This AI Crop Spraying System Can Tell Plants and Weeds Apart

Trevor Smith | February 22, 2018

The agriculture industry is one of the world’s largest and most impactful. The $5 trillion industry composes 10% of global consumer spending and 40% of employment, according to McKinsey.

It also represents 30% of global greenhouse gas emissions, and is responsible for untold volumes of toxins and herbicides being put into the soil and water table.

It’s tackling those environmental issues that inspired Blue River Technology founder Jorge Heraud to start his company, which was recently acquired by John Deere for $305 million just six years after its founding.

Heraud and his small team spent countless hours perfecting “See & Spray” technology — a system that teaches machines to differentiate between weeds and crops, and precisely deliver a small but lethal dose of herbicide to remove the offending plants. This preserves the crops while, at the same time, greatly reducing the amount of toxic chemicals needed to keep weeds at bay, reducing their use by 90%, according to Wired.

At the same time, the system constantly gathers data about the crops it’s working with, making adjustments as needed and ensuring that only the smallest necessary amount of herbicides are used.

How See & Spray Works

See & Spray technology is fitted onto tractors like standard weed spraying machinery, but it’s also equipped with an array of cameras and machine-learning software. This enables it to tell the difference between weeds and crops, and actually improve performance as it learns. The system is so precise, in fact, that it can tell the difference between cotton plants and weeds in 30 milliseconds.

See & Spray isn’t Blue River Technology’s first foray into automated crop equipment. It saw great success with its LettuceBot, which is deployed on fields where young lettuce plants grow. The bot initiates a sort of controlled Darwinism, not only eliminating weeds, but actually thinning out the lettuce it deems too small to be viable and creating space for the larger, stronger plants to thrive. Today, 1/5 of all lettuce grown in the United States has been thinned by a LettuceBot, according to Bloomberg.

The development of See & Spray technology wasn’t without its early hiccups either. Initial models experienced issues during the testing phase like leaking nozzles, which dripped concentrated fertilizer on acres upon acres of seedlings on test fields in Arkansas.

In response to this problem, Heraud and his team added a fail-safe automatic abort function, which stops any nozzle that flows for more than five seconds. To make things right with the farmers whose crops they killed, the company thinned their next 100 acres for free.

A Greener Future

A major side-effect of agriculture’s reliance on (and less-than-judicious use of) weed-killer is one of the reasons innovations like Blue River Technology’s has caught the eye of big farming companies.

Weeds are hardy plants, and they’ve developed resistance to commercial weed killer like Roundup at an alarming rate. According to Bloomberg, in 2008, there were 10 million acres of Roundup-resistant weeds. By 2012, there were 30 million, and today there are 70 million acres, an area about the size of Nevada.

The $28 billion herbicide industry is unlikely to go down without a fight, but, perhaps surprisingly, even some of the biggest names in the business were early investors in Blue River Technology, including Monsanto Growth Ventures and Syngenta Ventures.

The first See & Spray bots are expected to hit the US in 2020, with Europe following a year later. Reducing agriculture’s reliance on haphazardly deployed toxic chemicals to thin crops and kill weeds will benefit our world in many ways. That includes a cleaner, less chemically tainted food supply, fewer toxins seeping into the world’s waterways and the preservation of aquatic and amphibious species.

As Heraud told Bloomberg, “Robots don’t have to take us away from nature — they can help us restore it.”

Learn how teams are strengthening their development process for complex products such as robotics with our white paper, “Better Product Development: Five Tips for Traceability.”