# loco-3d/crocoddyl

Crocoddyl is an optimal control library for robot control under contact sequence. Its solver is based on various efficient Differential Dynamic Programming (DDP)-like algorithms

Repository: https://github.com/loco-3d/crocoddyl
Canonical: https://ross.abutalabs.com/products/crocoddyl
Language: C++
License: BSD-3-Clause
License Family: permissive
Topics: optimal-control, motion-planning, differential-dynamic-programming, legged-robotics, model-predictive-control, code-generation, ros, conda, crocoddyl, robotics, trajectory-optimization
Last push: 2026-08-26T12:32:11+00:00

## Health v2 (maintenance only)
Score: 89/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 71, longevity 100
- inputs: {"age_days": 2647, "days_push": 7, "days_rel": 115, "gap_med": 67, "n_releases_24m": 6}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1285, forks 213 (observed 2026-08-28T04:04:14.763532+00:00)

## What it is
Crocoddyl is an open-source optimal control library for robot control under contact sequences, computing optimal trajectories and feedback gains using efficient Differential Dynamic Programming (DDP)-like solvers. It is written in C++ with Python bindings and leverages Pinocchio for fast rigid-body dynamics and analytical derivatives.

## Use cases
- compute optimal trajectories for legged robots with contact sequences
- implement model predictive control for robotic manipulators
- solve trajectory optimization problems with DDP algorithms
- generate feedback gains for whole-body robot control
- plan dynamic motions like jumping or running for quadrupeds
- prototype optimal control solvers in Python with C++ performance

## When to choose
- you need real-time optimal control or MPC for robots with contact dynamics
- you want efficient DDP-based trajectory optimization with analytical derivatives
- you work with Pinocchio and need a compatible optimal control layer
- you need both C++ performance and Python bindings for robotics research

## When to avoid
- you need a general-purpose nonlinear optimizer unrelated to robot dynamics
- you want a plug-and-play motion planner without formulating optimal control problems
- your project requires a permissively integrated GUI or simulation environment out of the box

## Facets
- artifact type: library
- maturity: active
- function: simulation, robotics, math
- domain: robotics
- platform: windows, python, cpp
- tags: optimal-control, differential-dynamic-programming, trajectory-optimization, model-predictive-control, legged-robotics, motion-planning, pinocchio, optimization, algorithms, research, linux, macos

## Member repositories
- loco-3d/crocoddyl (main) score 89

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:14.763532+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:56:40.437978+00:00, confidence not recorded.
  - readme: https://github.com/loco-3d/crocoddyl (fetched 2026-08-28T04:04:14.763532+00:00, sha 0464a2b3db61)
- Data as of 2026-08-30T08:39:29.467469+00:00.