Jacobian Python Packages

pytorch-kinematics

Robot kinematics implemented in pytorch

jenn

Jacobian-Enhanced Neural Networks (JENN) are fully connected multi-layer perceptrons, whose training process was modified to account for gradient information. Specifically, the parameters are learned by minimizing the Least Squares Estimator (LSE), modified to minimize prediction error of both response values and partial derivatives.

roboticstoolbox-python

Robotics Toolbox for Python

jaxsim

A differentiable physics engine and multibody dynamics library for control and robot learning.

synria-robocore

Unified High-Throughput Robotics Library

asdex

Automatic Sparse Differentiation in JAX.

fastdual

forward-mode automatic differentiation via dual numbers as a CPython C extension

pytorch-kinematics-ms

Robot kinematics implemented in pytorch

nngeometry

{KFAC,EKFAC,Diagonal,Implicit} Fisher Matrices and finite width NTKs in PyTorch

disptools

Generate displacement fields with known volume changes

autograv

Automatic differentiation for numerical relativity using JAX

undefined-ad

An awesome and fast automatic differentiation calculation tool using Automatic Differentiation (supporting both forward and reverse mode).