stack-of-tasks/pinocchio

A fast and flexible implementation of Rigid Body Dynamics algorithms and their analytical derivatives

View on GitHub ↗Jump to charts ↓Open shareable report

Summary Information

Updated 24 minutes ago
Added to GitGenius on September 18th, 2026
Created on October 7th, 2014
Open Issues & Pull Requests: 105 (+0)
GitHub issues: Enabled
Number of forks: 577
Total Stargazers: 3,745 (+0)
Total Subscribers: 69 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 2.3 hours
Mean response time: 16.4 days
90th percentile: 14.7 days
Tracked items: 187

Most active contributors

Sign in to see contributor activity.

How this project is maintained

About 12% of issues opened in the past year have never received a reply. 80% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Work labelled "bug" is answered fastest, typically in about 7 hours, while "feature request" waits about 2 days. 65% of issues opened in the past year have been closed, leaving a working backlog. Three people close 66% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 55
New in 7 days: 1
Closed in 7 days: 0
Avg open age: 511 days
Stale 30+ days: 33
Stale 90+ days: 32

Recent activity

Opened in 7 days: 1
Closed in 7 days: 0
Comments in 7 days: 2
Events in 7 days: 5

Top labels

  • bug (24)
  • feature request (20)
  • ready (8)
  • c++ (7)
  • core developers (7)
  • binding (1)
  • ci (1)
  • help wanted (1)

Detailed Description

Pinocchio is a C++ library for efficient rigid body dynamics computation and analytical differentiation of dynamics algorithms.

The library solves the problem of computing dynamics, kinematics, and their derivatives for articulated mechanical systems. It implements state-of-the-art rigid body algorithms including the Recursive Newton-Euler Algorithm and the Articulated-Body Algorithm, with analytical derivatives built in rather than computed numerically. The tool handles closed-loop kinematic mechanisms and frictional contact problems, and enables gradient-based optimization and learning by providing exact derivatives of physics computations.

Pinocchio suits researchers and practitioners working on robot control, motion planning, and physics-based simulation who need both forward dynamics computations and their gradients. While originally designed for robotics, it applies to biomechanics, computer graphics, and vision applications. The library builds on Eigen for linear algebra and coal for collision detection, and provides a Python interface alongside its C++ core, making it accessible for rapid prototyping through standard package managers.

The project maintains active development with comprehensive documentation and online resources. Test coverage is tracked and reported publicly. The codebase uses pre-commit checks to maintain code quality standards across contributions.