PLEASE NOTE: Due to the COVID-19 crisis - hard copies of publications will be unavailable for the foreseeable future

2018 Winter - Is agriculture ready for autonomy?

Please note single Journal articles are not available in hard copy.

To download the free editorial articles click here

This catalog has no sub-catalogs.

Farm Policy Journal: Vol 15 No 2 2018 Winter - Full Journal - Is agriculture ready for autonomy?

Australian Farm Institute (2018), Is agriculture ready for autonomy? , Farm Policy Journal: Vol. 15 No. 2, Winter 2018, Surry Hills, Australia.

ISSN 1449–2210 (Print)
ISSN 1449–8812 (Web)


FPJ1502B - Lyons, N & Clark, C (2018), The Future of Autonomous Dairies

FPJ1502B - Lyons, N & Clark, C (2018), The Future of Autonomous Dairies, in Farm Policy Journal, vol. 15, no. 2, Winter 2018, pp. 1-5, Surry Hills, Australia.

Dairying is an important contributor to Australian agriculture and a strong source of regional employment. However, it is also a time and resource-intensive industry. Within New South Wales Department of Primary Industries and the Dairy Science Group at the University of Sydney, there is a strong vision for a connected, autonomous and smart dairy industry, where everything can be measured, monitored and managed in order to optimise productivity and maximise profitability.
In an ideal high-tech dairy industry, all participants in the supply chain should be able to ensure efficiency in both quantity and quality of milk production. Labour efficiency will be dramatically improved, and technology will be deployed at different levels, such as at animal or plant level, on-farm or at a regional basis.
However, currently farmers have too many options and not much clarity regarding the value of different technologies. There is also still work to be done on the research and development (R&D) side, as well as that related to extension and education services, in order to provide technology solutions fit-for-purpose and to ensure a level of technological competency across industry.


FPJ1502C - Chandra, R (2018), FarmBeats: Automating Data Aggregation

FPJ1502C - Chandra, R (2018), FarmBeats: Automating Data Aggregation, in Farm Policy Journal, vol. 15, no. 2, Winter 2018, pp. 7-15, Surry Hills, Australia.

Digital agriculture offers one of the most promising approaches to address the challenge of sustainably increasing food production by 70% by 2050 (from 2010 production levels). Using the latest advances in artificial intelligence (AI) and machine learning (ML), the farmer can be empowered with predictions that can improve farm processes, from planning until harvest.
Satellite data and remote sensing techniques can provide agricultural insights, by using advanced image processing algorithms and AI algorithms on multiple spectral bands in satellite imagery to estimate crop health. However, satellite imagery alone is unable to capture all the data from the farms. Recent work has investigated the use of in-field sensors and imagery to complement satellite data, along with unmanned aerial vehicles (UAVs), cameras and sensors on tractors. These data are streamed to the cloud using the latest Internet of Things (IoT) technologies, where they are processed to provide valuable insights to the farmer.
However, there are two key challenges in enabling this IoT-enabled vision of data-driven farming. First is the ability to get data from the farm, as most farms have poor Internet connectivity. The second is how to make data from different modalities actionable by the farmers. The heterogeneous sensor streams need to be merged and analysed together with satellite data. In addition, data collection and analysis need to be done in a way that does not add to the farmer’s workload, but instead streamline efficiency.
The FarmBeats solution at Microsoft uses new technologies, such as TV white spaces and Azure IoT Edge, to collect large amounts of data from the farm via sensors, tractors, cameras, drones and other devices. FarmBeats then develops new AI & ML algorithms (trained on this data), along with any available remote sensing data, to provide unique, actionable insights to farmers which can improve productivity.


FPJ1502D - Perez, T (2018), Agricultural Robotics – What Can Go Wrong?

FPJ1502D - Perez, T (2018), Agricultural Robotics – What Can Go Wrong?, in Farm Policy Journal, vol. 15, no. 2, Winter 2018, pp. 17-34, Surry Hills, Australia.

