Can a robot decide what to do in the greenhouse?
Source: HD.com
According to Alejandro Fernández, CEO of Botmotics, the recognition system is built on a neural network trained on approximately 105,000 images of weeds and cultivated plants, from which it learns to distinguish which vegetation should be removed within a horticultural plot. "In doing so, we have simultaneously reduced two common sources of contamination in this agricultural task: the diesel used by tractors, and the herbicides and other chemical products used to control weeds." From automation to "operational intelligence" Botmotics received two national awards last year from CaixaBank and Cajamar, recognising the company's evolution from automation to operational intelligence.
Botmotics, which has a presence and manufacturing facilities in Spain, Italy, Portugal, Mexico, Argentina, and China, has succeeded in connecting robots, sensors, and artificial intelligence so that machines do not simply execute pre-programmed instructions, but can interpret information from multiple devices before deciding independently how to act. "Applied to farming, a machine could, for example, use sensors to detect rainfall, measure wind speed, and combine that data with weather information before determining whether it is appropriate to go out and work, while the solar panel itself can adjust its position when wind conditions make it advisable to reduce its exposure." "We instrument everything so the robot can make its own decisions," says Fernández, who believes that the combination of artificial intelligence, sensor integration, and autonomous decision-making will define a significant part of the next phase of robotics, both in agriculture and in other sectors.
"While previous generations built much of agricultural mechanization around the tractor, younger growers show a greater willingness to adopt automation when they find an application that fits their operation and their cost structure." That shift is especially visible in Spain's most intensive growing regions, and the company is directing part of its focus towards Murcia and Almería, where it is working on new prototypes designed for greenhouse harvesting. Ozone boosts production of soilless strawberries by 30% at a farm in Verona “We are looking for the right partners to bring our proven working method worldwide” BFG Supply: 461 full-time employees affected "I see opportunities everywhere to make things more efficient" Greenhouse simulation brings energy and ventilation decisions into design Behind-the-scenes tomato cultivation at R&L Holt Choosing the right technology for an intensive greenhouse operation Bonaire project to test containerised CEA under local conditions Related Articles Retractable roof systems expand into orchards, fields and vineyards Can a robot decide what to do in the greenhouse?
Why this matters: For operators, this is a water-management story. The useful signal is that direct substrate measurements can help cut drain loss materially without giving up yield or fruit quality, which is exactly the kind of controllable efficiency gain a facility can build on.
Frequently Asked Questions
Why does substrate sensing matter in free-drain strawberry systems?
Because drain percentage tells a grower what already happened, while substrate moisture and EC data show root-zone conditions directly. That makes it easier to cut water loss without guessing.
What is the operator takeaway from this trial?
If the thresholds are understood well enough, growers can reduce drain water materially while protecting yield and fruit quality, which makes sensing an operational tool instead of a reporting tool.
