pin-pink
Inverse kinematics for articulated robot models, based on Pinocchio.
Decision gist · record as of 2026-08-14
Yes. Pink is actively maintained, has no known vulnerabilities, installs with low friction, and is licensed permissively. It is production-stable and well-suited for anyone building task-based inverse kinematics solvers for articulated robots. Install it if you need to control multi-objective robot motion; skip it if you only need forward kinematics or single-task IK.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires a Pinocchio robot model and configuration object; the package expects numpy arrays and assumes familiarity with robot kinematics concepts (Jacobians, task residuals).
- Low install friction with a pure Python wheel.
- Active maintenance with a recent release 30 days ago and steady repository activity.
License · maintenance · safety
permissive license (permissive) — Licensed under Apache 2.0 (permissive), allowing commercial and private use with minimal restrictions.
last release 2026-07-15 (30 days) · last repo commit 2026-07-25 · 817 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 264,025 downloads/mo, #8,345 on PyPI
Alternatives
Verify before relying
pip install pin-pink
from pink.tasks import FrameTask, PostureTask
from pink import Configuration, solve_ik
import numpy as np
tasks = {
"base": FrameTask("base", position_cost=1.0, orientation_cost=1.0),
"posture": PostureTask(cost=1e-3),
}
dt = 6e-3
for t in np.arange(0.0, 10.0, dt):
velocity = solve_ik(configuration, tasks.values(), dt, solver="quadprog")
configuration.integrate_inplace(velocity, dt)- Whether Pinocchio must be pre-installed or is handled as a transitive dependency through the listed runtime deps.
- Performance characteristics when solving IK for robots with many degrees of freedom.
- Compatibility with specific robot description formats beyond URDF.
What it is and what it does
Pink is a Python inverse kinematics solver built on top of Pinocchio for controlling articulated robots. It formulates robot motion as a set of weighted tasks—such as positioning a foot, orienting a base, or maintaining a preferred posture—and solves a quadratic program to compute joint velocities that satisfy all tasks simultaneously while respecting joint limits. The solver handles task conflicts by normalizing objectives and weighting them relative to each other, making it suitable for complex multi-objective control problems on robots ranging from simple arms to humanoids and quadrupeds.
The package provides a task-based API where you define residual functions (e.g., desired frame position minus current position) and costs, then call solve_ik to get a velocity command. It integrates with Pinocchio's robot models and supports floating-base velocity limits for robots with free-flyer or planar bases. The solver outputs differential velocities that can be integrated over time to reach target configurations, or continuously tracked if targets change.
Use it for
- Control a multi-limb robot (humanoid, dual-arm, or quadruped) to simultaneously achieve multiple frame and posture objectives.
- Solve inverse kinematics for a manipulator arm with end-effector position and orientation targets plus joint regularization.
- Track moving targets in real-time by continuously updating task targets and integrating the solver's velocity output.
- Enforce floating-base velocity limits on legged robots to clamp commanded linear and angular velocities.
- Resolve conflicting task objectives (e.g., foot contact vs. base orientation) by weighting normalized costs.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
Pink is actively maintained, has no known vulnerabilities, installs with low friction, and is licensed permissively. It is production-stable and well-suited for anyone building task-based inverse kinematics solvers for articulated robots. Install it if you need to control multi-objective robot motion; skip it if you only need forward kinematics or single-task IK.
Install
pin-pink on PyPI
Before you install
Low install friction with a pure Python wheel. Active maintenance with a recent release 30 days ago and steady repository activity. Supports current Python versions (3.10–3.14).
Requires a Pinocchio robot model and configuration object; the package expects numpy arrays and assumes familiarity with robot kinematics concepts (Jacobians, task residuals).
License in practice
Licensed under Apache 2.0 (permissive), allowing commercial and private use with minimal restrictions.
Quickstart
pip install pin-pink
from pink.tasks import FrameTask, PostureTask
from pink import Configuration, solve_ik
import numpy as np
tasks = {
"base": FrameTask("base", position_cost=1.0, orientation_cost=1.0),
"posture": PostureTask(cost=1e-3),
}
dt = 6e-3
for t in np.arange(0.0, 10.0, dt):
velocity = solve_ik(configuration, tasks.values(), dt, solver="quadprog")
configuration.integrate_inplace(velocity, dt)Verify before relying
- Whether Pinocchio must be pre-installed or is handled as a transitive dependency through the listed runtime deps.
- Performance characteristics when solving IK for robots with many degrees of freedom.
- Compatibility with specific robot description formats beyond URDF.
Package facts
| License | permissive license permissive |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 5 packagesloop-rate-limitersnumpypinqpsolverstyping-extensions |
| Maintenance | Actively maintained 30 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 264,025 / month, #8,345 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableFramework :: Robot Framework :: LibraryIntended Audience :: DevelopersIntended Audience :: Science/ResearchLicense :: OSI Approved :: Apache Software LicenseProgramming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Topic :: Scientific/Engineering |
Evidence: pin_pink-4.3.0-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “task-based robot control”
- pin-pinkPink solves differential inverse kinematics for articulated robots by…
- flexivrdkFlexiv Robotic Development Kit (RDK) provides Python bindings to…
- pylitterbotControl Whisker Litter-Robot and Feeder-Robot devices through an…
Give your agent the search over MCP, or paste the wish link into any chat.
More Scientific/Engineering packages
NumPy provides an N-dimensional array object and a comprehensive suite of mathematical, linear algebra, Fourier transform, and random number functions for scientific computing in Python.
pandas provides fast, flexible data structures (Series and DataFrame) for loading, cleaning, transforming, and analyzing labeled or relational data in Python.
scipy provides numerical algorithms for mathematics, science, and engineering—including optimization, integration, linear algebra, Fourier transforms, signal and image processing, and ODE solvers—built on numpy arrays.
scikit-learn provides a comprehensive Python library for supervised and unsupervised machine learning, including classification, regression, clustering, dimensionality reduction, and model evaluation tools built on NumPy and SciPy.
Install it if you need to train, evaluate, or deploy supervised or unsupervised learning models.
dill extends Python's pickle module to serialize and deserialize a much wider range of Python objects, including functions, lambdas, classes, and interpreter sessions, to byte streams for storage or network transmission.
Multiprocess is an enhanced fork of Python's standard multiprocessing library that uses dill for better serialization, allowing you to spawn processes with a threading-like API and share complex objects between them.
Install it if you use multiprocessing and encounter pickle serialization limits with lambdas or complex objects.
See also mink · dex-retargeting · pin · toppra · libpinocchio · quadprog · robosuite · python-motion-planning · daqp