ADAM (automatic differentiation for rigid-body dynamics)
- Software
- Humanoids and robot learning
- Library
A Python library that computes rigid-body dynamics for floating-base robots, with automatic differentiation across JAX, CasADi, PyTorch and NumPy backends sharing one interface.
Made by Generative Bionics, Italy (checked on github.com/gbionics (opens in a new tab)).
Source on GitHub: github.com/gbionics/adam (opens in a new tab). Facts read at commit b5bc641 (opens in a new tab).
Licenses
- Code
- BSD-3-Clause (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (BSD-3-Clause) at commit b5bc641 (opens in a new tab), on 16 Oct 2026.
- Commercial use
- Yes
What it does
- Computes mass matrix, Coriolis and gravity terms, forward kinematics, Jacobians and centroidal quantities for floating-base robots.
- Offers JAX, CasADi, PyTorch and NumPy backends that give numerically consistent results through the same interface.
- JAX backend supports jit compilation, vectorization and differentiation through XLA.
- PyTorch backend supports GPU acceleration and batched evaluation over many configurations.
- Loads robot models from URDF, MuJoCo objects and OpenUSD files, and can export models to USD.
- Includes a viser-based visualizer and an inverse kinematics solver built on CasADi.
Written by Robotheca from the project's README (opens in a new tab) at commit b5bc641.
Getting started
- Difficulty
- Intermediate
- How to start
- The project's website (opens in a new tab)
Maintenance
- Status
- Active: a commit in the last 90 days
- Newest commit
- 21 Sept 2026 on main
- Latest release
- v0.6.2 (21 Sept 2026)
Checked on GitHub on 16 Oct 2026.
Links
Robots that can run it
No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.
Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.