Saturday 13th August 2022

Ag game changing and the intelligence is inside | The Western Producer


Artificial intelligence in agriculture is at the technology farmgate with machines that think like farmers

Artificial intelligence is on the cusp of causing a sea change in agriculture that promises to quickly challenge conventional crop-production and farm management techniques.

Many components required to build autonomous, smart agricultural equipment for vegetable and grain production in North America are already proven technologies.

Sensors including camera, lidar, and radar, as well as components that enable the electrification of machines such as hydraulic pumps, batteries and control systems are also far more available now compared to a few years ago.

The rapid increase of component options available to OEMs, short-line and start-up equipment manufacturers suggests competitive pricing pressure will be an early feature of the autonomous farm equipment market.

Most of the agriculture systems available today capable of performing tasks semi-autonomously, from autosteer to spot spraying systems including Weed-It or John Deere’s See and Spray Select, are based on straightforward, if complex, computer programming.

For instance, the spot sprayers mentioned above use cameras to identify plants on a field, and then commands are sent to individual nozzles to only spray areas where plants were found.

These systems are not capable of differentiating between a weed or plant, but this will change quickly because AI and machine learning strategies that drove the digital revolution in other sectors are being adapted for agriculture.

For instance, Bilberry is a tech startup founded in 2015 by Guillaume Jourdain, Hugo Serrat and Jules Beguerie, who developed an AI-based system to drive green on green spot spraying with the help of technology developed for autonomous automobiles.

Green on green spot spraying occurs when individual weeds are found and sprayed in-crop.

“At that time (2015) it was really the beginning of artificial intelligence embedded in vehicles, in a very broad way. Before it was very difficult to solve all the technological challenges that exist for spot spraying. But with AI and the rise of embedded systems, really we were at the right time to work on this and try to finish the solution,” said Guillaume Jourdain of Bilberry.

The Bilberry system has a camera every three metres on the boom. Each camera has a dedicated processor that sends the information to a central computer in the sprayer’s cab.

“From there we send the information to the nozzles to open them and close them in real-time; so individual nozzle control. Obviously, we are also linked to the GPS so we also have a section control that’s working,” Jourdain said.

“Normal speed for us to be about 20 km-h. It can be a bit faster, but 20 k is where we are very comfortable.”

Training machine learning algorithms is a long and tedious process.

Bilberry started by driving fields with sprayers and four-wheel drive vehicles equipped with cameras.

The FarmWise weeding robot at work in the Salinas Valley in Calfornia. It detects every plant on a field, both weed and crop, and then onboard computers send instructions to the robotic weeding arms. | FarmWise photo

The images were then labelled by manually identifying the plants in the photos and then the AI training process could begin.

“AI training means basically showing the labelled images to the algorithm several hundred or thousands of times so that it can start learning what the weeds are, what the crop is, and then in a new situation it will be able to say, ‘OK, that’s a weed or that’s a crop’,” Jourdain said.

He said Bilberry’s spot spray system is effective at taking broadleaf weeds out of cereal crops, with a 90 percent average hit rate of the weeds while using a fraction of the chemical required for blanket applications.

The company continues to train their algorithms to improve its ability to differentiate different kinds of weeds in many crops including canola, but the system is already commercially available in parts of Australia.

Bilberry is working with multiple spraying manufacturers including Europe’s Agrifac and SwarmFarm Robotics, an Australian start up that sells small autonomous robots that can be used for multiple applications.

Bosch and BASF’s new joint venture, called Bosch BASF Smart Farming, will offer its AI-based green on green smart spraying technology in Brazil by the end of the year, and plans to expand the service to North America.

An American startup called FarmWise builds an autonomous weeding robot for the vegetable industry that detects every plant on a field, both weed and crop, and then onboard computers send instructions to the robotic weeding arms.

FarmWise spent years developing in-house AI algorithms that are made for the specific purpose of detecting crops and weeds.

FarmWise spent years developing in-house AI algorithms that are made for the specific purpose of detecting crops and weeds. | FarmWise photo

“We rely on deep learning algorithms and a lot of data that we accumulated over the years to get to a very accurate decision-making process, in terms of what type of plant this is, where it’s located, and then a few other parameters that help us do a very good job at the service that we deliver,” said Sebastien Boyer, chief executive officer of FarmWise.

A Seattle-based startup uses AI in its 9,000 pound autonomous robot that uses a 72-horsepower Cummins diesel engine to power weed-blasting lasers.

Creator of Carbon Robotics, Paul Mikesell said the machine was built to manage weeds in vegetable row crops.

“There are eight lasers across. They are arranged in a fashion that’s parallel to the furrows. So if you imagine a row with our vehicle in it that’s driving forward, those lasers are arranged linearly pointing back to front. Then through some optics the targeting bounces that beam down at the bottom of the robot to target the weeds,” Mikesell said.

Eight lasers across, the unit uses optial sensors to find and kill weeds. | Carbon Robotics photo

Mikesell’s background is in computer vision and deep learning, which he applied to help the robot differentiate weeds from crops.

“It’s a learning algorithm, so it’s a neural net that has many different layers to it. It runs on GPU’s (graphics processing unit’s), which originally originated for graphics processing and have now been used for other things, you know like crypto currency mining. We use them a lot in deep learning because it’s very fast vector operations, things that can run in parallel, much like a human brain does,” Mikesell said.

He said the learning procedure involves providing the algorithm many sample images with enough labels that say what’s in the image.

“By label I mean pixel locations that have a label associated with it. So like this would be an onion for example and there’s an outline of an onion, or this is a weed that we want to shoot and we’ll have the center of the weed meristematic growth plate of the weed that we’re shooting with the laser,” Mikesell said.

Once the neural net is given enough samples it will learn to differentiate weeds and crops.

“Now it can make inferences about things that it hasn’t seen before, and it can say, ‘oh that’s this kind of plant I’ve seen that before, it’s not an exact copy but I know that’s an onion. Or I’ve seen that before, it’s not an exact copy, but I know that’s a purslane, which is a type of weed, or lambs quarters, which is a type of weed.’ So it learns, and then as we feed it more and more information and it gets better and better.”

The processing and predictions are made in real-time by the on-board computer, which does not need broadband connectivity.

However, during the training process, the neural nets require the team to gather example imagery and upload it to computers that conduct the deep learning processes.

Before turning the laser-blasting robots loose on a field, Carbon Robotic scouts weeds to fine-tune the AI for a specific field.

“Sometimes we can deploy the exact same ones (neural nets) that we’ve had before. Sometimes there are some smaller tweaks, what’s generally referred to as fine-tuning,” Mikesell said.

“The procedure usually takes 24 to 48 hours from initial arrival (at the field) to getting a good neural net, good predictions for us. That’s assuming it’s a new field.”

The example listed above is just the precursor when it comes…


Read More:Ag game changing and the intelligence is inside | The Western Producer