This project aims to contribute to the penetration of agricultural robots into commercial markets by further developing a teleoperated robot, which was implemented in a previous project (AgriRobot). The main idea of this project is to combine the two existing directions (fully automated and teleoperated robot) in order to design, develop, test and evaluate a Semi-Autonomous Vineyard Spraying Agricultural Robot (SAVSAR).

This proposal aims to develop an automated system for precise application of nitrogen (N) fertiliser and plant growth regulators (PGRs). Algorithms and software will be developed for integrating diverse forms of data from crop sensing instruments, yield maps, soil maps and soil N measurements. This will enable more accurate N fertiliser and PGR management through real-time decision making in the field, both on a field-by-field basis and on a metre-by-metre basis.

Abstract The project brings together agronomy research, on rapid protein assays for milling wheat, with engineering of photonic sensors, image recognition & mechatronic systems. The ultimate goal is to deliver a tractor-mount scanning unit for autonomous mapping of protein content across wheat fields, to a spatial resolution better than 2 square metres at full field application speeds (17km/hr) for precision application of nitrogen (N). N is the primary input cost and 80% of the carbon footprint, in milling wheat production, however it is over applied in 3 out of 4 cases.

Abstract AUTOPIC is a multi disciplinary project aimed at mechanising the harvesting of soft fruit through the use of autonomous vehicles and robotics. Partners include Harper Adams University, the Shadow Robot Company, Interface Devices Limited and the National Physical Laboratory. The project is timely since the source of migrant seasonal fruit pickers is no longer supported by the Seasonal Agricultural Workers Scheme and in general migration is being discouraged by government policy.

The project will develop an autonomous robot allowing >50 % herbicide reduction in sugar beet weeding. New weed detection vision algorithms will be developed and ported to a graphics processing unit. A low-power robotic arm and robust multi-sensor navigation will be designed. Five solar-powered prototypes will be validated in real operation. The robot will significantly reduce weeding cost, allowing return on investment in 3 years. The project is aimed at distributing the robot in all of Europe, with envisaged sales of 1000 robots per year from 2018 on.

Hydraulic modules are the building blocks of many applications, in particular specialized vehicles. The aim of this project is to develop a safe and resource-efficient technology of regulation and control for a stilt tractor. This is to be achieved by an innovative approach to sensor integration. External position and altitude sensors will be used to enable highly dynamic control. The upgrade of consisting hydraulic modules will be possible. The stilt tractor will be demonstrated in a vineyard.

Robots invade farmland An increasing number of farming operations in the field are taken over by robots because many agricultural implements have become so automatic that they can do the job on their own. However, the farmer is not yet completely superfluous since the robots need to be monitored and guided. For years farmers and their machinery have been partners in shouldering the heavy jobs that have to be done in the field. Now a new type of partnership with machinery is emerging where machines are asked to not merely do the heavy jobs.