Category Archives: Research

AgTech, Automation, LandWISE People, Precision Agriculture, Research, Sensing

In Search of Farm Robots: Ch 1

January 30, 2017 Dan Bloomer

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

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

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

Agronomy, AgTech, Controlled Traffic Systems, Precision Agriculture, Research

In Search of Farm Robots: Ch2 Denmark

January 29, 2017 Dan Bloomer

This article originally appeared in “The Grower”

A visit to Denmark in search of farm robotics expanded to include wide span tractors, controlled traffic farming, growing Christmas trees and farm nutrient management plans and audits.

Automation of the agricultural sector has EU and government attention and funding. Despite an influx of refugees and workers from Eastern Europe, the focus is filling a labour void in the agricultural sector.

The new USD Tek Centre housing an engineering research group of around 500 people at the University of Southern Denmark (USD) illustrates the investment.

The Tek Centre at University of Southern Denmark illustrates the investment Europe is making in agritech development

Research institutes, municipalities and government are working on a proposal to turn a nearby commercial airport into a specialised unpiloted aerial system (UAS/UAV) facility.

USD is developing unmanned aerial systems to distribute beneficial insects to grapevines. Ground application results in losses as many beneficials cannot climb to colonise the target plant. The technical hurdle is UAS control – needing to control flight to release the beneficials from 200-500 mm above the canopy.

USD Robotic specialist Kjeld Jensen promotes open source software as key to increasing the pace of development. Having access to standards, stable architecture and software libraries means researchers can focus on new things rather than constantly reinventing the wheel.

An innovation hub in Struer was established in a facility donated by Ericsson Communications when they shifted research and development from Denmark. It is now home to about 150 technologists in a number of start-up companies.

Resident ConPleks Innovation develops automation technology for other manufacturers (for example Intelligent Marking and MinkPapir). The availability of such support makes it much easier for traditional companies to enter the field of robotics.

At the Agro Food Park in Aarhus, AgroIntelli has a focus on autonomy for weed control in organic productions systems, a movement apparently stronger in Europe than in New Zealand. This start-up grew out of a disbanded Kongskilde R&D group.

Safety of unmanned systems is critical. All the above are involved in “SAFE”, a project that brings together major agricultural machinery manufacturers and universities to develop advanced sensors, perception algorithms, rational behaviours for semi-automated tractors and implements and finally autonomous robots.

Hans Henrik Pedersen is well known to LandWISE members for his work on controlled traffic farming and gantry tractors. At Kjeldahl Farms on Samso we saw the prototype 9m ASA-Lift gantry. At 20+tonnes plus another 20+ tonnes with a hopper of onions it’s not a small machine. It seems version two will be different, but development funding is yet to be found.

The ASA-Lift 9m wide span gantry tractor at Kjeldahl Farms

At the Aarhus Agro Food Park Dan Bloomer delivered a presentation on Precision Agriculture in New Zealand to 70 Dutch agronomists and agrichem representatives touring Denmark. An afternoon field trip visited a biogas generator on a dairy farm and a facility for high quality Christmas tree production.

Specialist equipment for commercial production of Christmas trees fits narrow rows and automates labour intensive tasks

Other presentations covered the operation of SEGES, a farmer owned agricultural research and extension organisation performing more than 1,000 field trials every year in partnership with universities, government departments, businesses and trade associations.

SEGES covers all aspects of farming and farm management – from crop production, the environment, livestock farming and organic production to finance, tax legislation, IT architecture, accounting, HR, training and conservation.

A lot of work involves nutrient management. Denmark introduced nitrogen regulations in 1994. We are only now at a similar position. Caps introduced to stop leaching halved losses by 2014 by which time the nitrogen cap was about 25% lower than the economic optimum. With most benefit coming from improved handling of animal manures, the cap is now being lifted.

All Danish farmers must have nutrient management plans with budgets and fertiliser purchase documentation and application records. They are must report annually, work mostly being done by about 3,500 consultants. All fertiliser sales are reported to the Environment Agency so farm reports can be audited.

Dan’s travel was supported by a Trimble Foundation Study Grant

AgTech, Automation, LandWISE People, Precision Agriculture, Research, Sensing, Soil, Tillage

In Search of Farm Robots: Ch3 Switzerland, France and England

January 28, 2017 Dan Bloomer

This article originally appeared in “The Grower”

A desire to reduce soil compaction and avoid high and inefficient use of chemicals and energy inspired Steve Tanner and Aurelien Demaurex to found eco-Robotix in Switzerland.

