Intelligent harvesting

Researchers at the National Physical Laboratory have developed imaging technology to be used in an intelligent harvesting machine that could, it is claimed, save farms up to £100,000 a year.


Researchers at the National Physical Laboratory (NPL) have developed imaging technology to be used in an intelligent harvesting machine that could, it is claimed, minimise wastage and solve an impending labour shortage.



According to a statement, up to 60 per cent of certain crops are lost annually, which can add up to £100,000 of lost revenue for an average farm every year. Similarly, the falling number of migrant labourers means that healthy crops are not being gathered at the optimum time.



NPL’s scientists are working with KMS Projects and Vegetable Harvesting Systems (VHS) to turn the technology into an intelligent harvesting machine, which can look beneath the leafy layers of a crop, identify the differing materials, and enable precise size identification.


This can be used to develop a fully-automated harvesting robot, which would be able to fill the gap left by the labour shortage.



Radio frequencies, microwaves, terahertz and the far-infrared have been identified as being the most appropriate technologies for this kind of application. These four parts of the electromagnetic spectrum all have potential to safely penetrate the crop layers and identify the size of the harvestable material for a relatively low cost.


NPL has developed a methodology for crop identification and selection focusing on cauliflower crops, one of the hardest crops to measure due to the large amount of leafage that covers the vegetable.



The researchers at NPL began by modifying microwave-measurement systems to measure a cauliflower’s structure. A series of measurements made on real crops in the laboratory and field enabled a statistical range of measurements for precise size identification.


This data is then designed into an algorithm to enable a simple size indication from a raw measurement with uncertainties. The final technology will be developed for a first-generation harvester and tested in a real farming environment.


A successful demonstration of the imaging technology was given recently at Fanuc Robotics in Coventry, which attracted further commercial support from G’s, one of the largest lettuce growers in the UK. A complete unit could be available as early as next year.