PyRoki

A Modular Toolkit for

Robot Kinematic Optimization

Chung Min Kim *
Brent Yi *
Hongsuk Choi
Yi Ma
Ken Goldberg
Angjoo Kanazawa

UC Berkeley

*Denotes Equal Contribution

(Python Robot Kinematics)

TL;DR: PyRoki is a modular, extensible, and cross-platform toolkit for kinematic optimization.

We unify problems like inverse kinematics, trajectory optimization, and motion retargeting using composable kinematic variables and costs. PyRoki aims to support a broad variety of robots and tasks, and runs on CPU, GPU, and TPU -- fully in Python.

Citation

@misc{pyroki2025,
    title={PyRoki: A Modular Toolkit for Robot Kinematic Optimization}, 
    author={Chung Min Kim* and Brent Yi* and Hongsuk Choi and Yi Ma and Ken Goldberg and Angjoo Kanazawa},
    year={2025},
    eprint={2505.03728},
    archivePrefix={arXiv},
    primaryClass={cs.RO},
    url={https://arxiv.org/abs/2505.03728}, 
}