The recent focus of the agri-robotics community has been to identify applications where the automation of repetitive tasks is more efficient or effective than a traditional human or large machine approach. One advantage of modern robotics is their ability to be built using low-cost, lightweight and smart components. Due to their prevalence in consumer electronics, such as mobile phones, gaming consoles and mobile computing, high quality cameras and embedded processors can be built in to many platforms at very low cost.

Adoption Considerations:
A robot can use 90% less herbicide, making it 30% cheaper than traditional treatments. A fleet of these robots could easily replace human farm labor down the road. Fruit picking robots, driverless tractor/sprayers, and sheep shearing robots are designed to replace human labor. Robots can be used for other horticultural tasks such as pruning, weeding, spraying and monitoring. As well as in livestock applications such as automatic milking, washing and castrating. They can also be used to automate manual tasks, such as weed or bracken spraying, where the use of tractors and other manned vehicles is too dangerous for the operators. Automated Guided Vehicles can increase the precision of agricultural operations. For example, autonomous tractors with intelligent agricultural tools, can reduce soil compaction and reduce the overdosage of nitrogen and herbicides.

The sensor technology evolution is generating cheaper sensors for several relevant agronomic parameters. These sensor attached to IoT solutions, Robots, agricultural machinery will feed advanced Farm Management Intelligent Systems with relevant data to obtain accurate prescriptions maps, which will allow a more eco-friendly and precision agriculture/forestry

Adoption Considerations:
The sensor technology evolution is generating cheaper sensors for several relevant agronomic parameters, such as NPK quantification, soil moisture, soil temperature, rainfall, wind, sunlight, chlorophyll concentration Index, leaf wetness, air temperature, etc.; which allows better decisions with an expected impact on the efficient use of the resources.

Interconnection of sensing and actuating devices providing the ability to share information across platforms through a unified framework, developing a common operating picture for enabling innovative applications. This is achieved by seamless large-scale sensing, data analytics and information representation using cutting edge ubiquitous sensing and cloud computing.

Adoption Considerations:
IoT will play an essential role on intelligent and precision agriculture/forestry, namely to collect data more accurately and allow a precision control on the field, to reduce water and energy costs and improve operations efficiency. IoT can innovate and interconnect irrigation systems, crop data collection, climate conditions monitoring, greenhouse automation, Crop management, Cattle monitoring and management, operations monitoring and control, transport management systems and end-to-end farm management systems. IoT depends on Lora, Sigfox, Wifi, 4G, 5G networks and, as other solutions, their implementation still suffers from traditional challenges such as a lack of or poor infrastructure, failures of interoperability, and other technological issues.

Systems thought and designed to provide support to decision-makers, giving them access to a wide range of data and facilitating the use of procedures, operations, and models in an easy and flexible way; allowing managers to virtually change parameters and observe the implications in the final results.

Adoption Considerations:
DSS should provide valuable information to support decision-making concerning the management of the resources available such as water, machinery, workers. The plans and schedules for performing operations along the value chain are often displayed in the form of user-friendly interfaces. Dashboards and other monitoring features enable remote follow-up of operations execution when integrated with IoT. DSS implies the design and implementation of information systems that can integrate machine learning, predictive analytics, big data and optimization approaches as back-office tools.

Artificial Intelligence (AI) is a field of computer science that deals with intelligent machines. Machine learning and deep learning are two of the most commonly used algorithms in the field of AI. These models learn from data and are used to make predictions. The objective is to come up with the most suitable solution to any problem. Today, machine learning models are being developed to deal with the complexity and variety of data in the food industry.

Adoption Considerations:
ML can be used in many tasks related to agriculture since data can be collected. These data can be images, data from sensors, data obtained from soil analysis, from meteorological stations, from productivity cards, measures collected in plant breeding projects, among others. These data can be used to generate production predictions or potential hydric predictions, to detect plagues, to recommend treatments given the place and the time, among several other tasks.

Digital Marketplaces and Platforms are flourishing today thanks to the advances made in Artificial Intelligence, machine learning, real-time personalization and the scale and speed of the latest generation of cloud platforms. Today’s digital marketplaces are capitalizing on these technologies to create trusted, virtual trading platforms.

Challenges:
Apart from providing market prices to users, ability to post bids and offers, e-marketplaces systems consist of a matchmaking feature to match user’s bids and offers for commodities. Providing such information to users contributes to improved negotiation power (e.g., farmers’ increase their power to negotiate with intermediaries, based on their ability to understand pricing in multiple markets); sophisticated marketing plans based on price information; access to better and variety markets; reduced logistics and transportation costs.