Autonomous Remote Sensing of Invasive Species from Robotic Aircraft

  • Ali Haydar Göktoǧan
  • Salah Sukkarieh
Reference work entry


This chapter presents an Unmanned Aircraft System (UAS) which consists of a helicopter, a fixed wing Unmanned Aerial Vehicles (UAVs), and their supporting infrastructure. This UAS, which was used in a number of environmental research experiments focused on autonomous remote sensing, detection, classification, and management of invasive species, weeds, in Australia.

The annual cost of weeds to the Australian economy is estimated at A$4 billion. Over the last few years, experiments have been performed at three geographically distant regions of Australia to evaluate if the UAS can be used as a cost-effective tool in management of invasive species. In these experiments three distinct families of weeds, growing on three different types of terrain were investigated.

In the first group of experiments, a helicopter UAV equipped with a high-resolution imaging payload was flown over difficult to reach water channels and wetlands for detection of aquatic weeds. The second set of experiments was performed in large, relatively flat rangelands to map woody weed infestations. A low-flying fixed-wing UAV platform was also operated over a designated cattle grazing area and collected high-resolution aerial imagery. Weed infestation maps were produced from aerial imagery using machine learning techniques. By incorporating the human subject matter experts and farmers into the decision-making process, weed management plans produced. An autonomous helicopter was then tasked with spraying herbicides on aquatic weeds and dispensing granular herbicides on top of the selected woody weeds. The third set of experiments was focused on the airborne detection of wheel cacti on remote mountainous terrain using fixed-wing aircraft. Cacti infestation maps were generated and compared with data collected by weed experts on the ground. Successful results of these experiments are encouraging and suggest that robotic aircrafts in a properly designed UAS can play an important role in environmental robotic science.


Global Position System Data Aquatic Weed Unman Aircraft System Aerial Imagery Above Ground Level 
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.



This work is supported in part by the Australian Centre for Field Robotics (ACFR) funded by the New South Wales State Government and Land & Water Australia (LWA) as a part of the “Defeating the Weed Menace” (DWM) program; by Meat and Livestock Australia (MLA) under project code B.NBP.0474; “UAV Surveillance Systems for the Management of Woody Weeds,” the Australian Weeds Research Council (AWRC) under project code AWRC08-04; the ARC Centre of Excellence program and Linkage Project LP0989291, funded by the Australian Research Council (ARC); and the New South Wales State Government. Authors express their appreciation to Judy Lambert, DWM program Coordinator; Andrew Petroeschevsky, National Aquatic Weeds Coordinator, NSW Department of Primary Industries, Grafton Agricultural Research & Advisory Station; Luke Joseph, Farm & Dam Control Pty Ltd: and SunWater for their invaluable advice. This project would not be possible without the dedicated work of Mitch Bryson, Calvin Hung, Alistair Reid, Nick Lawrence and Zhe Xu, and the support of ACFR's Aerospace Group members, particularly without the state-of-the-art engineering support from the team of Jeremy Randle, Steve Keep, and Muhammad Esa Attia.


