Agriculture

Agriculture, aquaculture and bio-monitoring

 

Agricultural Portfolio Lead Tristan Perez

 

There is a labour vacuum in food production. Employment in agriculture, which used to provide almost all the jobs in the pre-modern era, now accounts for only 2% of employment in the first world. With a world population projected to reach almost 9 billion by 2050, sustainability and food security worldwide are significant challenges. Australia, in particular, faces a real challenge to ensure its participation in food production is both competitive and sustainable. We need robots to enhance agricultural productivity and to achieve sustainable production of food with less land, lower inputs and fewer famers. Robotic technology will soon have a significant impact on agricultural practices.

Our vision is to develop and fast track farm robotic technology that will reinvigorate productivity through increased production and reduced costs. The Strategic Investment in Farm Robotics (SIFR) program is funded by Queensland’s Department Agriculture and Fisheries (QDAF), and it is part of the Australian Centre for Robotic Vision at QUT. Such technology can be used to conduct autonomous multi-vehicle operations in applications of weed management, fertilising, and seeding. The use of multiple, relatively low cost, field robots can enable novel alternative weed destruction methods based, for example, on mechanical and thermal principles rather than herbicides. Such advances could reduce the input cost for weed management in terms of energy, labour, and improved chemical delivery by up to 40%. The robots will also have the capability to communicate, not only with each other, but also with unmanned aircraft and operations managers in order to combine different kinds of environmental and field information. Our robots will be equipped with sensors for navigation and crop data collection. We will use sophisticated algorithms for data-fusion to extract information from the sensor data, allowing us to use low-cost sensors, such as cameras, and yet obtain high accuracy in robot localisation and navigation. Cameras can be used to navigate, detect and avoid obstacles, and also for weed detection and classification as well as to control variable rate technology in herbicide application.

As well as being used for tasks related to field and crop management, robots enable new management practices and data collection, which will lead to advances in the field of precision agriculture. When data collection is combined with an appropriate digital infrastructure, the result can be more refined site-specific crop management leading to increased performance and robustness of crop agricultural enterprise systems. This will optimise productivity (increase of yield and quality) and profitability (optimising the return on investment in energy, water, and labour), while maintaining performance (reduce volatility) in the face of climate variability, incomplete information, market movements and other threats that may be biophysical or socio-economic.

 

Agricultural application CASE STUDY

 

Indian Prime Minister meets AgBot II during the G20 Summit

 

 

Modi_signing_agbot

Indian Prime Minister, Narendra Modi, writes a message on AgBot II

 

n November 2014, Brisbane hosted the G20 Leaders Summit, the principle forum for international economic cooperation. An annual event, the G20 is an opportunity for world leaders to meet and share ideas to address key international issues.
Among the dignitaries in Brisbane was the tech-savvy Indian Prime Minister Narendra Modi, who visited QUT to meet with Centre researchers working in agricultural robotics.

With the agriculture industry in transition, many modern farmers are using digital networks, sensors and autonomous devices for many agricultural functions including planting, harvesting, sorting, packaging and boxing.

Lead researcher, ACRV AI Tristan Perez says that the farm of the future will be supplied with lightweight, small, autonomous and energy efficient machines called AgBots. Each AgBot will perform a particular task but will work together to weed, fertilise, control pests and diseases, all working while collecting valuable data that can be analysed to improve farming practices.

“We are starting to see automation in agriculture for single processes such as animal and crop monitoring using unmanned aerial vehicles (drones), robotic weed management, autonomous irrigation,” he said. “There is enormous potential for AgBots to be combined with sensor networks and unmanned drones to provide farmers with large amounts of data, which then can be combined with mathematical models and novel statistical techniques (big data analytics) to extract key information for management decisions — not only on when to apply herbicides, pesticides and fertilisers but how much to use and where.”

Peter Corke, Director of the ACRV, and Tristan met with Prime Minister Modi to brief him on the latest development, the second generation AgBot II.
AgBot II is being developed for broad acre weeding and fertilising, and is part of a larger project funded by QDAF.

Tristan told Mr Modi that the new AgBot II would autonomously seed, weed and fertilise with trials starting in 2015.

“We have done an economic analysis for weed management that anticipates a reduction of costs of up to 40 per cent in terms of energy, labour and chemical savings,” Tristan said.

Looking to ensure India’s future food security Mr Modi is a strong advocate and supporter of agricultural research and development, particularly in the area of agricultural technologies.

Asked to write a message on the robot, Mr Modi wrote (translated from Gujarati):
“Research is the mother of invention. The development journey of mankind is a continuous stream of research. Science and technology is very important for agriculture. Agricultural scientists rely heavily on science and technology. Agricultural progress is very important for the welfare of humanity. I congratulate you for your efforts here and wish you the best. Narendra Modi”

 

AgBot II

Agbot II is an agricultural robot  developed at the Queensland University of Technology for weed and crop management in broadacre as well as horticulture applications.

