All posts by LandWISE Admin

Automation, LandWISE 2015, LandWISE People, Precision Agriculture, Sensing, Tillage

Robotics and Intelligent Systems to Improve Land and Labour Productivity

Leave a comment

LandWISE 2015 Presenter, Robert Fitch

RobertFitch2

Robert Fitch and Salah Sukkarieh
Australian Centre for Field Robotics
School of Aerospace, Mechanical and Mechatronic Engineering
The University of Sydney, NSW Australia

Food production in the 21st century must respond to significant new pressures to increase quantity and nutritional quality. Because natural resources are limited, achieving such goals must involve improvements in production efficiency. At the same time, we must engage in environmental stewardship, contend with the rising cost and diminishing availability of human labour, and reverse the steady decline in the number of farmers worldwide.

Meeting these challenges will require major innovations in technology, farming systems, and operations enabled by advances in robotics and automation.

One of the leaders in agricultural robotics research is the Australian Centre for Field Robotics (ACFR) at The University of Sydney, recognised as one of the largest field robotics groups in the world. We conduct research using both ground and aerial robots that is helping to shape the future of farms.

Our collaboration with Queensland University of Technology (QUT) and start-up company SwarmFarm addresses the issue of soil structure damage from ever-larger tractors and implements by replacing a single large soil-compacting vehicle with many small vehicles that move lightly across the surface without compacting the soil or disturbing its protective top layer.

The Ladybird robot designed by the University of Sydney
The Ladybird robot designed by the University of Sydney

The potential for robot teams is also strong in integrated weed management strategies. The Ladybird is a prototype we designed and fabricated for the vegetable industry, supported by AusVeg. Beneath the outer shell is a manipulator arm that can be used to position a variety of implements for weed control, such as tines, microwave, grit-blasting, and steerable targeted spray.

The problem of detecting individual weeds is one part of our general framework for crop intelligence, where robots perform autonomous farm surveillance (mapping, classification, detection) for crop growth and health.

SydneyRobots
Two ground robots and one aerial robot used in tree crops supported by Horticulture Innovation Australia Ltd.

The farm of the future will not simply replace manual operation with autonomous operation, but instead will adopt a systems view that coordinates all activities and draws more people into farming.

Whole-farm optimisation can be seen as ‘thinking beyond the robot’ to restructure farm operations in terms of the timing and logistics of all activities, where individual crop elements have a ‘personality’ that is accurately tracked over the crop lifecycle.

The ACFR has a long history of working in large-scale operations and optimisation with various industry partners and are now beginning to apply the resulting successful methodologies to the agriculture domain.

 

 

 

Agronomy, Automation, LandWISE 2015, Precision Agriculture, Sensing

Instruments for Crop Quality Measurement

LandWISE 2015 Presenter Peter Schaare

PeterSchaarePeter Schaare, Bio-engineering, Plant & Food Research.

Peter specialises in designing measuring instruments for biological applications including non-destructive measurement technologies, optical instrumentation, spectroscopy, ultrasonics and automation. He is currently investigating laser technologies to assess the mineral nutrient status of plant material in the field.

The key to precise management of crops is the provision of timely and spatially detailed information on the factors determining yield and quality.  Instrumentation already exists to evaluate some of these factors; for example, yield monitors, nitrogen level sensors and electromagnetic soil mapping are in common use.  However, in-field, real-time measurement of other factors is proving challenging.  Peter’s presentation covers some types of instrumentation that may provide the key to more detailed information on the factors determining plant production.

Examples include thermal imaging of the surface temperature of leaves in the canopy to identify stress from water shortage or disease, LiDAR to estimate traits such as biomass, leaf area and height and visible-near infrared spectroscopy (VIS-NIR) which has been shown to be able to estimate soil pH via a tractor-mounted soil penetrator.

Plants emit particular volatiles when under attack by pests such as herbivores or fungi, or as a normal component of their metabolism and these volatiles can be used to diagnose the plant’s status. Which technology is a superbly sensitive technique?

Instruments and measurement are the key to precise management of horticultural and arable crop production systems and the farmer of 2030 will routinely use measurement technologies to guide his operations to an even greater extent than is done today.

plantandfood_logo1

Automation, LandWISE 2015, LandWISE People, Precision Agriculture, Sensing

Technology Transfer to the Primary Sector

LandWISE 2015 Presenters Mark Burgess and  Bruce MacDonald

MarkBurgess UoA
Mark Burgess
BruceMacDonald
Bruce MacDonald

 

 

 

 

 

New Zealand’s national goals increasing primary sector exports require a significant investment in new technologies that radically optimise resource usage and mitigate impacts associated with sector intensification.  Crucially they need to be technologies that will be adopted by the primary sector.