  1. T.R. Brinkley, M. Bomford, Agricultural Sleeper Weeds in Australia What Is the Potential Threat? (Bureau of Rural Sciences, Kingston, 2002)Google Scholar
  2. M. Bryson, S. Sukkarieh, Detecting Cacti – by using unmanned aerial vehicles and innovative classification algorithms, vol. RIRDC publication no 11/018, RIRDC Project No AWRC 08-04, 2011aGoogle Scholar
  3. M. Bryson, S. Sukkarieh, UAV Surveillance Systems for the Management of Woody Weeds (Meat & Livestock Australia Limited, Locked Bag 991, North Sydney, 2011b)Google Scholar
  4. M. Bryson, A. Reid, C. Hung, T. Abuhashim, S. Sukkarieh, Using unmanned aerial vehicles for mapping, classification and monitoring of invasive weeds, in International Symposium on Remote Sensing of the Environment (ISRSE), Sydney, 2011aGoogle Scholar
  5. M. Bryson, S. Sukkarieh, A.H. Göktoǧan, J. Randle, M.E. Attia, S. Keep, A. Reid, C. Hung, T. Abuhashim, Z. Xu, N. Lawrance, T. Lupton, A. Kassir, J.J. Chung, G. Brooker, N. Tahir, Robotic aircraft for remote sensing of the environment. Paper presented at the workshop on robotics for environmental monitoring at the IEEE/RSJ international conference on intelligent robots and systems (IROS), San Francisco, 2011bGoogle Scholar
  6. J.C.B. Christopher, A tutorial on support vector machines for pattern recognition. Data Min. Knowl. Discov. 2(2), 121–167 (1998). doi:10.1023/a:1009715923555CrossRefMathSciNetGoogle Scholar
  7. K.L.B. Cook, The silent force multiplier: the history and role of UAVs in warfare, in Aerospace Conference, Big Sky (IEEE, 2007), pp. 1–7Google Scholar
  8. T.H. Cox, C.J. Nagy, M.A. Skoog, I.A. Somers, Civil UAV capability assessment (Draft Version). NASA, 2004Google Scholar
  9. D.C. Cunningham, C.B. Simon, G. Woldendorp, M.B. Burgess (2004) A framework for prioritizing sleeper weeds for eradication. Weed Technol. 18(ArticleType: research-article/Issue Title: Invasive Weed Symposium/Full publication date: 2004/Copyright c 2004 Weed Science Society of America):1189–1193CrossRefGoogle Scholar
  10. M. Dunbabin, L. Marques, Robots for environmental monitoring: significant advancements and applications. IEEE Robot. Autom. Mag. 19(1), 24–39 (2012). doi:10.1109/mra.2011.2181683CrossRefGoogle Scholar
  11. W.D. Eldon, G.F. Lemmer, Origins of aerial crop dusting. Agric. Hist. 39(3), 123–135 (1965)Google Scholar
  12. J. Everitt, R. Fletcher, H. Elder, C. Yang, Mapping giant salvinia with satellite imagery and image analysis. Environ. Monit. Assess. 139(1), 35–40 (2008). doi:10.1007/s10661-007-9807-yCrossRefGoogle Scholar
  13. A.H. Göktoǧan, S. Sukkarieh, Distributed simulation and middleware for networked UAS. J. Intell. Robot. Syst. 54(1–3), 331–357 (2009). doi:
  14. A.H. Göktoǧan, S. Sukkarieh, M. Bryson, J. Randle, T. Lupton, C. Hung, A rotary-wing unmanned air vehicle for aquatic weed surveillance and management. J. Intell. Robot. Syst. 57(1), 18 (2010). doi:10.1007/s10846-009-9371-5Google Scholar
  15. G.C. Grigg, A.R. Pople, L.A. Beard, Application of an ultralight aircraft to aerial surveys of kangaroos on grazing properties. Wildl. Res. 24, 359–372 (1997)CrossRefGoogle Scholar
  16. S.R. Herwitz, L.F. Johnson, J.C. Arvesen, R.G. Higgins, J.G. Leung, S.E. Dunagan, Precision agriculture as a commercial application for solar-powered unmanned air vehicles, in AIAA's 1st Technical Conference and Workshop on Unmanned Aerospace Vehicles, Portsmouth, 20–23 May 2002, pp. 2002–3404Google Scholar
  17. Holm LGDLPea, Center E-W, The World's Worst Weeds: Distribution and Biology, vol. xii (Published for the East-West Center by the University Press of Hawaii, Honolulu, 1977)Google Scholar
  18. C. Huang, L.S. Davis, J.R.G. Townshend, An assessment of support vector machines for land cover classification. Int. J. Remote Sens. 23(4), 725–749 (2002). doi:10.1080/01431160110040323CrossRefGoogle Scholar
  19. C. Hung, M. Bryson, S. Sukkarieh, A novel vision-based tree crown and shadow detection algorithm using imagery from an unmanned airborne vehicle, in 15th Australian Remote Sensing & Photogrammetry Conference (ARSPC), Alice Springs, 2010, p. 12Google Scholar
  20. C. Hung, M. Bryson, S. Sukkarieh, Multi-class predictive template for tree crown detection. ISPRS J. Photogramm. Remote Sens. 68(0), 170–183 (2012). doi:10.1016/j.isprsjprs.2012.01.009CrossRefGoogle Scholar
  21. C. Hung, M. Bryson, S. Sukkarieh, Vision-based shadow-aided tree crown detection and classification algorithm using imagery from an unmanned airborne vehicle, in 34th International Symposium on Remote Sensing of Environment (ISRSE), Sydney, 2011Google Scholar
  22. F. Körner, R. Speck, A.H. Göktoǧan, S. Sukkarieh, Autonomous airborne wildlife tracking using radio signal strength, in The IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Taipei, 18–22 Oct 2010, pp. 107–112Google Scholar
