Category Archives: Automation

LandWISE 2017: Are we ready for automation?

In 2017 our 15th Annual Conference focuses on automated tools for data collection, decision making and doing actual tasks on the farm (and beyond).

  • What do you want?
  • What’s on offer?
  • How will farms and management have to change?

We have a comprehensive programme. We’ve gone a bit outside the box to bring a variety including from outside the horticultural and arable sectors. We find cross-pollination and hybrid vigour valuable!

So register, come along and listen to excellent presenters, discuss the ideas with colleagues and go away with new understanding and plans.

Thanks to Our Loyal Platinum Sponsors!
Many thanks to AGMARDT, sponsors of our international presenter, Thibault Delcroix, France

Hawke’s Bay Regional Council, John Deere and BASF Crop Protection are our Platinum Sponsors again in 2017. Many thanks to these loyal supporters who have backed the Conference for a number of years.

We also welcome our Gold Sponsors, meal sponsors and  trade displays new and old. These are the organisations that make conferences like this possible and affordable.

Join them and us at the Havelock North Function Centre on 24-25 May 2017 to mix with leading practitioners, farmers, growers, researchers, technology developers and providers.

Register now – click here!

 

Counting buds and berries

James Beech and Tony Cooper are data scientists and the principals of Precision AI Ltd. Tony and James will present to “LandWISE 2017: Are we ready for automation?” and discuss how machine vision and machine learning can be used to automate such things as counting buds, shoots and fruits in orchards and vineyards. 

Capturing quality imagery with changing light conditions, when your target is hiding behind leaves and you are traveling at speed on bumpy ground is quite a challenge. Identifying and quantifying the things you are interested in is a challenge as well.

What are the tools that can help? How close are we to automatically collecting this type of data?

James has over 15 years’ experience in software development, advanced analytics and data visualisation.

James specialises in open data, data infrastructures, business intelligence dashboards and predictive modelling. James is has particular interest in the application of big data through the use of statistical and analytic techniques to solve business problems. His experience spans across financial services, telecommunications and the agricultural sectors.

Tony has a distinguished track record in predictive analytics and data mining. His specialties include machine learning and computer vision. 

Tony has made exciting advances in quantitative research and received industry accolades. He holds a Bachelor of Science (Hons.) in Statistics and Computer Science from Massey University and a Master of Science in Statistics from Stanford University (USA).

Tree climbing robots in forestry

Richard Parker

Richard Parker is a Senior Scientist at Scion in Christchurch.  His research focuses on difficult, dangerous and essential occupations such as forest harvesting and rural fire fighting from the perspectives of human factors and technology.  

Richard is involved in the development of novel robots for forest operations and the human factors of forest work. He was a tree faller and breaker out in a former life.  He is also leads research on rural fire fighter performance and new technologies for fire detection and suppression and is a volunteer rural firefighter.

Delegates at LandWISE 2017: are we ready for automation? will hear Richard say that robotics is inevitable in forestry as specialised machines for forest tasks are developed.  The mining industry already has a history of robot development and automation and forestry is learning from their experience. However, forestry has particular challenges – much of the commercially forested land in New Zealand is on steep and remote terrain. 

Forest harvesting operations have been traditionally considered physically demanding and potentially dangerous, with forest workers on foot exposed to heavy and fast-moving trees, logs and machinery.  Many tasks in forestry have already been mechanised to reduce hazards to the worker and increase productivity.  For example, the axe was replaced by the chainsaw, which was replaced by the excavator based harvesting machine.  However large machines can damage the sensitive forest soils and cannot work on steep terrain where many forest grow.  This presentation will discuss the next stage of forest machine development which uses the standing trees for support.

Animals have lived in the trees for millions of years and have developed behavioural, structural and physiological adaptations to the arboreal environment.  Some animals move slowly from branch-to-branch like the stick insect.  Others, such as gibbons, can move rapidly using brachiation, engaging in the arboreal equivalent of running through the forest from branch to branch.  An opportunity exists to use this form of locomotion, although more slowly than gibbons, for the movement of forestry machinery. 

The proposed machine could always stay above ground moving from tree-to-tree using the trees for support. The machine would eliminate the problem of soil disturbance and would not be limited by terrain steepness.

