World Resources Institute figures suggest that a third of all food produced is wasted, explaining 8% of global greenhouse gas emissions and $940B economic losses per year. This project will focus on waste reduction in strawberry production (average waste 9%, about $1B globally) but the approaches developed will be applicable to other fruit crops too. Picked fruit may be wasted either because it is defective or because it cannot be sold due to market conditions - typically because weather-driven production peaks result in oversupply. Growers try to manage both kinds of waste by surveying the crop (i) to identify causes of lost productivity (diseases, pests, microclimate changes, etc.) and therefore take corrective action and (ii) to predict and therefore better manage the impacts of future yield variation. Current best practice requires experienced harvest managers to 'walk' the crop (often spread over many disparate fields) and attempt a subjective visual assessment of crop health and potential yield for each field. This project will improve yield monitoring and forecasting by using existing soft fruit picking robots to obtain much richer data about the condition of the crop. Denser survey coverage will facilitate the development of more accurate long-range yield forecasting models. Another benefit will be an innovative automatic yield monitoring system sensitive enough to small changes in productivity to provide growers with earlier warning of disease and other causes of waste. This project will be implemented by three exceptionally innovative UK businesses: Dogtooth Technologies, developer of the state-of-the-art soft fruit picking robot, Fresh4cast market leader in the supply of yield forecasting tools, and Hugh Lowe Farms, a widely respected and large UK producer of berry fruits and influential member of the UK's largest soft fruit cooperative Berry Gardens. Following successful completion of this project, the consortium partners will bring to market a yield monitoring/forecasting solution giving step-change performance increase compared to the current state of the art. This will benefit soft fruit producers globally, initially strawberry producers and later producers of other crops.

Following on from Project Idaeus, which delivered a proof of concept raspberry harvesting robot, this project Tenaci will pick up the development of two major threads of work: End-effector development and adaption of the crop to facilitate robotic harvest. Dogtooth has picked over 1.2M strawberries in the YTD 2023 using the end-effector developed through Idaeus. This level of real world testing has given a very clear understanding of the requirements for additional development work and specifies the content of this project. The goals of project Tenaci are: an end-effector at a Technology Readiness Level that will allow mass adoption of robotic harvest through hardware sales; increased capital utilisation through performing additional tasks such as husbandry and pruning; and consistently higher robotic picking efficacy throughout the season due to consistently high quality fruit presentation. Project Tenaci will generalise the work to understand and develop protocols for managing raspberry crops to top-fruit and project partner Adrian Scripps will drive development and validation of these protocols to development orchard architecture that both facilitates robotic harvest and maximises return on investment.

Strawberry harvesting is a labour intensive task that depends critically on the availability of a large amount of low-cost labour. Growers are increasingly vulnerable to labour market price fluctuations and burdened by high employment overheads. Building on Dogtooth's proof of concept strawberry picking robot (developed during Innovate UK project Ananassa), project Vesca will deliver commercially viable picking performance using cutting edge machine learning and computer vision techniques to facilitate more efficient localization of target fruit (by more nearly optimal control of robot motion) and more accurate determination of suitability for picking. The project will also provide ancillary benefits such as yield mapping and prediction that are of significant importance to growers.

Dogtooth Technologies is helping to make farming more sustainable through intelligent robotics. Project Demeter will increase the number of berries a battery powered (charged from renewable sources) picking machine will harvest in its lifetime. Not only will the project reduce the operational carbon emissions to close to zero, it will spread its embodied carbon over many more berries and will help reduce emissions from travel to the field. Reduced wastage in the supply chain will be provided by a more consistent crop that can be be better forecasted thanks to enormously rich data sets that the robots provide as they go about their work.

Raspberries are fragile fruits that require significant manual labour to harvest. The raspberry industry has seen significant growth in production due to consumer demand, but the cost and availability of labour is threatening its economic viability. This project will produce a proof of concept raspberry picking robot that will demonstrate the approach required to alleviate this bottleneck in growth of the sector. Building on the cutting edge developments that Dogtooth Technologies has already achieved in bringing to market a commercial strawberry picking robots, this project will continue to push the boundaries of the application of robotics to the needs of the agricultural sector.