WHY IT MATTERS: Autonomous equipment is advancing quickly on roads, but farm fields present a different set of challenges.

The work was discussed during a recent presentation at St. Jean Farm Days in early January. Researchers with the project are focused on the challenge of uncertainty in agricultural environments, and obstacles to realistic adoption of the technology.

“We want the robot or tractor or any machine working in the agriculture field to follow the design path as accurately as possible,” said Jay Wang, an assistant professor with the University of Manitoba’s faculty of mechanical engineering.

Many modern road vehicles are now equipped with some form of autonomous control. With that in play, people may tend to think that fields, with their wide open spaces free of pedestrians or heavy traffic, would be a comparative slam dunk.

But Wang, who also heads up his department’s Robotics Lab, points out that farms present unique problems:

• Fields are bumpy
• Conditions are constantly changing
• Precipitation can change ground texture
• Crop residue can create obstacles
• Soil compaction differs across the field

By contrast, a flat, hard road, defined by lane markings and supported by traffic signals and signage, is much easier terrain for artificial intelligence (AI) to navigate.

Searching for autonomous adaptability

The University of Manitoba research looks at ways machines can adapt to that volatility in field conditions. The approach takes traditional engineering models, contrasting it with collected data as equipment moves through the field. That data is then processed through machine learning or artificial intelligence.

“The AI tool we use is called Gaussian process,” Wang said. “It is used to correct the discrepancy between the physical-based model and the actual observed data.”

To test the concept, researchers are using small robotic platforms equipped with GPS and other onboard navigation sensors like LiDAR and RTK, “basically, so the robot knows where it is in the real-world environment,” said Wang.

The experiments were conducted on University of Manitoba agricultural plots. The robots follow set paths while collecting data on how their real-world movement differs from expected behaviour. That information is then used to refine how the machine responds in different field conditions.

Bringing autonomy to the farm

Commercial autonomous farm systems already exist, but they typically work within tightly defined tasks and operating conditions, and require human supervision. Wang’s research, by contrast, is looking at ways to reduce the need for operators to compensate when the ground doesn’t behave as expected.

The work is still in its early stages and Wang doesn’t expect it to translate into near-term, farm-ready technology. However, he said the work is ultimately intended to benefit farmers.

“We want to use AI to boost agriculture,” Wang said. “That’s the whole reason we’re interested in it.”

The post Autonomous machinery still struggles in the field appeared first on Manitoba Co-operator.

WHY IT MATTERS: Today’s farms generate more data, use more technology, incorporate more computers and connectivity and have more digital sophistication than at any point in history.

At Brandon’s Assiniboine College, Chris Budiwski, the interim dean of the Russ Edwards School of Agriculture and the Environment, has seen the shift firsthand.

“Agriculture is often an early adopter of innovation and technology, and the skill sets are changing,” Budiwski said during a Dec. 4 Manitoba Agriculture webinar.

The event tackled agriculture’s growing automation and technology skills gap.

That gap has underpinned the college’s agriculture-related expansion in the last few years. Assiniboine College is in the last push to a new home for its ag-related programs, the Prairie Innovation Centre for Sustainable Agriculture. Expanded syllabus and research plans (some of which have already launched) span digital agriculture training, mechatronics, greenhouse horticulture, and other tech-heavy areas. That’s on top of existing programs like GIS (geographic information systems) and communications engineering technology programs.

Local agribusinesses have also been brought on during program development to help tailor the material to increasingly sophisticated labour needs.

“We’ve always said we’re Manitoba’s ag college, and we’re really doubling down on that,” Budiwski said.

It’s a problem for productivity, an area where Farm Credit Canada (FCC) worries Canadian agriculture has slackened pace considerably. After hitting two per cent growth rates two decades ago, the sector managed only 1.3 per cent growth in the 2010s and could dip below one per cent without intervention, said a Dec. 2 report.

The agency identifies two major obstacles to productivity: companies aren’t investing enough in agricultural research, and venture capital backing for ag-tech startups remains weak.

“There’s fewer and fewer people that understand kind of the robotics and barns and the sensors that are being used,” Ashton said.

RBC recently invested $5 million in Manitoba agriculture, including funding for hackathons and micro-credentials to help attract students to the sector, whether or not they come from a farm.

“We’re hearing that there’s more and more demand for action on exposing more people to the agricultural career opportunities, but then also ensuring that we’re preparing the students that are entering the agricultural workforce have the right skills and are really actually job ready,” Ashton said.

“Agriculture sector technology has advanced more rapidly than many sectors out there,” he said.

These include incoming technologies like AI-driven sprayers that can target individual weeds and a fully autonomous tractor that John Deere revealed at Consumer Electronics Show 2022. John Deere has said that by 2030, a complete fleet of autonomous equipment will be available for purchase, including self-driving machines.

With machines evolving at that pace, dealerships need people who can diagnose electronics and software.

“There’s less wrench turning work and more diagnosing computers, electronics and controllers,” Bohn said. “We don’t even rebuild engines anymore. They all come as remanufactured engine(s) from the factory, and then they have them bolted and take it out and put the other one in.”

Budiwski agreed the shift is happening across agriculture. Dairy barns, hog barns, vertical farms and greenhouses now run on sensors and automation.

“They’re not your traditional romantic pitchfork and red barn imagery. It is computer science. It is programmable logic controllers and being able to diagnose these systems on different platforms,” he said.

Increasingly, agriculture is becoming just as much about prioritizing problem solving, communication, critical thinking and technical know-how as it is familiarity with farming.

“We need to take these people with zero background, or next to zero background, and give them a little bit of an introduction to agricultural fundamentals,” Budiwski said.

One teacher told him several students changed their university plans after seeing the equipment in action.

“Seeing has such a greater impact than just talking,” he said.

There’s a big opportunity to invite people into agriculture who may not think of themselves as “ag” but are passionate about the food system, Ashton said.

The post VIDEO: Technical skills gap looms for agriculture appeared first on Manitoba Co-operator.