  23. F. López-Granados, Weed detection for site-specific weed management: mapping and real-time approaches. Weed Res. 51(1), 1–11 (2011). doi:10.1111/j.1365-3180.2010.00829.xCrossRefGoogle Scholar
  24. A. Lucieer, S. Robinson, D. Turner, Using an unmanned aerial vehicle (UAV) for ultrahigh resolution mapping of antarctic moss beds, in 15th Australian Remote Sensing & Photogrammetry Conference (ARSPC), Alice Springs, 2010, p. 12Google Scholar
  25. MLA, Weed control takes to the skies (Episode 12). MLA (2010), v=LhBGyURY3do. Accessed 12 Mar 2012
  26. Nebiker, S. Annen, A. Scherrer, M. Oesch, D. A light-weight multispectral sensor for micro UAV - opportunities for very high resolution airborne remote sensing. In proceedings of XXI ISPRS congress, In International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences; Beijing, China, 2008; vol. 37, pp. 1193–1200Google Scholar
  27. NRMMC, The Australian weeds strategy: a national strategy for weed management in Australia (Natural Resource Management Ministerial Council, Canberra, 2007). Accessed from
  28. I. Nuberg, B. George, R. Rei, Agroforestry for Natural Resource Management (CSIRO Publishing, Collingwood, 2009)Google Scholar
  29. R. Pash, Chopper weed. Contours Australian Government, Department of Agriculture, Fisheries and Forestry (2007)Google Scholar
  30. G.P.J. Patrick, D.C. Agnew, D. Cooke, A model for state wide co-ordinated management of invasive cacti, in 17th Australasian Weeds Conference, Christchurch, 2010, pp. 287–290Google Scholar
  31. A. Rango, A. Laliberte, C. Steele, J.E. Herrick, B. Bestelmeyer, T. Schmugge, A. Roanhorse, V. Jenkins, Research article: using unmanned aerial vehicles for rangelands: current applications and future potentials. Environ. Pract. 8(03), 159–168 (2006). doi:10.1017/S1466046606060224CrossRefGoogle Scholar
  32. A. Reid, F. Ramos, S. Sukkarieh, Multi-class classification of vegetation in natural environments using an unmanned aerial system, in IEEE International Conference on Robotics and Automation Shanghai International Conference Center, Shanghai, 9–13 May 2011Google Scholar
  33. G.R. Sainty, S.W.L. Jacobs, Waterpants in Australia, 4 edn. (Sainty and Associates Pty. Ltd., Sydney, 2003)Google Scholar
  34. J. K. Scott, K. Batchelor, N. Ota and P. Yeoh, Sleeper and alert weeds: where will they awaken as climate changes, Land & Water Australia, 2009, p. 4Google Scholar
  35. J. Sinden, R. Jones, S. Hester, D. Odom, C. Kalisch, R. James, O. Cacho, The economic impact of weeds in Australia: report to the CRC for Australian Weed Management/ by Jack Sinden . . . [et al.]. CRC for Australian Weed Management technical series no. 8 (CRC for Australian Weed Management, Glen Osmond, 2004). Accessed from
  36. P.W. Singer, Wired for War: The Robotics Revolution and Conflict in the Twenty-First Century (Penguin, New York, 2009)Google Scholar
  37. S. Sukkarieh, Cost-Effective Surveillance of Emerging Aquatic Weeds Using Robotic Aircraft (Lands & Water Australia, Australian Centre for Field Robotics, Sydney, 2008)Google Scholar
  38. S. Sukkarieh, Aquatic weed surveillance using robotic aircraft, Land & Water Australia, 2009, p. 8Google Scholar
  39. S. Sukkarieh, Thinking bush: what do you get when you strap a rotor to a weed controller? Land and Water Australia, 8, 40–41, 2009Google Scholar
  40. S. Sukkarieh, Terrestrial and aquatic weed detection using robotic aerial systems. Paper presented at the 10th Queensland Weed Symposium, Capricorn Resort, Yeppoon, 26–29 July 2009bGoogle Scholar
  41. S. Sukkarieh, M. Bryson, A.H. Göktoǧan, M.E. Attia, S. Keep, T. Lupton, J. Randle, Cost effective surveillance of emerging aquatic weeds using robotic aircraft. ACFR (2009), Accessed 12 Mar 2012
  42. M. Trebar, N. Steele, Application of distributed SVM architectures in classifying forest data cover types. Comput. Electron. Agric. 63(2), 119–130 (2008)CrossRefGoogle Scholar
  43. V.N. Vapnik, The Nature of Statistical Learning Theory. Statistics for Engineering and Information Science, 2nd edn. (Springer, New York, 2000)CrossRefzbMATHGoogle Scholar
  44. J.G. Virtue, R.H. Groves, F.D. Panetta, Weed Risk Assessment (CSIRO Publishing, Collingwood, 2001)Google Scholar
  45. A.C. Watts, J.H. Perry, S.E. Smith, M.A. Burgess, B.E. Wilkinson, Z. Szantoi, P.G. Ifju, H.F. Percival, Small unmanned aircraft systems for low-altitude aerial surveys. J. Wildl. Manage. 74(7), 1614–1619 (2010)CrossRefGoogle Scholar
  46. C. Yang, J.H. Everitt, Comparison of hyperspectral imagery with aerial photography and multispectral imagery for mapping broom snakeweed. Int. J. Remote Sens. 31(20), 5423–5438 (2010). doi:10.1080/01431160903369626CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2015

Authors and Affiliations

  1. 1.Australian Centre for Field Robotics (ACFR), School of Aerospace, Mechanical & Mechatronic Engineering (AMME)The University of SydneySydneyAustralia

Personalised recommendations