The University of Auckland has been embracing the associated
technology challenges through a strategy that links its strengths in
life sciences, engineering, chemistry, physics and ICT with the
well-established agricultural and horticultural research institutes
throughout New Zealand and adopting a proactive approach to connecting its scientists and engineers to these sectors and their issues.

For example, ubiquitous work in UAV systems, robotics and automation technologies is now being directed to agritech issues such as pasture management and pollination.

This presentation will cover the strategies implemented to create an
agricultural lens for city scientists and present some case studies of
the research programmes being undertaken. We will present our view on the drivers for adoption.

Associate Professor Bruce MacDonald completed a BE (1st class) and Ph.D in the Electrical Engineering department of the University of Canterbury.  Bruce worked with NZ Electricity and the DSIR in Wellington, NZ, then the Computer Science Department of the University of Calgary in Canada. In 1995 he joined the Department of Electrical and Computer Engineering at the University of Auckland.

His long term goal is to design intelligent robotic assistants that improve the quality of peoples’ lives, with primary research interests in human robot interaction and robot programming systems, and applications in areas such as healthcare and agriculture.

He is the director of the department’s robotics group and a leader for the multidisciplinary CARES robotics team at the University of Auckland. He is the leader of Faculty of Engineering research theme Technology for Health, and Chairman for NZ’s robotics, automation and sensing association.

Bruce is part of a research team to develop modular robots for horticulture.  The Autonomous Multipurpose Mobile Platform (AMMP) modular robot is capable of navigating autonomously in orchards and will include vision-sensing of flowers and fruit for kiwifruit and apples in orchards and arms and grippers for harvesting kiwifruit and apples as well as fast-acting directional control mechanisms for precision targeted spraying of pollen and soft robotic handling of apples and kiwifruit.

The ‘Multipurpose Orchard Robotics’ project is a four year collaboration between Robotics Plus Ltd, University of Auckland, University or Waikato and Plant and Food Research aiming to automate the harvesting and pollination of kiwifruit and apples. (C) RoboticsPlus
The ‘Multipurpose Orchard Robotics’ project is a four year collaboration between Robotics Plus Ltd, University of Auckland, University or Waikato and Plant and Food Research aiming to automate the harvesting and pollination of kiwifruit and apples. (C) RoboticsPlus

The research is a collaboration between Plus Group’s RoboticsPlus Ltd, the University of Auckland, Plant and Food Research, and the University of Waikato.

Automation, LandWISE 2015, Precision Agriculture, Sensing

Grape Vine Pruning Robot

LandWISE 2015 Presenter Tom Botterill

Tom Botterill
Tom Botterill, Research Fellow, Department of Computer Science, University of Canterbury.

Tom described advances in developing a viable grape vine pruning robot.  This work is through the MSI-funded project on “Vision Based Automated Pruning”.  Tom’s research interests include 3D reconstruction and modelling using computer vision.

Grape vines must be pruned every year in order to increase yield, prevent disease, and control excess growth. While some simple mechanical pruning systems are available, most of New Zealand’s winegrowers prefer to prune vines manually, even though hand-pruning is often the most expensive task in the vineyard.

To hand-prune a vine, the healthiest canes are selected and the rest are removed. For a robot to prune vines in this way, it must understand the 3D structure of the plant, it must be able to decide which canes to keep or remove, and it must be able to make the required cuts without damaging other canes.

Cane pruning a vine requires detailed recognition and selection
Cane pruning a vine requires detailed recognition and selection

A team at the University of Canterbury are developing just such a robot system. The system is mounted on a platform which straddles the vines and moves along the row, pruning as it goes. The robot uses three high resolution digital cameras to image the vines, then uses computer vision algorithms to make a 3D model of the vine from these images.

Given these vine models, an artificial intelligence system decides which canes to keep and which to cut. The artificial intelligence was “trained” to make good pruning decisions by providing it with examples of how pruning experts prune vines. To prune the vines, a six-jointed robot arm reaches amongst the canes and makes the required cuts with a spinning cutting tool.

The major technical challenges in the current system were building a 3D model of the complex vine structure, then reaching to cut the vines while the platform moves. After four years of development, the 3D models are finally complete and correct enough to make decisions about where to prune, however the dynamic robot arm control is still under development, so the robot must stop at each plant to make the cuts.

Our system has been made possible by rapid advances in computer vision and robot technology over the last decade, and it is close-to-working despite being far from the simplest way to automate pruning. The algorithms and techonology are now available to automate many harvesting, pruning and precision-agriculture tasks, and there are now no technical barriers to seeing all of these tasks automated out in the field.