Bottle Lake Trial Robot

With funding from Scion, the Ministry for Primary Industries and the Forest Growers Levy Trust, the concept of a tree-to-tree forestry machine became real.  Scion and University of Canterbury Mechanical Engineering and Mechatronics students built a working radio controlled tree-to-tree locomotion machine. Development of a real machine demonstrated that being independent of the ground makes operator control easier because the ground conditions (holes, rocks, loose soil) do not have to be adjusted for.

Soil to sprinkler, automating irrigation management

Anthony (Tony) Davoren is a Director of Aqualinc with responsibility for the HydroServices business unit that provides irrigation and environmental management services; soil moisture, and water level and water meter monitoring. 

Tony’s expertise in and knowledge of soils and hydraulic properties, irrigation systems and design, and crop water demand has been applied and enhanced over the last 35 years working in these fields.

We asked Tony to talk about automating irrigation – from the soil to the sprinkler and round again. He’s doing just that at LandWISE 2017: Are we ready for automation?

Tony says several questions need to be asked and honest answers or solutions given:

  • Are we and you ready?
  • What do we need?
  • Is automating irrigation management wise or the right solution?

Are we or you ready?

When considering automating irrigation management, both the provider and the user must be an “innovators”; i.e. they must be in the top 2.5% of the industry.  It may be that some “early adopters”, the next 13.5% of the industry, might be ready for the technology and its application to automate irrigation management.

What do we need?

Because it will be the innovators who adopt and field prove any technologies, these technologies must be robust and proven with a sound scientific backing.  Innovators will identify the financial benefits of the automation, which needs:

  • Well-designed irrigation systems
  • High uniformity irrigation systems
  • Well maintained irrigation systems
  • Precise soil moisture and/or crop monitoring systems
  • Interface “model” to irrigation controller

Are these all in place?

Is automation wise or the right solution?

Tony established HydroServices providing on-farm irrigation management services based on in situ soil moisture measurements in Canterbury, Pukekohe, Waikato, Gisborne, Hawkes Bay, Manawatu, Wairarapa and Central Otago. During this he provided specialist soil moisture monitoring for Foundation for Arable Research, LandWISE, Crown Research Institutes, Regional Councils, Clandeboye Dairy Factory and others.

Tony completed his PhD in Engineering Science at Washington State University, Pullman, USA.

Supporting digital innovation

We are delighted that Dr Amanda Lynn is confirmed as a key speaker at our Annual AgTech Conference LandWISE 2017: Are we ready for automation?

Amanda’s focus for this event is on moving “change” away from something that happens to us, to something we do as a natural part of our personal, business, economic and social development. This is called “purposive change” and she will explain how we create, adapt and integrate it.

When we talk about change we often do so without a clear idea of what is meant, and without recognition of our own—individual and collective—roles in adapting to change, or even catalysing it. 

We seldom talk about levels of change and processes of development; instead, getting caught in black and white terminology like “disruption” and forgetting that change is natural, incremental and evolutionary. 

Innovation is purposive change.  We can sometimes forget that purposive change is something we—people—are very, very good at.  And there’s a lot of us; resulting in a lot of purposive change. 

The Executive Director of the Innovation Partnership, and Chair of the Innovation Partnership Forum,  Amanda specialises in development. 

The Innovation Partnership is a not-for-profit Trust.  Sponsored by Google, Chorus and InternetNZ, the Innovation Partnership connects businesses, educators and Government entities to support digital innovation. 

In addition to working with the Innovation Partnership, Amanda leads her own contracting enterprise, Mandolin Associates, undertaking public speaking, research and advisory services, and through this has worked closely with some of New Zealand’s leading agriculture and aquaculture innovators. 

Amanda is a member of the New Zealand Association of Economists, and a Professional Member of the Royal Society of New Zealand.

Is the Juice worth the Squeeze?

Chris Roberts

Chris Roberts, Head of Industrial Robotics at Cambridge Consultants UK is confirmed as a keynote speaker for our Annual Conference. LandWISE 2017: Are we ready for automation?

Cambridge Consultants is a world-class supplier of innovative product development engineering and technology consulting with more than 500 staff including scientists, mathematicians, engineers and designers.

Chris was one of the presenters at AgriTech-East’s Robotics Pollinator in October 2016, which Dan attended as part of his Trimble Foundation Study Trip investigating farm robotics.

“I was really impressed with Chris and his presentation. He worked clearly  and methodically through the issues that need very careful consideration.” 

In this presentation Chris will take a look at the prospects for robotic fruit harvesting, an issue of note in New Zealand as production levels rise and labour availability reduces.

