Trajectory Optimization Python Packages

nyx-space

Nyx is a high fidelity, fast, reliable and validated astrodynamics toolkit library written in Rust and available in Python

dymos

Open Source Optimization of Dynamic Multidisciplinary Systems

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

copp-py

Convex-Objective Path Parameterization

libcrocoddyl

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

asset-asrl

High-speed, extensible, object-oriented trajectory design and optimization

pycddp

Constrained Differential Dynamic Programming Solver for Trajectory Optimization and Model Predictive Control

qpmpc

Model predictive control in Python based on quadratic programming

mpopt

A pseudo-spectral collocation based multi-phase Optimal control problem solver

pyoptas

OpTaS: An optimization-based task specification library for trajectory optimization and model predictive control.

ivy-robot

Functions and classes for gradient-based robot motion planning, written in Ivy.

lqrax

GPU-friendly, auto-differentiable LQR solver with JAX.

invariants-py

Calculate invariant trajectory representations from trajectory data and generate new trajectories from the invariants.

ltv-mpc

Model predictive control in Python based on quadratic programming

barrier-states-python

Python library for Barrier States (BaS) safe control and safety-embedded systems.

pockit-optimal-control

pockit: Python Optimal Control KIT

caliper-robotics

Open robotics engine in Rust — kinematics, IK, dynamics, planning, control, datasets. One engine, three faces: desktop app, CLI, Python.

clap-family

Conservative Lapse-Action Planning (CLAP): a variational access-and-dwell framework for safe AI optimization. Surf the conservative-lapse field to the best safe basin and dwell there — theorem-backed, pip-installable, with differentiable PyTorch training adapters.