forest fire fields “truth models”, approximated by radial basis function (RBF) parameterizations. When compared to a conventional raster scan approach, our algorithm shows a significant reduction in the time necessary to map the fire field.

Keywords

Adaptive sampling Sensor fusion Kalman filter Potential fields Environmental monitoring Forest fires 
This is a preview of subscription content, log in to check access.

References

  1. 1.
    Anderson, B., Moore, J.: Optimal Filtering. Prentice-Hall, Englewood Cliffs, NJ (1979)MATHGoogle Scholar
  2. 2.
    Anderson, D.H., Catchpole, E.A., DeMestre, N.J., Parkes, T.: Modeling the spread of grass fires. J. Aust. Math. Soc. (Ser. B.) 23, 451–466 (1982)MATHCrossRefGoogle Scholar
  3. 3.
    Cannell, C.J., Stilwell, D.J.: A comparison of two approaches for adaptive sampling of environmental processes using autonomous underwater vehicles. Oceans 2, 1514–1521 (2005)Google Scholar
  4. 4.
    Christopoulos, V.N., Roumeliotis, S.: Adaptive sensing for instantaneous gas release parameter estimation. International Conference on Robotics and Automation, 2005. ICRA 2005. In: Proceedings of the 2005 IEEE, pp. 4450–4456. (2005) 18–22 AprGoogle Scholar
  5. 5.
    Chuvieco, E. (ed.): Wildland Fire Danger Estimation and Mapping: The Role of Remote Sensing Data. World Scientific Publishing Company, New Jersey, USA (2004)Google Scholar
  6. 6.
    Creed, E.L., Glenn, S.M., Chant, R.: Adaptive sampling experiment at LEO-15. OCC 1998 Proceedings, Marine Technology Section. pp. 576–579 (1998) NovGoogle Scholar
  7. 7.
    Elfes, A.: Using occupancy grids for mobile robot perception and navigation. Computer. 22(6), 46–57 (1989)CrossRefGoogle Scholar
  8. 8.
    Farrell, J.A., Shuo, P., Wei, L.: Chemical plume tracing via an autonomous underwater vehicle. IEEE J. Oceanic. Eng. 30(2), 428–442 (2005)CrossRefGoogle Scholar
  9. 9.
    Finney, M.A.: FARSITE: fire area simulator-model development and evaluation. Res. Pap. RMRS-RP-4. U.S. Department of Agriculture, Forest Service, Rocky Mountain Research Station, Ogden, UT, p. 47 (1998)Google Scholar
  10. 10.
    Fox, D., Burgard, W., Kruppa, H., Thrun, S.: A probabilistic approach to collaborative multi-robot localization. Auton Robots. 8(3), 325–344 (2000), Special issue on Heterogeneous Multi-Robot SystemsCrossRefGoogle Scholar
  11. 11.
    Ge, S.S., Cui, Y.J.: Dynamic motion planning for mobile robots using potential field method. Int. J. Auton. Robots. 13, 207–222 (2002)MATHCrossRefGoogle Scholar
  12. 12.
    Green, D.G.: Shapes of simulated fires in discrete fuels. Ecol. Mod. 20, 21–32 (1983)CrossRefGoogle Scholar
  13. 13.
    Green, D.G., Gill, A.M., Noble, I.R.: Fire shapes and the adequacy of fire-spread models. Ecol. Mod. 20, 33–45 (1983)CrossRefGoogle Scholar
  14. 14.
    Haykin, S.: Neural Networks: A Comprehensive Foundation, 2nd. Prentice Hall, USA (1998)Google Scholar
  15. 15.
    Hombal, V., Sanderson, A., Blidberg, R.: A non-parametric iterative algorithm for adaptive sampling and robotic vehicle path planning. International Conference on Intelligent Robots and Systems, 2006 IEEE/RSJ, pp. 217–222. (2006) OctGoogle Scholar
  16. 16.
    Howard, A., Mataric, M.J., Sukhatme, G.S.: Mobile sensor network deployment using potential fields: a distributed, scalable solution to the area coverage problem. In: Proc. of 6th International Symposium on Distributed Autonomous Robotic Systems. Fukuoka, Japan, pp. 299–308 (2002)Google Scholar
  17. 17.
    Jatmiko, W., Sekiyama, K., Fukuda, T.: A mobile robots PSO-based for odor source localization in dynamic advection-diffusion environment. In: International Conference on Intelligent Robots and Systems, 2006, IEEE/RSJ. pp. 4527–4532 (2006) OctGoogle Scholar
  18. 18.
    Johnson, E.A., Miyanishi, K. (ed.): Forest Fires-Behavior and Ecological Effects. Academic, San Diego (2001)Google Scholar
  19. 19.
    Karafyllidis, I., Thanailakis, A.: A model for predicting forest fire spreading using cellular automata. Ecol. Mod. 99, 87–97 (1997)CrossRefGoogle Scholar
  20. 20.
    Khatib, O.: Real-time obstacle avoidance for manipulators and mobile robots. In: Proc. IEEE, International Conference on Robotics and Automation, pp. 500–505. (1985) 25–28 MarGoogle Scholar
  21. 21.
    Krogh, B.H.: A generalized potential field approach to obstacle avoidance control. In: Proc. of International Robotics Research Conference. pp. 1150–1156 (1984) AugGoogle Scholar
