Sign up for the farmnewsNOW newsletter
Mojow autonomous equipment (supplied photo/Mojow)
Autonomous Agriculture

Autonomous tractor kit receives funding boost

Jan 31, 2024 | 2:50 PM

The Canadian Agri-Food Automation and Intelligence Network (CAAIN) is supporting agtech research and innovation projects through its 2022 Open Competition and its Beef & Pork Primary Processing Automation and Robotics Program.

CAAIN is contributing $682,028 towards the $2,225,680 total cost of Made in Canada autonomous equipment.

Edmonton’s Mojow Autonomous Solutions has developed an Autonomous Tractor Kit. President Owen Kinch is a grain farmer who worked off farm and spent seven years in SeedMaster’s R&D department, before becoming the first employee of the company’s autonomous vehicle spinoff, DOT Technology Corp.

While there, he met his friend and eventual Mojow co-founder, Mojtaba (Moji) Hedayatpour, a systems architect and software developer.

While still at DOT, Kinch farmed his own land year-after-year with the company’s autonomous platform, and the experience provided unique insight into the challenges that slow adoption of such innovation. When Kinch left DOT and returned to his farming roots, he soon became frustrated with how much of his work still required manual labour. He sat down with other producers to better understand how technology might improve broad-acre farming.

What emerged was eye-opening and led Hedayatpour and Kinch to found Mojow in early 2020. Autonomous agtech is widely viewed as a key to reducing the agri-food sector’s reliance on increasingly scarce labour. However, existing models generally depend on GPS-driven navigation controllers, which don’t deal well with unplanned obstacles. Kinch said they require constant supervision of a trained human operator.

“It’s relatively easy to develop machines that can drive up and down fields independently in straight lines,” Kinch said. “But that’s not the entire farming story. Three important bottlenecks or complex challenges must be addressed if agricultural machinery is to operate without human intervention.”

The first is driving the headland without prior mapping. Second, the equipment must navigate the roads between the fields while the last piece is the ability of the tractor to transition seamlessly from road to field using entrances.

“If it can do all that, a vehicle is truly autonomous,” Kinch said. “Our customers’ equipment should drive itself from the yard to the road, access any fields and roads necessary, and return to its starting point when the job is done.”

The Mojow system employs a series of stereo cameras installed around the vehicle to create a 360-degree unobstructed view of its environment. Everything runs through a proprietary controller called EYEBOX™, which automatically manages frame rates of anywhere between 10 and 30 images per second, depending on the vehicle speed and required job function.

EYEBOX™ is a small sensor outfitted with multiple cameras, a GPS, and a computer that processes data in real time. The system collects images automatically, passing them through a deep neural network that classifies each pixel to create or update a digital representation of the entire farming entity including field boundaries, entrances, and roads. The digital twin, or map, of a farm serves as the foundation of the autonomous navigation controller that guides the machinery and makes it autonomous. The continuous intake of real-time image data from the peripherals of the tractor assures a high level of relative position accuracy between the vehicle and any physical object encountered within its working environment.

As part of the CAAIN-funded project, the Mojow team is addressing real-time detection of, and response to, all relevant external and internal field boundaries, the detection of all types of field entrance, the response all roadway types, specifically dirt and gravel roads and double track trails.

EYEBOX™ is designed to operate ISO 11783-certified farm implements such as air seeders, sprayers, and fertilizer spreaders. However, Mojow intends to start with land rolling and heavy harrowing before adding tools that apply product.

CAAIN CEO Darrell Petras said the project ticks several boxes as it is a Canadian company developing technology that will provide significant value to domestic farmers.

“The solution in question relies on artificial intelligence and machine learning at a time when individuals, companies, and governments are recognizing the tremendous benefits that can accrue to agriculture through the appropriate application of advanced computing,” Petras said. “This is the kind of R&D our growing system of smart farm networks was designed to evaluate and demonstrate.”

Petras said CAAIN is able to fund the tech’s development and the means to ensure its adoption and eventual commercial success if it proves effective.

alice.mcfarlane@pattisonmedia.com

On X: @farmnewsNOW

View Comments