booster_mjlab: open-source sim-to-real training stack for the Booster K1 humanoid
kevin_zakka · x · 2026-09-19
- A team released boostermjlab, an mjLab integration for the Booster K1 humanoid: robot model, training tasks, and an AMP motion-prior pipeline spanning simulation to the real robot.
- Tasks include AMP-based velocity tracking and motion tracking (enabling acrobatics), with motion references retargeted from LAFAN1 onto the K1's parallel-ankle design; a built-in viewer lets you browse, play back, and edit clips before training.
- An in-browser interactive demo runs the exported policy at 50 Hz in MuJoCo compiled to WebAssembly (14 MB), controllable via joystick, WASD, or gamepad.
- On hardware, the AMP velocity policy walks after 30k training steps. The project comes from the whIRLwind team, which focuses on robot football and is recruiting students and collaborators.
More from Embodied
- Dev diving into robot post-training says the robotics ChatGPT moment is near — LoganGrasby · 2026-09-19
- Toyota to Deploy 400,000 Robots to Work Alongside Factory Staff — Recoil42 · 2026-09-19
- GPT-6 Astra solves tricky spatial tasks, sparking 'GPT moment for robotics' jokes — burny_tech · 2026-09-19
- Robots are easier to parallelize than cars and can help build themselves — teortaxesTex · 2026-09-19
- Robot fight PR spat: cixliv accused of hiding behind 'the influencer wanted it' — KyleMorgenstein · 2026-09-19
- Astra Solves in One Shot What a Robotics Team Spent Two Years Building — YuXiang_IRVL · 2026-09-19