Shunichi09/PythonLinearNonlinearControl

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

1041 stars · 190 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Python library implementing linear and nonlinear control theory algorithms such as MPC, iLQR, DDP, MPPI, and CEM using only NumPy and SciPy. It ships reference implementations with example environments like cartpole and two-wheeled tracking for studying model-based control and model-based reinforcement learning.

Use cases

• implement model predictive control in python
• compare mpc ilqr ddp and mppi controllers
• learn nonlinear control theory with runnable examples
• prototype model-based reinforcement learning controllers
• simulate cartpole with a python control algorithm
• extend a control algorithm with custom dynamics and costs

When to choose

• you want pure-python reference implementations of classic and sampling-based control algorithms
• you need a lightweight codebase built only on numpy and scipy that is easy to modify
• you are studying or teaching optimal control and model-based RL methods
• you want to test controllers on simple environments like cartpole or a two-wheeled robot

When to avoid

• you need real-time or hard real-time control performance in compiled code
• you require a maintained production library with active releases and support
• you need GPU acceleration or large-scale robotics stacks like ROS integration
• you want a no-code or GUI control design tool

Facets

library · maturity maintenance

simulation machine-learning reinforcement-learning math developer-tools robotics reinforcement-learning simulation education python cross-platform model-predictive-control mpc nmpc ilqr ddp mppi cem optimal-control control-theory model-based-rl cartpole scipy numpy algorithms

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Shunichi09/PythonLinearNonlinearControl")