Their solution is a light-weight fully solar-powered weeding robot, a 2 wheel drive machine with 2D camera vision and basic GPS. Two robotic arms position herbicide nozzles or a mechanical device for precision weed control.

Steve Tanner lab testing the exoRobotix vision and robotic weed control system

The ecoRobotix design philosophy is simplicity and value: avoiding batteries cuts weight, technology requirements and slashes capital costs. It is a step towards their vision of cheap autonomous machines swarming around the farm.

Bought by small farms, Naio Technologies’ Oz440 is a small French robot designed to mechanically weed between rows. The robots are left weeding while the farmer spends time on other jobs or serving customers. Larger machines for vegetable cropping and viticulture are in development.

Prototypes V1, V2 and V3; precursors to the Naio Oz440 show the steps in a robot’s development

Naio co-founder Gaetan Severac notes Oz440 has no GPS, relying instead on cameras and LiDAR range finders to identify rows and navigate. These are small machines with a total price similar to a conventional agricultural RTK-GPS system, so alternatives are essential.

Tech companies have responded and several “RTK-GPS” systems are now available under $US1000. Their accuracy and reliability is not known!

Thorvald an example of research collaboration: Norwegian University robot being automated at University of Lincoln show the common design of four wheel steer and four wheel drive

Broccoli is one of the world’s largest vegetable crops and is almost entirely manually harvested, which is costly. Leader Tom Duckett says robotic equipment being developed at the University of Lincoln in England is as good as human pickers at detecting broccoli heads of the right size, especially if the robot can pick through the night. With identification in hand, development is now on mechanical cutting and collecting.

In 1996, Tillett and Hague Technologies demonstrated an autonomous roving machine selectively spraying individual cabbages. Having done that, they determined that tractors were effective and concentrated on automating implements. They are experts in vision systems and integration with row and plant identification and machinery actuation, technology embedded in Garford row crop equipment.

Parrish Farms has their own project adapting a Garford mechanical to strip spray between onion rows. Nick Parrish explained that Black Grass control was difficult, and as available graminicides strip wax off onions boom spraying prevents use of other products for up to two weeks.

Simon Blackmore is a global leader in farm robotics thinking at Harper Adams University. His effort to address robotic safety issues includes a seven level system:

Route planning to avoid hazards and known obstacles
Laser range finder to sense objects and define them as obstacles
Wide area safety curtain sensing ground objects at 2m
Dead man’s handle possibly via smartphone
Collapsible bumper as a physical soft barrier that activates Stop
Big Red Buttons anyone close can see and use to stop the machine
Machines that are small, slow and light minimise inertia

“Hands free hectare” is Harper Adams University’s attempt to grow a commercial crop using open source software and commercially available equipment in an area no-one enters.

Harper Adams research to develop a robotic strawberry harvester is notable for the integration of genetics for varieties with long stalks, a growing system that has plants off the ground, and the robotic technologies to identify, locate and assess the ripeness of individual berries and pick them touching only the peduncle (stalk).

So what have I learned about farm robotics?

People believe our food production systems have to change
Farm labour is in short supply throughout the western world
Machines can’t get bigger as the soil can’t support that
Robotics has huge potential but when
Safety is a key issue but manageable
There is huge investment in research at universities, but also in industry
It’s about rethinking the whole system not replacing the driver
There are many technologies available, but probably not the mix you want for your application.

As Simon Pearson at the National Centre for Food Manufacturing says, “It’s a Frankenstein thing, this agrobotics. There are all sorts of great bits available but you have to seek them out and stitch them together yourself to make the creature you want.”

Dan’s travel was supported by a Trimble Foundation Study Grant

AgTech, Nutrients, Precision Agriculture, Projects, Research, Soil

Fertiliser Spreader Calibration

January 17, 2017 Dan Bloomer Leave a comment

We successfully completed our SFF project “On-farm Fertiliser Spreader Calibration” and launched the online tool, www.fertspread.nz earlier this year.

Some key messages:

Our testing found wide performance variation
Most new machines do a good job if set up correctly
Caution is essential spreading blended fertilisers or when bout widths exceed 30 m
Visible striping indicates > 40% application variability and at least a 20% yield penalty.
Fertiliser ballistics play a critical role

Setting out a line of catch trays to test fertiliser application uniformity

We ran a number of workshops from Waikato to Ashburton reaching a wide range of farmers and industry people. Information, training handouts and how-to YouTube video clips are on the LandWISE website. See www.fertspread.nz for the on-line calculator and field recording sheets.

