Abstract
In the situation of pollutant leakage from industrial facilities, comprehensive and accurate monitoring of the area of incident is critical. In this paper, we present a Bayesian Optimization (BO)-based approach for such a task and use the Gaussian Processes (GPs) as the underlying surrogate model. A spatial-temporal covariance is designed for the GPs to capture the time varying environment which is modeled using a Gaussian puff dynamic model. The performance achieved by using a fixed senor network and an Unmanned Aerial Vehicle (UAV) is compared and analyzed. We construct a continuous path-based reward function, based on which BO will design an optimal, three-dimensional path for the UAV. A more challenging situation that involves multiple puff emissions is also considered. The UAV is shown to be able to monitor the periodic environment and track the highest concentration which is time-varying.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Availability of data and material
Not applicable.
Code availability
The code used in the study is written on MATLAB software. And the code is customized based on a free source offered by [15]
References
Marchant, R., Ramos, F.: Bayesian optimisation for intelligent environmental monitoring. In: 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 2242–2249. (2012). https://doi.org/10.1109/IROS.2012.6385653
Marchant, R., Ramos, F.: Bayesian optimisation for informative continuous path planning. In: 2014 IEEE International Conference on Robotics and Automation (ICRA), pp. 6136–6143. (2014). https://doi.org/10.1109/ICRA.2014.6907763
Marchant, R., Ramos, F., Sanner, S.: Sequential bayesian optimisation for spatial-temporal monitoring. In: Proceedings of the Thirtieth Conference on Uncertainty in Artificial Intelligence, UAI’14, pp. 553–562. AUAI Press, Arlington, Virginia, USA (2014)
Stachniss, C., Plagemann, C., Lilienthal, A., Burgard, W.: Gas distribution modeling using sparse gaussian process mixture models. In: Robotics: Science and Systems IV, Robotics: Science and Systems Foundation (2008). https://doi.org/10.15607/RSS.2008.IV.040.http://www.roboticsproceedings.org/rss04/p40.pdf
Brooks, A., Makarenko, A., Upcroft, B.: Gaussian process models for sensor-centric robot localisation. In: Proceedings 2006 IEEE International Conference on Robotics and Automation, 2006. ICRA 2006., pp. 56–61. IEEE, Orlando, FL, USA (2006). https://doi.org/10.1109/ROBOT.2006.1641161.http://ieeexplore.ieee.org/document/1641161/
Lilienthal, A., Duckett, T.: Buildi ng gas concentration gridmaps with a mobile robot. Robotics and Autonomous Systems 48(1), 3–16 (2004). https://doi.org/10.1016/j.robot.2004.05.002.https://linkinghub.elsevier.com/retrieve/pii/S092188900 4000727
Gosmann, J.: Gaussian processes for plume distribution estimation with uavs. Master’s thesis, TU Berlin (2013). /fileadmin/fg135/publikationen/Gosmann_2013_GPP.pdf
Stockie, J.M.: The mathematics of atmospheric dispersion modeling. SIAM Rev. 53(2), 349–372 (2011). https://doi.org/10.1137/10080991X
Kathirgamanathan, P., McKibbin, R., Mclachlan, R.: Source term estimation of pollution from an instantaneous point source. Research Letters in the Information and Mathematical Sciences 3
De Nardi, R.: The qrsim quadrotors simulator. RN 13(08), 08 (2013)
Balter, B., Faminskaya, M.: Irregularly emitting air pollution sources: acute health risk assessment using AERMOD and the Monte Carlo approach to emission rate. Air Quality, Atmosphere & Health 10(4), 401–409 (2017). https://doi.org/10.1007/s11869-016-0428-x
Rasmussen, C.E., Williams, C.K.I.: Gaussian processes for machine learning (Adaptive Computation and Machine Learning). The MIT Press (2005)
Guestrin, C., Krause, A., Singh, A.P.: Near-optimal sensor placements in Gaussian processes. In: Proceedings of the 22nd international conference on Machine learning - ICML ’05, pp. 265–272. ACM Press, Bonn, Germany (2005). https://doi.org/10.1145/1102351.1102385
Hollinger, G., Sukhatme, G.: Sampling-based motion planning for robotic information gathering. In: Robotics: Science and Systems IX, Robotics: Science and Systems Foundation (2013). https://doi.org/10.15607/RSS.2013.IX.051.http://www.roboticsproceedings.org/rss09/p51.pdf
Bradford, E., Schweidtmann, A.M., Lapkin, A.: Efficient multiobjective optimization employing Gaussian processes, spectral sampling and a genetic algorithm. Journal of Global Optimization 71(2), 407–438 (2018). https://doi.org/10.1007/s10898-018-0609-2
Singh, A., Ramos, F., Whyte, H.D., Kaiser, W.J.: Modeling and decision making in spatio-temporal processes for environmental surveillance. In: 2010 IEEE International Conference on Robotics and Automation, pp. 5490–5497. (2010). https://doi.org/10.1109/ROBOT.2010.5509934
Brochu, E., Cora, V.M., de Freitas, N.: A tutorial on bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning. arXiv:1012.2599 [cs]
Nyikosa, F.M., Osborne, M.A., Roberts, S.J.: Bayesian optimization for dynamic problems. arXiv:1803.03432 [stat]
Shahriari, B., Swersky, K., Wang, Z., Adams, R.P., de Freitas, N.: Taking the human out of the loop: A review of bayesian optimization. Proc. IEEE 104(1), 148–175 (2016). https://doi.org/10.1109/JPROC.2015.2494218
Cox, D., John, S.: A statistical method for global optimization. In: [Proceedings] 1992 IEEE International Conference on Systems, Man, and Cybernetics, vol. 2, pp. 1241–1246. (1992). https://doi.org/10.1109/ICSMC.1992.271617
Wikipedia, Sobol sequence. https://en.wikipedia.org/wiki/Sobol_sequence, accessed April 2021
Shampine, L.: Vector ized adaptive quadrature in MATLAB. J. Comput. Appl. Math. 211(2), 131–140 (2008). https://doi.org/10.1016/j.cam.2006.11.021,https://linkinghub.elsevier.com/retrieve/pii/S037704270 600700X
Finkel, D.E., Kelley, C.T.: Global optimization with the direct algorithm, Ph.D. thesis, aAI3162434 (2005)
MathWorks, Find minimum of constrained nonlinear multivariable function. https://www.mathworks.com/help/optim/ug/fmincon.html, accessed January 2021
Funding
No funds, grants, or other support was received for conducting this study.
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and initial ideas. Tianyu Gao contributed to the designs and Xiaoli Bai joined in the discussion and approved the designs. Environment building, simulation and analysis were performed by Tianyu Gao. The first draft of the manuscript was written by Tianyu Gao, and Xiaoli Bai commented on every previous versions of the manuscript. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflicts of interest
The authors have no relevant financial or non-financial interests to disclose.
Ethics approval
Not applicable.
Consent to participate
Not applicable.
Consent for publication
Not applicable.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Gao, T., Bai, X. Bayesian Optimization-based Three-dimensional, Time-varying Environment Monitoring using an UAV. J Intell Robot Syst 105, 91 (2022). https://doi.org/10.1007/s10846-022-01709-x
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10846-022-01709-x