Some of Chris’ questions:

  • Automation has existed in agriculture for decades: what’s new?
  • Why hasn’t it happened everywhere already?
  • Which tasks to automate?
  • What has to come together for a  successful harvesting robot?

Chris will address these questions and more at LandWISE 2017.

Hyperspectral imaging to map species distribution

Tommy Cushnahan is a PhD student at Massey University within the NZ Centre for Precision Agriculture.

Tommy is presenting some of his research at LandWISE 2017: Are we ready for automation?

Remotely sensed hyperspectral data provides the possibility to categorise and quantify the farm landscape in great detail, supplementing local expert knowledge and adding confidence to decisions.

In his presentation, Tommy will explain how hyperspectral aerial imagery is being used to classify various components of the hill country farming landscape. He focuses on development of techniques to identify and classify various vegetation components including water, tracks/soil, Manuka, scrub, gum, poplar and other tree species. 

Tommy’s PhD has been funded by Ravensdown and MPI as part of the PGP project “pioneering to precision”.  A background in agronomy and 15 years’ experience in golf course design, construction and project management has developed an array of real-world skills that has helped shape his research. His goal is for his work to produce tangible benefits for hill country farmers.

Refill Scheduling for Agricultural Robots and Other Vehicles

Rob Fitch

Refill scheduling is the problem of deciding when a robot or other agricultural vehicle should pause in its work to replenish a resource, such as herbicide or fuel. This problem is commonly solved in broadcast spraying, for example, by simply running the spray tank dry and then refilling it.

This strategy actually leads to lost time in traveling to the refill location, and we can show that these time losses can be significant. When multiple machines must queue at a refill location, the problem is made worse.

In this talk, Rob will explain the theoretical difficulty of this problem and give examples from robotic spot-spraying and broadcast spraying to illustrate the potential time losses. He will present an optimisation approach that chooses optimal refill times to minimise travel distance and queuing time. These results apply to agricultural robots, human-driven spray rigs, and any other machine that must refill or empty some material at a fixed location during the course of its work.

Rob will conclude the talk by tying these results into the larger research program in agricultural robotics, including novel machine learning methods for fruit/vegetable detection that support selective harvesting.

Rob Fitch is Associate Professor at University of Technology Sydney.He was previously a Senior Research Fellow with the Australian Centre for Field Robotics (ACFR) at The University of Sydney where he retains an honorary position. He is a leading research scientist in the area of autonomous field robotics. He is interested in systems of outdoor robots and their application to key problems in agriculture and environmental monitoring.

Robert received his PhD in computer science from Dartmouth (USA). He has led research in planning and collaborative decision-making for both ground and aerial robots in a variety of government and industry sponsored projects including those in broad-acre agriculture, horticulture, bird tracking, and commercial aviation.

 

Integrating Public and Private Spatially-based Data

Aaron McCallion

Very pleased to confirm Aaron McCallion as a speaker at our Annual AgTech Conference LandWISE 2017: Are we ready for automation?

Aaron’s presentation will focus on how public and private data are being integrated to provide better land management outcomes.

For example, a recent European initiative has used data integration to automate pesticide application to crops in a way that protects adjacent natural ecosystems through the use of legal buffer zones identifiable by machine readable maps. 

In New Zealand, integration of public and private data is being piloted to assist Maori land owners in achieving economic returns within their environmental, social and cultural values.  This is being enabled through open government data initiatives that include legal land titles, vegetation cover maps, soil databases, digital elevation models and remote sensing.

The impact of different land management approaches can be assessed when such public data is combined with private data that includes historic land use practices, climate monitoring, ecosystem health indicators, inputs and financial data.

Visual representation of this spatial data in interactive mapping and analysis tools can then allow users to understand land management issues as well as aid the identification of risk mitigation or restorative strategies.  

Aaron will discuss what is needed for such approaches to be effective,  and ethical and legal requirements that need to be maintained with respect to privacy where the public or private data could identify individuals.

Aaron McCallion is Executive Director of Waka Digital, a leading Information Technology firm established in 2006 to deliver IT and communications based products and services. 

Aaron combines system dynamics modelling, economics and management with his understanding of sustainable development and environmental restoration. His skills include assessment of effectiveness, efficiency, user satisfaction and accessibility to measure or improve the usability of new or existing products or services, including prototypes.

