cd /news/robotics/heavy-metal-acrobatics · home › topics › robotics › article
[ARTICLE · art-171380] src=sites.google.com ↗ pub= topic=robotics verified=true sentiment=↑ positive

Heavy Metal Acrobatics

Reinforcement learning policies trained in simulation and transferred to reality autonomously performed acrobatic maneuvers on a John Deere 332G, an operational 5-tonne skid-steer loader, according to the research. The policies swing the machine onto two wheels and, while balancing, drive over rough terrain, trace specified trajectories, spin, and swing the bucket before landing back on four wheels — maneuvers previously accomplished only by a small number of elite human operators in official world-record performances. The work demonstrates that RL and sim-to-real transfer enable dynamic autonomous control of heavy machinery for construction, mining, and material handling.

key takeaway

RL policies trained in simulation transferred to a real 5-tonne John Deere 332G skid-steer loader, autonomously balancing on two wheels, driving over rough terrain, tracing trajectories and spinning before landing safely on four wheels.

read1 min views7 publishedNov 17, 2026

Automation of heavy machinery offers the opportunity to improve productivity in mechanized industries such as construction, mining, and material handling. Yet, automation of such machines is challenged by their complex dynamics, in part because of hydraulic actuation that involves fluids, flexible elements, and nonlinear delays. A concomitant challenge is the size and weight of these machines, which can make experiments on the physical systems exceedingly dangerous. Here, we show that Reinforcement Learning (RL) in simulation, followed by transfer of the learned policies from simulation to reality, can successfully automate acrobatic maneuvers that push a heavy construction machine to the limits of its actuation and have only previously been accomplished by a small number of elite human operators in official world-record performances. We trained policies that perform autonomous acrobatic maneuvers on a John Deere 332G, an operational 5-tonne skid-steer . The policies can autonomously swing the machine up onto two wheels and, while balancing on two wheels, drive over rough terrain, trace out specified trajectories, spin around, and swing the bucket back and forth before landing it safely back onto four wheels. This work demonstrates that RL and sim-to-real transfer enable dynamic autonomous control of heavy machinery, directly contributing to greater automation in heavy equipment sectors.

Movie S1. Soft-landing controller compared to zero commands.

Movie S2. Linear velocity tracking at different target speeds while balancing.

Movie S3. Robustness to arm movement while balancing.

Movie S4. Robustness to spinning commands while balancing.

Movie S5. Driving over undulating terrain while balancing.

Movie S6. Case study: Super Mega Bot (SMB). Method overview, data-collection and experimental evaluation on the SMB.

── more in #robotics 4 stories · sorted by recency
── more on @john deere 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/heavy-metal-acrobati…] indexed:0 read:1min 2026-11-17 · —