The introduction of autonomous systems, such as robots, in agriculture offers significant opportunities to the sector regarding potential increases in productivity and profitability whilst ensuring sustainability. However, it also poses challenges. This article focuses on aspects of risk about agricultural robot operations for cropping applications. We consider examples of robotic applications and discuss the risks associated with their services in crop protection, nutrition, and harvesting. We then discuss how these risks can be mitigated not only by robot design but also by the understanding of the limitations of the technology through assessment safety and performance metrics and their uncertainty quantification. The latter can inform decisions of regulatory agencies, insurance companies, and end users. Finally, we discuss challenges that robotics and autonomous systems may pose to current legislation and regulation.


FPJ1502E - Wiseman, L, Cockburn, T & Sanderson, J (2018), Legal Consequences of Autonomous Farming

FPJ1502E - Wiseman, L, Cockburn, T & Sanderson, J (2018), Legal Consequences of Autonomous Farming, in Farm Policy Journal, vol. 15, no. 2, Winter 2018, pp. 37-46, Surry Hills, Australia.

With the increasing world population placing greater and greater pressure on food production, the issue of food security is high on the world agenda. In the search for strategies to address this looming crisis, attention is being drawn to the power of new digital and autonomous technologies to increase agricultural productivity. As Revich has noted, ‘the next leg of food production growth will come from greater precision in agriculture, with advances in hardware, software and computing power converging with technologies like self-driving tractors and drones to help farmers feed humanity’s next century.’
The aim of this paper is to do just that: to highlight the potential legal consequences of the introduction of autonomous machines and technologies into Australian agriculture. As autonomous and robotic equipment use increases so too will the rate of incidents or accidents involving such autonomous and robotic equipment.
We will focus on the potential legal issues that may arise where an autonomous farming machinery causes an incident or accident that results in legal action for compensation for personal injury and/or property damage and discuss how the current laws in Australia are likely to respond. Legal issues relating to potential criminal liability; workers compensation and specifically the CASA regulations around the use of drones claims are beyond the scope of this paper. However, as is happening in other countries, we argue it is time for a review of the current schemes of compensation available for loss or injuries caused by autonomous farm machinery, keeping in mind those who are using these technologies are ultimately contributing to a food secure future.


FPJ1502F - Devitt, K (2018), Cognitive Factors that Affect the Adoption of Autonomous Agriculture

FPJ1502F - Devitt, K (2018), Cognitive Factors that Affect the Adoption of Autonomous Agriculture, in Farm Policy Journal, vol. 15, no. 2, Winter 2018, pp. 49-60, Surry Hills, Australia.

Robotic and Autonomous Agricultural Technologies (RAAT) are increasingly available yet may fail to be adopted. This paper focuses specifically on cognitive factors that affect adoption including: inability to generate trust, loss of farming knowledge and reduced social cognition. It is recommended that agriculture develops its own framework for the performance and safety of RAAT drawing on human factors research in aerospace engineering including human inputs (individual variance in knowledge, skills, abilities, preferences, needs and traits), trust, situational awareness and cognitive load. The kinds of cognitive impacts depend on the RAAT’s: level of autonomy, ie whether it has automatic, partial autonomy and autonomous functionality and stage of adoption, ie adoption, initial use or post-adoptive use. The more autonomous a system is, the less a human needs to know to operate it and the less the cognitive load, but it also means farmers have less situational awareness about on farm activities that in turn may affect strategic decision-making about their enterprise. Some cognitive factors may be hidden when RAAT is first adopted but play a greater role during prolonged or intense post-adoptive use. Systems with partial autonomy need intuitive user interfaces, engaging system information, and clear signaling to be trusted with low level tasks; and to compliment and augment high order decision-making on-farm.


Purchase a
membership and gain
unlimited access to
our journal and
research library


Purchase our
latest report