  22. 22.
    Latombe, J.: Robot Motion Planning. Academic, Boston (1991)Google Scholar
  23. 23.
    Lewis, F.L., Xie, L., Popa, D.O.: Optimal and Robust Estimation: With an Introduction to Stochastic Control Theory. CRC, Florida, USA (2007)Google Scholar
  24. 24.
    Li, X., Yeh, A.G..: Neural-network-based cellular-automata for simulating multiple land use changes using GIS. Int. J. Geogr. Inf. Sci. 16(4), 323–344 (2002)CrossRefGoogle Scholar
  25. 25.
    Lippmann, R.P.: Pattern classification using neural networks. Commun. Mag, IEEE. 27(11), 47–50, 59–64 (1989) NovCrossRefGoogle Scholar
  26. 26.
    Low, K.H., Gordon, G.J., Dolan, J.M., Khosla, P.: Adaptive Sampling for Multi-Robot Wide-Area Exploration. In: 2007 IEEE International Conference on Robotics and Automation. pp. 755–760, (2007) 10–14 AprGoogle Scholar
  27. 27.
    Mandel, J., Darema, F. (Ed.): Dynamic Data Driven Wildfire Modeling. Dynamic Data Driven Applications Systems. Academic, New York (2004)Google Scholar
  28. 28.
    Muzy, A., Innocenti, E., Aiello, A., Santucci, J., Wainer, G.: Specification of discrete event models for fire spreading. Simulation 81(2), 103–117 (2005)CrossRefGoogle Scholar
  29. 29.
    Olfati-Saber, R.: Distributed Kalman filter with embedded consensus filters. In: 44th IEEE Conference Decision and Control, 2005 and 2005 European Control Conference. CDC-ECC ‘05 pp. 8179–8184, (2005) 12–15 DecGoogle Scholar
  30. 30.
    Popa, D.O.: Optimal sampling using singular value decomposition of the parameter variance space. In: 2005. (IROS 2005). 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 3131–3136, (2005) 2–6 AugGoogle Scholar
  31. 31.
    Popa, D.O., Mysorewala, M.F., Lewis, F.L.: EKF-based adaptive sampling with mobile robotic sensor nodes. In: International Conference on Intelligent Robots and Systems, 2006 IEEE/RSJ, pp. 2451–2456 (2006) OctGoogle Scholar
  32. 32.
    Popa, D.O., Mysorewala, M.F., Lewis, F.L.: Deployment Algorithms and In-Door Experimental Vehicles for Studying Mobile Wireless Sensor Networks. To appear in ACIS International Journal of Sensor Networks (2009)Google Scholar
  33. 33.
    Popa, D.O., Stephanou, H.E., Helm, C., Sanderson, A.C.: Robotic deployment of sensor networks using potential fields. In: The Proc. of International Conference on Robotics and Automation (2004) April–MayGoogle Scholar
  34. 34.
    Popa, D.O, et al.: Adaptive sampling algorithms for multiple autonomous underwater vehicles. In: Autonomous Underwater Vehicles, 2004 IEEE/OES, pp. 108–118 (2004) 17–18 JuneGoogle Scholar
  35. 35.
    Rao, B.S., Durrant-Whyte, H.F.: Fully decentralised algorithm for multisensor Kalman filtering. IEE Proc Part D. 138(5), 413–420 (1991)Google Scholar
  36. 36.
    Rothermel, R.C.: How to predict the spread and intensity of forest and range fires. Gen. Tech. Rep. INT-143. U.S. Department of Agriculture, Forest Service, Intermountain Forest and Range Experiment Station, Ogden, UT, p. 161 (1983)Google Scholar
  37. 37.
    Roumeliotis, S.I., Bekey, G.A.: Distributed Multi-Robot Localization. Distributed Autonomous Robotic Systems 4. Springer Verlag, New York, pp. 179–188 (2000)Google Scholar
  38. 38.
    Russell, R.A., Bab-Hadiashar, A., Shepherd, R.L., Wallace, G.G.: A comparison of reactive robot chemotaxis algorithms. Robot. Auton. Syst. 45(2), 83–97 (2003) 30 NovCrossRefGoogle Scholar
  39. 39.
    Scott, D.: Multivariate Density Estimation: Theory, Practice, and Visualization. Wiley, New York (1992)MATHCrossRefGoogle Scholar
  40. 40.
    Silverman, B.: Density Estimation for Statistics and Data Analysis. Chapman & Hall/CRC, USA (1986)MATHGoogle Scholar
  41. 41.
    Singh, A. et al.: Multiscale sensing: a new paradigm for actuated sensing of high frequency dynamic phenomena. In: International Conference on Intelligent Robots and Systems, 2006 IEEE/RSJ, pp. 328–335 (2006) OctGoogle Scholar
  42. 42.
    Trunfio, G.A.: Predicting Wildfire Spreading through a Hexagonal Cellular Automata Model. ACRI, pp. 385–394 (2004)Google Scholar
  43. 43.
    Wagner, V.: A simple fire growth model. Forestry Chron. 45, 103–104 (1969)Google Scholar

Copyright information

© Springer Science+Business Media B.V. 2008

Authors and Affiliations

  • Muhammad F. Mysorewala
    • 1
  • Dan O. Popa
    • 1
  • Frank L. Lewis
    • 1
  1. 1.Automation & Robotics Research InstituteThe University of TexasArlingtonUSA

Personalised recommendations