He is a Key Researcher in the MBIE programme, Oranga Taiao, Oranga Tangāta – Knowledge and Toolsets to Support Co-Management of Estuaries and previously in the MBIE gold-rated programme, Manaaki Taha Moana-Enhancing Coastal Ecosystems for Iwi. (2009-2015)

Aaron has a BBS from Massey University and an M.B.A. through the global program operated jointly by Sejong University in Korea and Syracuse University in the United States.

In Search of Farm Robots: Ch 1

A version of this article previously appeared in The Grower

Dan Bloomer has been travelling in Australia and Europe asking, “How ready are robots for farmers and how ready are farmers for robots?”

Notable areas of active research and development globally are scouting, weeding and fruit picking.  Success requires machines that can determine and follow a route traversing whatever terrain it must, capture information, identify and selectively remove weeds, and identify, pick and transport fruit.  They have to sense, analyse, plan and act.

Robotics is widespread in industries such as car manufacturing that have the exactly the same task being repeated over and over again. With possible exception of robotic milking, farm operations are not like that. Virtually every single case is unique with unique responses needed.

Many groups around the world are looking at robotic weeding . There are many items needing attention. How do we tell weeds from crop plants? Can we do that fast enough and reliably enough to make a robot commercially viable on-farm? Once identified, how do we optimise robotic arm movement to best attack a patch of weeds?

The Australian Centre for Field Robotics (ACFR) at the University of Sydney is well known for its field robots such as the solar powered Ladybird. The new generation Ladybird is known as Rippa, and is currently undergoing endurance testing. Look on YouTube for ACFR videos and you’ll even see SwagBot moving around rolling hill country.

A key theme for Rob Fitch and colleagues is Active Perception: perception being what we can detect with what accuracy and confidence; active meaning in real time and including planning actions. They invest heavily in developing mathematics to get fast results. And they are succeeding.

Using Intel’s RealSense structured light camera it takes them less than half a second to identify and precisely locate groups of apples on a trellis. Within that time they also calculate exactly where to place the camera to get a second confirming view.

Smart maths allow ACFR scientists to capture 3D images and identify and locate apples in less than half a second
Smart maths allow ACFR scientists to capture 3D images and identify and locate apples in less than half a second

Cheryl McCarthy and colleagues at the National Centre for Engineering in Agriculture (NCEA) are 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 include automation for weed spot spraying, adaptive control for irrigation optimisation, and remote crop surveillance using cameras and remotely piloted aircraft.

At LandWISE 2015, Cheryl reported on their machine vision and sensing system for weed detection systems that uses depth and colour segmentation and a new processing technique to operate at commercial ground speeds of 10-15 km/h.

Now Cheryl is using UAVs to capture photos of crops, stitching the pictures to get a whole paddock image, then splitting it up again to efficiently identify and locate individual plants and weeds. This is enabling her to create accurate maps some other weed destroying robot can use.

cherylmccarthy
Research at the University of Southern Queensland investigates UAVs to scout paddocks combined with image stitching and analysis for interpretation to create maps of weeds for later treatment

SwarmFarm founders, Andrew and Jocie Bate grow cereals and pulses near Emerald. Spray-fallow is used to conserve water in this dryland environment and WeedSeeker® and Weedit® technologies reduce chemical use to a very small percentage of traditional broadcast application.

4WD SwarmFarm robots carrying WeedSeeker technology cover the paddock spraying only living weeds
4WD SwarmFarm robots carrying WeedSeeker technology cover the paddock spraying only living weeds

With large areas, most growers move to bigger machinery to maximise labour efficiency. This has a number of adverse effects including significant soil damage and inability to work small areas or work efficiently around obstacles such as trees.

SwarmFarm chose robots as practical light weight equipment. They reason that several small machines working together reduce soil impact and have the same work rate as one big machine. Andrew estimates that adoption of 8 m booms versus 34 m booms could increase the effective croppable area in Queensland by 2%.

Are these robots ready for farmers? Are farmers ready for these robots?

Only SwarmFarm has multiple machines currently working on farm in Australia. They are finalising a user interface that will allow non-graduate engineers (smart farmers) to manage the machines.

The question that remains is, “Why would I buy a specialised machine when I can put a driver on a cheaper conventional tractor or higher work rate sprayer and achieve the same?”

Is it the same?

Travel to Australia was supported by a Trimble Foundation Study Grant