This project is funded by MBIE and is a partnership between the University of Canterbury, NZ Winegrowers, Pernot Ricard NZ, Scott Technology, Lincoln University and the University of Otago.

Tom’s publications and more information: http://hilandtom.com/tombotterill/

Agronomy, Automation, LandWISE 2015, Precision Agriculture, Soil, Tillage

Tulloch Farm Machines

GoldTulloch Farm Machines will demonstrate their  Oekosem Rotor Strip-Tiller and Monosem NG Plus 4 planter combination at “The Farm of 2030” LandWISE Conference. 

Oekosem Rotor Strip-Tiller and Monosem Planter
Oekosem Rotor Strip-Tiller and Monosem Planter

The Oekosem Strip Tiller is a  Swiss product manufactured by Baertschi. Nick Gillot says it’s all about creating an optimal seedbed in rows, minimizing soil erosion and operating costs and simultaneously securing earnings over the long term.

Nick says the metering unit is a major component of the Monosem planter. With the new NG Plus 4 model, Monosem has conserved the the best of the NG Plus units and has added the operating comfort. Nick says adjustments are made easier so the planter can be perfectly adjusted to conditions to get optimal planting.

The machine was operating at the LandWISE MicroFarm Field Session on Day 2 of the Conference. The area put aside for the demonstration was in long term grass that had not been sprayed out – it was a good test.

More about “The Farm of 2030” Conference here>

Thanks to our Platinum Sponsors

Platinum

Agronomy, Automation, Drainage, Irrigation, LandWISE 2015, LandWISE People, MicroFarm, Nutrients, Precision Agriculture, Projects, Sensing, Soil

More adequate or less better sensor arrays and wireless networks

LandWISE 2015 Presenter – Gert HattinghInstalling the WINTEC wireless soil moisture sensor array
Installing the WINTEC wireless soil moisture sensor array

Gert Hattingh is Industry Research Champion at the Waikato Institute of Technology in Hamilton.

Gert’s current work involves finding ways to build more sustainable and energy efficient homes, finding better ways for the normal household to live sustainably, and evaluating new technologies.

Gert says the most burning question in any business venture is whether your actions will cost you money, or make you money.  Any decision you make in the production, marketing or operational sphere has an influence on this statement.  This paradigm has been a design key since Wintec have ventured into producing cost effective sensor arrays and wireless networks.

In the modern measurement world, there are three cost drivers – quality of the sensor(s), the cost of the network carrying the data, and the cost of making sense of and using the data.

Gert and colleagues started off by looking at the network and the data carrier first, and designed a generic sensor module to host and manage almost any sensor type.  They also developed a database model that would host any data from sensors, as well as the encryption and data quality protocols.

To date, their system can host the following type of sensors:  GPS, Air Humidity, Air Temperature (2 sensors), Air pressure, solar irradiation, wind speed, wind direction, soil moisture (various sensors), pH, conductivity, dissolved oxygen, oxidation-reduction potential, ammonia, CO2, methane, propane, NOX and some alcohols.

A single sensor module can carry at most thirteen sensors, with a practical thirty sensor modules per network.  This totals to 390 sensors per network.

This technology is being trialed at the LandWISE MicroFarm, gathering, transmitting and processing soil moisture information from an array of sensors.

Agronomy, LandWISE People, Precision Agriculture, Soil

Planting Precisely – John Chapman

LandWISE 2015 Presenter, John Chapman

JohnChapmanJohn Chapman is the Product Specialist for seeding and cultivation equipment at Power Farming.

John spent 15 years managing farms in Suffolk and Norfolk in the UK after graduating with an MSc in Farm Management.

His  experience with rotations involving many different crops involved many cultivation techniques, as well as a wide range of cultivators and drills to achieve quality seed beds and successful crop establishment in all sorts of conditions and soil types.

Success from precision planting does not come from one or two well made decisions but from a whole host of factors that come together to produce a successful crop.

It is critical to check all areas where the seed drops from to the point where it hits the ground that there are no points at which the seed may catch or have its trajectory affected.

Ensure that seed plates are clean and free from any grooving that has occurred. Badly grooved seed plates have the potential to be distorted and loose vacuum.  The seed needs to be of the optimum quality to singulate well. Even size and condition is essential.  Seed size directly relates to the seed plate chosen.

Forward speed is where in most cases the wheels fall off the wagon. Forward speed has a direct correlation to spacing through the planter’s ability to cope with the speed.

Although drilling depth is of vital importance for even seed germination and emergence it will be affected by the soil conditions, forward speed, varying conditions across the paddock and the state of the coulters.

