Stanford open-sources frax: JAX robot kinematics with IK over 100k FPS, no GPU needed
ZeYanjie · x · 2026-11-05
Stanford's ASL lab released frax, a pure-Python robot kinematics and dynamics library built on JAX for JIT compilation and automatic differentiation (MIT license, 411 stars).
- Typical IK/inverse-dynamics controllers run in low microseconds on CPU (25-100 kHz);
- On GPU/TPU, dynamics terms compute at over 100 million per second depending on batch size;
- v0.2.0 adds frax.ik for humanoid retargeting and inverse kinematics at >100,000 FPS without a GPU, with perfect contact handling.
The goal: Pinocchio-level speed, Python ease of use, and MJX-style differentiation and parallelization.
More from Embodied
- CoRL paper GUILD: actively guiding robot data collection toward useful auxiliary tasks — RobobertoMM · 2026-11-05
- TAMPAgent at CoRL: coding agents + TAMP planning for zero-shot long-horizon mobile manipulation — dhadfieldmenell · 2026-11-05
- Raven Prism launches: a full Linux computer in glasses, controlled by eyes and voice — Scobleizer · 2026-11-05
- Johns Hopkins hosts 'Embodied AI in Healthcare' symposium on December 14 — mdredze · 2026-11-05
- How Hugging Face rebuilt robotics open source in 3 years, from LeRobot to RoboColosseum — DJiafei · 2026-11-05
- The CERN analogy fits robot evaluation: shared hardware, protocols and published failures — DJiafei · 2026-11-05