PN001 - Complete Vehicle_v17.19
The agricultural robot (AgBot II) shown below has been developed at QUT. This robot is 2m long by 3m wide, and 1.4 m height – all dimensions can be adjusted. Such a robot can conduct autonomous multi-vehicle operations in applications of weed management, fertilising, and seeding. The robots may also have the capability to communicate not only with each other, but also with unmanned aircraft and the operation manager in order to combine different kinds of environment and field information.  The robots are equipped with sensors for navigation and crop data collection. Sophisticated algorithms for data-fusion are used to extract information from the data of various sensors. This allows the use of cheap sensors and yet obtain high accuracy in robot localisation and navigation.

Cameras can not only be used to navigate, but also to conduct image processing for detection and avoidance of obstacles during both day and night operations. This may potentially result in the suppression of expensive radar and laser ranger sensors, as well as real-time-kinematic satellite navigation sensors as computer-vision-based detect and avoid technology improves in the future. Cameras can also be used for weed detection and classification as well as to control variable rate technology in herbicide application.

The use of multiple vehicles results in lower-speed operations conducted at 5 to 10km/h. This can enable novel alternative weed destruction methods based, for example, on mechanical and thermal principles. Research on these technologies, which at some point in the past was abandoned due to the cheap and efficient use of agrochemicals,  is currently on the rise due to the increasing resistance that some weeds present to herbicides. Robots moving at lower speeds and with the ability to use vision as to enable detection, classification, and manipulation of weeds is opening new opportunities to alternative weed destruction methods. A recently developed economic model shows improvements in the range of 40% in the reduction of input cost for weed management in terms of energy, labour, and improved chemical delivery.

Having robot platforms operating in the field can also be used to collect data to improve precision agriculture. When this is combined with an appropriate digital infrastructure, data analytics, and algorithms for complex decision making under uncertainty, the result can be more refined site-specific crop management leading to an increased performance and robustness of crop agricultural enterprise systems. Performance in this context relates to the optimisation of productivity (increase of yield and quality) and profitability (optimising the return on investment in energy, water, and labour). Robustness relates to maintaining performance (reduce volatility) in the face of climate variability, incomplete information, market movements and other threats that may be biophysical or socio-economic.

 

AgBot III:

Agricultural robot  developed at the Queensland University of Technology for weed and crop management in broadacre as well as horticulture applications.

PN001 - Complete Vehicle_v17.21

 

The Strategic Investment in Farm Robotics (SIFR) is a program supported by the Queensland’s Department Agriculture, Fisheries, and Forestry (QDAFF)

SIFR_Logo_without Sub-text_v1 Qld CoA Stylised 1L mono

 

For details contact

Professor Tristan Perez – Leader Strategic Investment in Farm Robotics Program

Electrical Engineering and Computer Science

Queensland University of Technology

phone: + 61 7 3138 9076

email: tristan.perez@qut.edu.au

 

Research Team

– Prof Tristan Perez (Program Leader and lead researcher system dynamics and control),
– A/Prof Ben Upcroft (Program Deputy Leader and researcher robotic vision),
– Dr David Ball (Lead vehicle design),
– Dr Christopher McCool (Lead robotic Vision),
– Dr Christopher Lehnert (Lead manipulation),
– Ray Russel (Lead mechanical design),
– Dr Jason Kulk (Lead software/electronics design),
– Prof Paul Hyland (Associated researcher – economic modelling)
– Prof Margot Brereton (Associated Researcher – Robot-human Interaction)
– Dr Thierry Peynot (Associated research – multi-mode sensing)
– Dr Feras Dayoub (Associated research – robotic vision)
– Dr Felipe Gonzalez (Associated research – UAV remote sensing)
– Dr Inkyu Sa (Associated research)
– Owen Bawden (RHD student – industrial design),
– David Hall (RHD Student – robotic vision)
– Andrew English (RHD student – navigation)
– Patrick Ross (RHD student – navigation)
– Brad Dranko (Research Assistant)
– Ben Hutchins (Research Assistant – economic modelling)
– Shawn Perkins (Research Assistant)
– Jack Slater (Research Assistant)

