How the future of Australian agriculture is automation


The reason is known as Moravec’s paradox. Machines are wonderful at doing things humans struggle with, like quantum physics, but struggle with basic physical actions that people find simple.

“It seems like one of the most intuitive things humans do, you take a person to an orchard and they just pick an apple,” says Leopold Lucas, co-founder of another start-up called Ripe Robotics. works on a machine to do just that.

A Ripe Robotics machine being tested in an apple orchard. Each test run gathers data that improves the machine’s algorithms.

For a robot, the challenges are multiple. Unlike a warehouse, where automation is becoming commonplace, there are no smooth surfaces for a robot to navigate in an orchard. There are no road maps to follow. No two apples are exactly alike and no two trees grow the same. This means that every time a robot goes to pick an apple, it needs to be smart enough to scan the whole tree and figure out what it’s aiming for and how to get there without getting caught in a branch. Next, Eve, Ripe’s current test robot, named after the biblical picker of forbidden fruit, must apply just enough pressure to pull the fruit from the tree without leaving the slightest mark that can lead supermarkets to reduce its 90% price. And that’s before considering the weather.

“You have to do it on the pitch, where it can be windy, rainy, snowy, 40 degree heat. It gets difficult, very dusty,” says Lucas. “It is difficult to identify the fruit and assess its maturity, especially under different lighting conditions.”

After all, one of the main selling points of robots is that they can work in conditions that humans cannot, such as in the dark, and for longer hours than people who need food, drink, rest and bathroom breaks. There could also be benefits in tracing where food comes from and analyzing its quality, but that means robots need to have the durability and power supplies to go the distance.

Conditions are not as complex in a packing shed, but the basic challenge of grabbing and moving unevenly shaped fruit quickly remains.

Lyro co-founder Dr Nicole Robinson, who has a background in robotics at Queensland University of Technology, says there is a scale of difficulty. Regular, broadly spherical fruits like apples are among the easiest for a machine to grip. Sweet potatoes, which come in a range of sizes and twists, are in the middle. Small and capricious berries are among the toughest.

Ripe tried different types of gripping mechanisms to pluck apples from a tree.  A vacuum tube turned out to need too much power.  Now a gripping hand uses compressed air to suck apples from trees.

Ripe tried different types of gripping mechanisms to pluck apples from a tree. A vacuum tube turned out to need too much power. Now a gripping hand uses compressed air to suck apples from trees.

But there have been a host of innovations in recent years that make the challenge surmountable. Computer chips have become much faster and more efficient, allowing robots to perform more complex tasks. Vision systems, which allow them to identify objects, have improved considerably. Rural Internet is faster and more reliable. And even some farming practices — like planting apple trees on trellises that make it easier for machines to navigate orchards — help, too.

Robinson says the combination of advancing technology with a major problem to solve is what drew her to the industry. “There’s a lot of food waste that happens if you can’t pick and pack fruit in time. You know, millions of tons are wasted every year.

Food losses on farms have a variety of causes: disease, market prices and weather, as well as insufficient labor, but Robinson is right about its cost. A 2015 report by a government-industry-university research center estimated it at almost $3 billion a year in Australia alone.


There is also, according to Lyro chief executive Mark Adams, the opportunity to move workers from difficult, boring and repetitive tasks on farms to higher-skilled, better-paying jobs. This could mean things like analyzing products, supervising machines and performing skilled maintenance. Boardman hopes it will go that way too.

There are many roles in the first category.

It’s someone’s job to put a little hot glue on each of the thousands of pineapples that go down a conveyor belt for eight or 10 hours a day and someone else’s job to apply a sticker, Adams said. It’s someone’s job to put, say, 42 peaches in each tray: no more, no less. Someone has to cut every cabbage, bent in heat or cold. Laborers and machine operators, common on farms, have some of the highest rates of serious workplace injuries of any occupation, according to statistics from Safe Work Australia.

And on unscrupulous farms, underpayments are commonplace. In 2018, audits by the Fair Work Ombudsman revealed that more than 200 companies in the sector were in breach of wage laws; when he checked again in 2020, only one in five had their issues resolved.

But agricultural work also has advantages. It helps support regional centers that, at least before the pandemic, were struggling with population loss. And governments on both sides of politics have defended Australia’s deals with Pacific island countries to grant visas to farmworkers, arguing they provide workers with skills, money to send to family and are a way to deepen ties in the region at a time when competition for influence with China is fierce.

Agricultural work can be exhausting, repetitive and carried out under difficult conditions.

Agricultural work can be exhausting, repetitive and carried out under difficult conditions.Credit:PA

The United Workers Union, which represents horticultural workers, refused to make a manager available for an interview.

Even if Adams is right and agricultural workers are becoming more skilled, it seems likely that automation will mean there will be fewer of them in the future, at least seasonal workers. The economy does not work otherwise.


For now, Lyro and Ripe are small businesses, with the former’s latest raise totaling around $1.5 million in capital and grants, while the latter got around $1.2 million in raises and capital. important.

The two plan to raise more money from investors to continue developing their robots, despite tough seed fundraising conditions, with Lyro estimating it will need to spend a few million more to achieve major commercial scale at lease to farmers at an expected cost of approximately $7,000 to $8,000 per month. This model means they can move them from farm to farm as different crops come into season.

Ripe is experimenting this year in deals with farmers where it tries to match human costs of about $60 per bin of apples picked. Once he proves his concept by choosing a full bachelor’s degree, Lucas says Ripe hopes to raise $3-5 million to hire staff and expand his fleet of robots.

Boardman, the avocado grower, says he will only use robots on a large scale if they are as fast as a human and comparable in price.

“I think we’ll find that it will take some time for robots to reach the speed of a human,” Boardman says. “What the human body is capable of is truly amazing, compared to what robots can still do.”

MorningThe ing Edition newsletter is our guide to the most important and interesting stories, analysis and ideas of the day. register here.


Comments are closed.