這篇論文研究了關於陸、海、空，三種異質機構形式的機器人，其中包含:
1. 飛行機器人搭載灰塵傳感器進行空氣品質(霾害)之量測，以及智慧型自主亂流決策系統研發. 2. 地面機器人搭載微型光譜儀進行智慧型水質品質之量測(存在及濃度). 3. 陸海空三種異構機器人間之合作系統，其中包含空-陸；空-海(飛行機器人自主降落於地面機器人；飛行機器人自主降落於海上機器人)以及空-陸(飛行機器人定位及導航地面機器人移動至目的地)。
此論文結果成功利用類神經網路分類亂流方向，使機器人知道亂流從何而來並利用模糊邏輯進行決策，使機器人針對不同亂流的大小決定行走之方式(穿越或避開)。
此論文結果歸納出類神經網路可以精確的分類出液體之存在物質以及存在之濃度
，並提出一套新思路為利用影像辨識之方式判別液體是否為飲用水，此研究成果可以大幅幫助機器人在災區中快速辨識水質是否可飲用以及檢測出水質之物質及物質存在濃度。
此論文結果顯示由全域之空中機器人輔助地面機器人進行定位及導航較一般傳統局部性導航更為有效；結果也顯示由空中機器人之影像判別降落點比傳統使用全球定位系統更為符合災害應變之環境；此論文研究重點為證明在災害應變環境中單一機器人有諸多限制，因此提出陸海空機器人之群體智慧作為此篇論文之研究。

This thesis describes a heterogeneous robotic collaboration system. It includes 1. Air quality assurance using AMR (aerial mobile robot)/UAV (unmanned aerial vehicle) with the onboard PM2.5 detectors and the intelligent turbulence avoidance strategy, 2. Intelligent water quality assurance by using the GMR (ground mobile robot) with onboard micro-spectrometer. 3. Heterogeneous robotic collaboration, Aerial-Ground, Aerial-Water (AMR autonomous landing on GMR and WMR (Water Mobile Robot)) and Aerial-Ground (localization, mapping and path planning)
This thesis successfully used artificial neural network (ANN) to classify the direction of turbulence so that the AMR can know where the turbulence from and fuzzy logic control to making decision whether to go through or avoid it depends the different situation of turbulence.
The empirical result shows the ANN method can precise detect and recognize the liquid material and concentration. And the new ideal about liquid detect is the image based method about PSNR. It can quickly classify whether the liquid is pure water or not. This can quickly help people in disaster response area to classify whether it is the drinking water or not.
The empirical result shows the global aerial SLAM for the ground robot is more effective than the conventional local SLAM conducted by single ground robot alone. The visual servo based AMR landing on GMR and WMR is more reliable and precise than the conventional GPS and barometer based localization.

[1] W. J. Gauderman, R. Urman, E. Avol, K. Berhane, R. McConnell, E. Rappaport, et al., "Association of Improved Air Quality with Lung Development in Children," New England Journal of Medicine, vol. 372, pp. 905-913, 2015.
[2] K. A. Miller, D. S. Siscovick, L. Sheppard, K. Shepherd, J. H. Sullivan, G. L. Anderson, et al., "Long-Term Exposure to Air Pollution and Incidence of Cardiovascular Events in Women," New England Journal of Medicine, vol. 356, pp. 447-458, 2007.
[3] X. Liu, Z. Song, E. Ngai, J. Ma, and W. Wang, "PM2:5 monitoring using images from smartphones in participatory sensing," in Computer Communications Workshops (INFOCOM WKSHPS), 2015 IEEE Conference on, 2015, pp. 630-635.
[4] X. Sun, Y. Liu, W. Yao, and N. Qi, "Triple-stage path prediction algorithm for real-time mission planning of multi-UAV," Electronics Letters, vol. 51, pp. 1490-1492, 2015.
[5] Altitude and Horizontal Motion Control of Quadrotor UAV in the Presence of Air Turbulence M. Kamran Joyo, D. Hazry, S. Faiz Ahmed, M. Hassan Tanveer, Faizan. A. Warsi, A. T. Hussain.
[6] Anderson, S. J., et al. (2013). "The intelligent copilot: A constraint-based approach to shared-adaptive control of ground vehicles," IEEE Intelligent Transportation Systems Magazine 5(2): 45-54.
[7] Rodr, J., et al. (2014). "Field-Programmable System-on-Chip for Localization of UGVs in an Indoor iSpace," IEEE Transactions on Industrial Informatics 10(2): 1033-1043.
[8] Gupta, N. and R. Dahmani (1997). AOTF spectrometer for water pollutant monitoring. Engineering in Medicine and Biology Society, 1997. Proceedings of the 19th Annual International Conference of the IEEE.
[9] Lee, M. F. R., et al. (2013). Remote sensing and analysis using autonomous mobile robot with onboard micro-spectrometer, 2013 International Conference on Fuzzy Theory and Its Applications (iFUZZY).
[10] Hore, A. and D. Ziou (2013). "Is there a relationship between peak-signal-to-noise ratio and structural similarity index measure?" IET Image Processing 7(1): 12-24.
[11] Wang, H., et al. (2011). "A nonparametric-test-based structural similarity measure for digital images." Computational Statistics and Data Analysis 55(11): 2925-2936.
[12] J. H. Kim, J. w. Kwon, and J. Seo, "Multi-UAV-based stereo vision system without GPS for ground obstacle mapping to assist path planning of UGV," Electronics Letters, vol. 50, pp. 1431-1432, 2014.
[13] Y. Song, H. Wang, and J. Zhang, "A Vision-Based Broken Strand Detection Method for a Power-Line Maintenance Robot," IEEE Transactions on Power Delivery, vol. 29, pp. 2154-2161, 2014.
[14] C. Teuli, E. Marchand, and L. Eck, "3-D Model-Based Tracking for UAV Indoor Localization," IEEE Transactions on Cybernetics, vol. 45, pp. 869-879, 2015.
[15] Y. Zeng, R. Zhang, and T. J. Lim, "Wireless communications with unmanned aerial vehicles: opportunities and challenges," IEEE Communications Magazine, vol. 54, pp. 36-42, 2016.
[16] B.Subudhi,Computational Intelligence,Control and Computer Vision in Robotics and Automation. Narosa Pub House,2009.
[17] F. O. Karray and C. W. De Silva, Soft Computing and Intelligent Systems Design: Theory, Tools, and Applications: Pearson/Addison Wesley, 2004.
[18] Taiwan environment protection administration http://goo.gl/Ta4Neq.
[19] An Introduction to Signal Processing in Chemical Analysis. Available: http://terpconnect.umd.edu/~toh/spectrum/TOC.html? s_v1=37969498_1-EOGJSI.
[20] Curve fitting B: Multicomponent Spectroscopy. Available: http://terpconnect.umd.edu/~toh/spectrum/CurveFittingB.html.
[21] Zhengyou, Z. (1999). Flexible camera calibration by viewing a plane from unknown orientations. Computer Vision, 1999. The Proceedings of the Seventh IEEE International Conference on.