)
Cloncurry-founded agtech company SkyKelpie has successfully prototyped livestock herding algorithms in real-world paddock conditions, marking what it describes as a breakthrough in autonomous drone mustering after the technology was developed and tested in a simulation environment.
The trials were conducted across south-east and north-west Queensland as part of a collaborative project with Meat & Livestock Australia (MLA) and the Queensland Department of Primary Industries, with the company announcing the milestone this week.
SkyKelpie, which specialises in drone-enabled livestock mustering, now counts more than 600,000 head of livestock managed by its customers nationwide - double the 300,000 head founder Luke Chaplain reported at the EvokeAG agrifood innovation conference in April last year, where he flagged the company's trajectory toward what he termed "algorithmic-assisted mustering".
The leap from simulated to real-world autonomy represents a significant technical hurdle cleared, although Chaplain has been careful to describe the advance as augmentation rather than replacement of human stockmanship.
For Chaplain, a fourth-generation grazier, the project represents another stage in a journey that began with trialling small, affordable drones on his family's property near Cloncurry in north-west Queensland.
“It’s remarkable to see how far we’ve come from those early days testing what was possible, to now supporting producers across the country with tools that are genuinely changing the way livestock are managed,” he says.
“Seeing livestock herding algorithms move from simulation into real-world trials is a significant milestone, not just for SkyKelpie, but for the future of livestock management more broadly."
While the technology demonstrates promising results, SkyKelpie says the project also reinforces a critical lesson - that effective livestock management is about far more than simply moving animals from one location to another.
It says animal behaviour, terrain, environmental conditions, welfare outcomes and human judgement all play a role in successful livestock movement, and while automation will continue to advance, SkyKelpie believes the skill and adaptability of experienced stockhandlers will remain central to achieving positive outcomes.
“Our experience shows that commercialising AI in grazing is proving to be more about restraint than outright replacement,” says Chaplain.
“AI is becoming an incredibly powerful tool, but good stockmanship remains a highly human skill built around observation, timing and judgement.
"We see technology as something that should support graziers, not replace them.”
The approach places SkyKelpie at one end of an emerging debate within the autonomous mustering space about how much autonomy is too much.
Queensland-founded competitor GrazeMate raised $1.2 million in pre-seed funding led by Y Combinator in January this year for a fully autonomous drone mustering product built on reinforcement learning.
GrazeMate is piloting across 1.7 million acres in Queensland and NSW with a pitch centred on removing human operators from the loop entirely.
SkyKelpie's model, by contrast, keeps the grazier in the decision-making chain while offloading the repetitive and physically demanding elements of mustering to autonomous systems - a distinction Chaplain has consistently emphasised as critical to adoption among producers who remain sceptical of fully hands-off technology.
Now that a major breakthrough in automation has been achieved, SkyKelpie says the opportunity extends beyond mustering into a broader range of repeatable on-farm tasks where automation can play a role.
These may include livestock headcounts, pasture and biomass analysis, infrastructure and water monitoring, fence line inspections and identification of pests among other applications.
"Used in this way, AI could allow producers to spend less time on routine monitoring and more time focused on planning and executing their highest-priority tasks," says the company.
SkyKelpie is also applying AI within its own business with the company recently launching a customer portal integrating AI-powered support and troubleshooting tools, designed to help producers operating in rural and remote environments access information, solve problems and receive support more efficiently.
"As autonomous systems continue to evolve, the most important task ahead is to continue working closely with the company’s hundreds of customers across Australia," says SkyKelpie.
"This ensures future developments are shaped by producer needs and deliver meaningful, practical benefits to grazing operations - the same philosophy that has guided SkyKelpie from the very beginning."
)