We are grateful for strong support from Miles Grafton and Ian Yule at Massey University.

This project was co-funded by the Foundation for Arable Research (FAR), the Fertiliser Association (FertResearch) and MPI Sustainable Farming Fund.

More at www.landwise.org.nz/projects/fert-calibration

Agronomy, Drainage, Irrigation, MicroFarm, Plant Health, Planting, Precision Agriculture, Projects, Research, Soil, Water

Onion Crop Development

November 29, 2016 Dan Bloomer Leave a comment

The crop at the MicroFarm is showing increasing variability. The cause of some is understood, essentially excessive water pre-germination. But in some poor performing areas the causes have yet to be determined.

The effect of our artificially applied rain event pre-emergence is clearly evident in late November.

The lasting effect of a heavy (artificial) rain event pre-emergence (right panel) shows low population and poor growth compared to areas without heavy rain (left panel)

However, we also see other areas that have poor crop development that are outside the area irrigated to create the artificial rain event.

Wide variation within the area new to onions does not follow artificial rain or topographic drainage patterns.

Sharp differences in crop growth are evident in the new onion ground. Some parts that were heavily irrigated to simulate heavy rain show reasonable development. Areas that were not irrigated also show good development, but in some patches total crop loss.

Investigations of soil physical properties in these different areas are underway.

Agronomy, AgTech, Automation, Irrigation, MicroFarm, Nutrients, Plant Health, Precision Agriculture, Projects, Research, Sensing, Soil

Onion Crop Research Plan

November 29, 2016 Dan Bloomer Leave a comment

After identifying areas within paddocks that had yields limited by different probably causes, we conceived the idea of Management Action Zones (MAZs).

Yield assessments show considerable variation, limits imposed by population, growth of individual plants, or both

Some areas showed that yield was limited by plant number: establishment was poor. Others had the expected population, but low biomass: the plants were small due to some other limiting factor.

If we can identify zones easily, and determine the causes, we should be able to target a management response accordingly. So for this season, we set out a revised research aim.

What we want to know:

Can we successfully determine a management action zone in a field?

Why do we need to know this?

Develop a tool to increase uniformity and yield outcomes
Develop a tool to evaluate management practices and crop productivity

If we want to successfully determine a management action zone in a field then there are two main steps to achieve in this year’s work:

Confirm the relationship between digital data and crop model parameters
- Does the relationship stay constant over time and sites?
- How early in growth can a difference be detected?
- Can the relationship be used to show a growth map across a field?
Develop an approach to gather information and ways to input and display results, initially using a website approach.
- Can we integrate a plant count and yield information to start developing a management action zone?
- How should this be put together in a way growers can start to use to gather information about their crops?

At the MicroFarm, we established six research zones based on paddock history and excessive wetness at establishment.

We have three paddock histories: two years of onion production with autumn cover crops of Caliente mustard, two years of onion production with autumn cover crops of oats, and no previous onion crops planted after previous summer sweetcorn and autumn sown rye grass. In each of these areas, we deliberately created sub-zones by applying about 45mm of spray irrigation as a “large rain event”.

Artificial heavy rain event applied after planting and before emergence

The impact of the artificial rainstorm is evident on images taken at the end of November.

Agronomy, MicroFarm, Planting, Projects, Research, Soil, Tillage

Onion Crops Sown

September 12, 2016 Dan Bloomer Leave a comment

As part of our ongoing research project with Onions New Zealand, a new crop was sown on 6 September 2016.

Harvey from G & J Steenkamer planted the crop using Rhinestone seed donated by Vigour Seeds and treated for us by Seed and Field Services. We are very grateful for their continuing support.

We’ve aimed at a population of 580,000 plants/ha. With 8 rows in our 1.82m wide beds, we have seed at 72mm spacing in the row.

sowingonions03 — G& J Steenkamer sowing our onion crop.

After last harvest the beds, but not wheel tracks, were ripped to 450mm depth. Autumn planted Caliente and oat cover crops were mulched and incorporated in late June and the ground left fallow. Prior to sowing it was hoed and rolled.

Rain after planting had only minor impact, with a little soil capping in some areas.

AgTech, Plant Health, Research, Sensing

Vision System for Onion Crops

August 16, 2016 LandWISE Admin Leave a comment

Effective Sensing for Robotic Tasks- Still a Challenge

Kit Wong
Callaghan Innovation

Effective and reliable sensing for the performance of robotic tasks, such as manipulation in the outdoor environment remains a challenging problem.

