Videos of an incredibly acrobatic, nimble, and graceful John Deere 5-ton skid-steer loader have been shared by a group of researchers from the U.S. and Switzerland. A recently published paper titled Heavy Metal Acrobatics provides the reasoning behind this eyebrow-raising autonomous robotics feat. It is hoped this research will be useful in the future automation of heavy machinery in industries like construction, mining, and material handling. It also demonstrates that reinforcement learning in a simulation can transfer remarkably well to the real world.
Researchers have used reinforcement learning to teach a 5-tonne John Deere skid-steer loader to perform complex acrobatic manoeuvres autonomously. Trained in simulation and transferred to a real machine, the system can balance on two wheels, navigate rough terrain, spin, and control its bucket before landing safely.
The research demonstrates the potential of AI-driven automation for heavy construction and industrial machinery.
Video Credit: @leggedrobotics / @ETH
Paper: https://t.co/MT7fyZ54Hk
#engineering #technologyNovember 17, 2026
If you unfurl the video embed above, you can see a hulking 332G skid-steer do some astonishing tricks. It hops back and forth on two wheels, pirouettes, and balances while flexing its lift arm. Moreover, it does these moves while never looking like it will teeter over. The researchers claim that “only a handful of elite human operators” have ever been able to pull off stunts as you see in the demo videos.
The technology behind the remarkable acrobatic skid-steer is mostly Reinforcement Learning (RL), with physics modeling and neural network models. As machinery like this is so big, powerful, and bulky, undertaking RL directly on the hardware wasn’t deemed practical. Instead, the research team decided to use a simulation programmed with the John Deere 332G’s complex array of controls for training. This data was subsequently applied to the actual skid-steer via a sim-to-real transfer. The simulations must be extremely accurate.
This acrobatic goliath is impressive, but of course there’s an underlying goal driving Heavy Metal Acrobatics’ research. The scientists are laying the foundations for the enabling of “dynamic autonomous control of heavy machinery.” It is hoped this will help promote greater automation in heavy equipment sectors of industry. Eventually, autonomous control should be safer, faster, and more efficient than any human.
With these video demonstrations of nimble and highly maneuverable heavy machinery, it is clear that there’s more scope for AI-driven automation than one may have previously expected. Furthermore, it looks like being a skilled heavy machinery operator is definitely not an AI-proof occupation.
Get Tom's Hardware's best news and in-depth reviews, straight to your inbox.
Mark Tyson is a news editor at Tom's Hardware. He enjoys covering the full breadth of PC tech; from business and semiconductor design to products approaching the edge of reason.