Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

PyRoki: A Modular Toolkit for Robot Kinematic Optimization

About

Robot motion can have many goals. Depending on the task, we might optimize for pose error, speed, collision, or similarity to a human demonstration. Motivated by this, we present PyRoki: a modular, extensible, and cross-platform toolkit for solving kinematic optimization problems. PyRoki couples an interface for specifying kinematic variables and costs with an efficient nonlinear least squares optimizer. Unlike existing tools, it is also cross-platform: optimization runs natively on CPU, GPU, and TPU. In this paper, we present (i) the design and implementation of PyRoki, (ii) motion retargeting and planning case studies that highlight the advantages of PyRoki's modularity, and (iii) optimization benchmarking, where PyRoki can be 1.4-1.7x faster and converges to lower errors than cuRobo, an existing GPU-accelerated inverse kinematics library.

Chung Min Kim, Brent Yi, Hongsuk Choi, Yi Ma, Ken Goldberg, Angjoo Kanazawa• 2025

Related benchmarks

TaskDatasetResultRank
Inverse KinematicsPanda Arm open-world random target (test)
Execution Time (ms)13.96
20
Inverse KinematicsFetch Arm open-world random target (test)
Time (ms)12.92
20
Collision-free Inverse KinematicsMotionBenchMaker box_panda
Execution Time (ms)34.04
15
Inverse Kinematicsopen-world random target benchmark synthetic arm
Time (ms)15.09
12
Reference TrackingSquat movement
Mean Laplacian Error (m)0.057
6
Reference TrackingOne-foot balance movement
Joint RMSE0.848
5
Inverse KinematicsPanda Arm
MMD0.0451
4
Keypoint trackingKung fu
Laplacian Error0.062
3
Keypoint trackingPistol Squat
Laplacian Error0.057
3
Keypoint trackingBalancing Stick
Laplacian Error0.048
3
Showing 10 of 28 rows

Other info

Follow for update