While commercially available solutions such as ASA-LIFT are available for specific tasks and crops, and for operation in specific conditions, the systems are either not cost effective and or physically unsuitable for specific farming conditions and practices.

This research proposed to develop a mobile robot system with flexibility to adapt and with intelligence to cope with natural variability; through a two-fold aim utilising vision for navigation and manipulation. This talk discussed some of the recent developments on these aspects.

In particular, the talk focused on a novel approach that analyses point cloud information from a time-of-flight (ToF) camera to identify the location of foremost spring onions along the crop bed, for the intention of robotic manipulation. The process uses a combination of 2D image processing on the amplitude data, as well as 3D spatial analysis, extracted from the camera to locate the desired object.

Whilst the experimental results demonstrated the robustness of this approach, further testing was required to determine the ability of a system to cope with different scenarios that exist in the naturally varying environment.

For validation, the vision system was integrated with a robotic manipulation system and initial results of the investigation were presented.

AgTech, Automation, Planting, Research

Weeding Robots: A Global Review

August 15, 2016 LandWISE Admin Leave a comment

Current Prototypes of Field Robots

Armin Werner¹ Rory Roten¹ Luc van Rijen^2

1Lincoln Agritech PO Box 69 133, Lincoln 7640, New Zealand
²HAS University of Applied Sciences, The Netherlands
Email: Armin.Werner@lincolnagritech.co.nz

Excitement is being generated at conferences, farmer’s workshops and the general media about the next level in precision agriculture: field robots. We all know that robots work in factories to carry parts or conduct specific actions in manufacturing and that indoor robots are already standard technology in many industries.

There is also interest in developing autonomous equivalents in agriculture beyond the current tractor-carried or self-propelled equipment. There are already some tomato and cucumber picking robots in use in greenhouses in Europe and North America. However, stepping out of the ‘controlled’ environment of a factory building or a greenhouse into the unforgiving conditions of an arable field, a pasture or an orchard poses many serious challenges for scientists and engineers.

Most of these technical challenges have been solved or at least solutions are prototyped for outdoor conditions. This includes the exact positioning and the orientation of the robot under changing ambient light and weather or infrastructure, the recognition of the dynamically changing environment of a field robot as well as precisely controlling the actions that a robot has to conduct in a highly variable environment.

With these preconditions in mind, it is most likely that agricultural robotics will develop very fast in the next years. It is unclear what the first major applications may be and what challenges farmers will face when it comes to using such robots as standard equipment. From discussions with farmers, growers and the industry it is anticipated that weeding robots for row crops (annual field crops, perennial tree and vine crops) will be a good candidate to pave the way for field robots into agriculture.

The presentation will give an overview of current prototypes and weeding robots which are commercially available. We will discuss general differences between these robots and the type of applications that are intended.

Automation, Drainage, Research, Sensing

A Digital Horticulture Research Strategy

August 15, 2016 LandWISE Admin Leave a comment

Value Chain Approach To Identifying Priorities

Roger Williams
New Zealand Institute for Plant & Food Research Limited (PFR)

The industrial revolution gave us machines and agri-inputs that enabled us to farm at scale and speed. The green revolution began to unlock the potential of plant genes to increase yield. Now the digital revolution provides us with an opportunity to harness the power of ‘big data’ and technological innovation to radically re-engineer our horticultural production methods and supply chains.

Digitally informed decisions during production, harvesting, sorting, packing, storage and transit could be the basis for a step change to high profitability, high resource efficiency and low footprint horticultural value chains.

Identifying the research priorities that we need to realise this opportunity in New Zealand is a challenge in itself, given the pace of developments in sensing technology, robotics and the internet of things globally. Accordingly, Plant & Food Research assembled an expert panel from across its science teams, augmented with other specialists from New Zealand and Australia, to develop a digital horticulture research strategy.

The panel has taken a value chain approach to identifying research priorities, particularly in relation to production, harvesting, sorting and packaging, storage and transit. Future science needs are structured around the concepts of ‘sense, think, act’ for each part of the value chain and are linked by an ‘artery’ of data to feed forwards and backwards along the value chain.

Plant & Food Research looks forward to working with a wide range of partners to deliver this digital horticulture strategy for the benefit of New Zealand’s producers and exporters.

Effective Sensing for Robotic Tasks- Still a Challenge

Current Prototypes of Field Robots

Value Chain Approach To Identifying Priorities

Promoting sustainable production