Agronomy, Automation, LandWISE People, Precision Agriculture, Sensing

Robotic vision systems for real-time crop management

LandWISE 2015 Presenter – Cheryl McCarthy

Cheryl-McCarthyCheryl McCarthy is a researcher at the National Centre for Engineering in Agriculture, University of Southern Queensland based in Toowoomba.

As inputs costs continue to rise, on-farm productivity gains will come from greater sophistication in managing inputs like labour, water, chemicals and energy. Robotics is enabling the development of farming equipment and systems that can precisely sense and control to manage inputs and save labour.

NCEA is conducting a range of research projects that integrate autonomous sensing and control with on-farm operations, to robotically manage inputs within a crop. Major projects are being conducted in on-farm automation for weed spot spraying, adaptive control for irrigation optimisation, and remote crop surveillance using cameras and remotely piloted aircraft.

Cheryl is developing machine vision and sensing systems for agriculture. Machine vision-based weed detection systems have been developed for the sugar, cotton and pyrethrum industries. A Depth and Colour Segmentation process enables weed detection and a new processing technique enables the vision systems to operate at commercial ground speeds of 10-15 km/h.

Optimal irrigation strategies for overhead and surface irrigation systems are being investigated in projects for the cotton and horticultural industries. Trials in the cotton industry at sites on the Darling Downs and Central Queensland have demonstrated 10-30% water savings with 10% increase in yield, as well as labour savings, when using adaptive and automated irrigation systems which combine soil and crop monitoring sensors and variable rate applicators, together with software to calculate optimal irrigation amount.

Insufficient sampling for diseases or pests in crops and pastures can lead to misdiagnosis of the presence or level of infestation in a field, or uniform application of pesticide in a field where infestation is not distributed uniformly. Similarly, field conditions, including crop growth, water stress and weed coverage, vary spatially and require frequent monitoring to optimise management.

NCEA is developing technology that will couple rapid, field-scale data collection from RPAS with automated data and image analysis to automatically diagnose unhealthy areas of crop (see below).

3D model of cotton crop generated by RPAS and photogrammetry software
3D model of cotton crop generated by RPAS and photogrammetry software
Agronomy, Automation, MicroFarm, Precision Agriculture, Sensing, Soil

Aerial Mapping at the MicroFarm

Centre for Land and Water residents, AltusUAS are creating detailed farm and crop maps of the LandWISE MicroFarm.

Altus Unmanned Aerial Solutions specialises in the manufacture of professional UAS systems for wide-ranging applications. They build and operate systems of high specification with features including built in redundancy, custom control interfaces and integrated emergency parachute. They offer platforms with class leading flight performance as well as all-weather capabilities.

AltusMissionNDVI
An AltusUAS Quadcopter sets off on a mission to map the MicroFarm

Even a simple aerial image is highly informative – the view from above changes perception immensely!

MicroFarm fields and Green Shed meeting venue - image captured by AltusUAS
MicroFarm fields and Green Shed meeting venue – image captured by AltusUAS

At the MicroFarm, they are using their technologies to survey the site, photogrammetry to process imagery and further analysis to create a 3D model of the MicroFarm and crops.

A composite image created from many overlapped photographs taken from a GPS guided UAV - the basis for a 3D MicroFarm model
A composite image created from many overlapped photographs taken from a GPS guided UAV – the basis for a 3D MicroFarm model
A zoom-in on part of the image showing the Green Shed and corner of a crop of mustard
A zoom-in on part of the image showing the Green Shed and corner of a crop of mustard

 

View a flythough of the model (it looks like a video of the site) on YouTube here>

AltusMicroFarmVideoImage

As well as terrain models/topographic maps, they can produce detailed NDVI information.

We are using this information to understand our site in much more detail. With individual pixels as small as about 4cm, we can zoom in practically to individual leaf scale. Do we need that? Not for many applications, but it does raise new possibilities around pest and disease identification and definitely enable us to view individual plants.

To receive updates sign-up for the LandWISE E-newsletter and follow @LandWISENZ on Twitter (see the right sidebar).

Precision Agriculture

PAANZ Update

Leave a comment

LandWISE is a foundation member of the Precision Agriculture Association of New Zealand – PAANZ. Our Manager, Dan Bloomer, is a member of the PAANZ Committee which is working to build the organisation.

Dan says PAANZ has established itself, and is now developing resources to help farmers, industry, regulators and the community understand how precision agriculture can play roles increasing productivity while minimising resource use and environmental foot prints.

PAANZ has a wider coverage than the traditional LandWISE focus on cropping, viticulture and horticulture. As a pan-sector body, it aims to link industry and users across the spectrum, and to take a lead on generic issues.

The PAANZ website has a number of useful resources including case studies and news page. See more at http://www.precisionagriculture.org.nz/

PAANZ2