M5Stack Workshop: Training Self-Balancing Robots with RL from Sim to Hardware

ShawnHymel · x · 2026-07-31

Shawn Hymel, in collaboration with DigiKey and M5Stack, is hosting a hands-on workshop on training a two-wheeled self-balancing robot using reinforcement learning (RL).

The curriculum covers measuring the physical robot, creating a simplified model in FreeCAD, exporting physics data, and building a MuJoCo digital twin ready for RL. The ultimate goal is deploying the trained model from simulation to real hardware.

Original post →

More from Embodied

Embodied channel →