Name Location Role
Zongyuan GeQUTPhD Candidate
Zhibin LiaoUniversity of AdelaidePhD Candidate
Zetao “Jason” ChenQUTPhD Candidate
Yuchao JiangUniversity of AdelaidePhD Candidate
Yi “Joey” ZhouANUPhD Candidate
Yasir LatifUniversity of AdelaideResearch Fellow
Yan ZouMonashPhD Candidate
Xiaoqin WangMonashPhD Candidate
Will ChamberlainQUTPhD Candidate
Viorela IlaANUResearch Fellow
Vincent LuiMonashPhD Candidate
Vijay KumarUniversity of AdelaideResearch Fellow
Trung Than PhamUniversity of AdelaideResearch Fellow
Tristan PerezQUTAssociate Investigator
Tracy KellyQUTFinance & Administration Officer
Tong ShenUniversity of AdelaidePhD Candidate
Tom DrummondMonash UniversityChief Investigator
Tim MacugaQUTCommunications and Media Officer
Thuy MaiUniversity of AdelaideNode Administration Officer
Thanuja DharmasiriMonashPhD Candidate
Tat-Jun ChinUniversity of AdelaideAssociate Investigator
Sue KeayQUTChief Operating Officer
Stephen GouldANUChief Investigator
Sourav GargQUTPhD Candidate
Sean McMahonQUTPhD Candidate
Sareh ShiraziQUTResearch Fellow
Sarah AllenQUTNode Administration Officer, PA to Centre Director Professor Peter Corke
Ruth SchulzQUTResearch Fellow
Ross CrawfordQUTAssociate Investigator
Rodrigo Santa CruzANUPhD Candidate
Rob MahonyANUChief Investigator
Richard HartleyANUChief Investigator
Riccardo SpicaANUPhD Candidate
Qinfeng ShiUniversity of AdelaideAssociate Investigator
Philip TorrOxfordPartner Investigator
Peter KujalaQUTPhD Candidates
Peter CorkeQUTCentre Director
Peter AndersonANUPhD Candidate
Paul NewmanOxfordPartner Investigator
Niko SuenderhaufQUTResearch Fellow
Mike BradyOxfordCentre Advisory Committee
Michelle SimmonsUNSWCentre Advisory Committee
Michael MilfordQUTChief Investigator
Matt DunbabinQUTAssociative Investigators
Markus EichQUTResearch Fellow
Marc PollefeysETH ZurichPartner Investigator
Mandyam SrinivasanUniversity of QueenslandCentre Advisory Committee
Luis Mejias AlvarezQUTAssociate Investigator
Lin WuUniversity of AdelaideResearch Fellow
Laurent KneipANUAssociative Investigators
Khurrum AftabMonash UniversityResearch Fellow
Kate AldridgeQUTCentre Administrative Coordinator
Juxi LeitnerQUTResearch Fellow
Juan AdarveANUPhD Candidate
Jonghyuk KimANUAssociate Investigator
Jonathan RobertsQUTChief Investigator
John SkinnerQUTPhD Candidate
Jochen TrumpfANUAssociate Investigator
Jeffrey DevarajQUTPhD Candidate
Jason FordQUTAssociate Investigator
Jae-Hak KimUniversity of AdelaideResearch Fellow
Inkyu SaQUTResearch Fellow
Ian ReidUniversity of AdelaideDeputy Director
Hui LiUniversity of AdelaidePhD Candidate
Hugh Durrant-WhyteUniversity of SydneyCentre Advisory Committee
Hongdong LiANUChief Investigator
Gustavo CarneiroUniversity of AdelaideChief Investigator
Guosheng LinUniversity of AdelaideResearch Fellow
Greg LeeQUTExternal Engagement Coordinator
Gordon WyethQUTChief Investigator
Frank DellaertOxfordPartner Investigator
Francois ChaumetteInriaPartner Investigator
Feras DayoubQUTResearch Fellow
Fatih PorikliANUAssociate Investigator
Fangyi ZhangQUTPhD Candidate
Fahimeh RezazadeganQUTPhD Candidate
Edison GuoANUPhD Candidate
Donald DansereauQUTResearch Fellow
Dinesh GamageMonashResearch Fellow
David SuterUniversity of AdelaideAssociate Investigator
David HallQUTPhD Candidate
David BallQUTResearch Fellow
Dan RichardsQUTPhD Candidates
Clinton FookesQUTAssociate Investigator
Chuong NguyenANUResearch Fellow
Chunhua ShenUniversity of AdelaideChief Investigator
Chris McCoolQUTResearch Fellow
Chris LehnertQUTResearch Fellow
Chris JefferyQUTPhD Candidate
Bohan ZhuangUniversity of AdelaidePhD Candidate
Ben UpcroftQUTChief Investigator
Ben TalbotQUTPhD Candidate
Ben MeyerMonashPhD Candidate
Ben HarwoodMonashPhD Candidate
Basura FernandoANUResearch Fellow
Anton Van Den HengelUniversity of AdelaideChief Investigator
Anthony DickUniversity of AdelaideAssociate Investigator
Anoop CherianANUResearch Fellow
Anjali JaiprakashQUTResearch Fellow
Andrew SpekMonashPhD Candidate
Andrew EnglishQUTPhD Candidate
Andrew DavisonImperial College LondonPartner Investigator
Andres Felipe Marmol VelezQUTPhD Candidate
Anders ErikssonQUTResearch Fellow
Alex ZelinskyDefence Science and Technology OrganisationCentre Advisory Committee
Ajay PandeyQUTResearch Fellow
Ahmet SekerciogluMonash UniversityAssociate Investigator
Adam TowQUTPhD Candidate
Adam JacobsonQUTPhD Candidate