elijah-waichong-chan/go2-convex-mpc ? reverse-engineered prompt

Reverse engineered prompt

Build me a Python project that simulates the Unitree Go2 quadruped in MuJoCo and uses a convex MPC controller to make it walk in a stable trot.

I want it to handle forward, backward, sideways, and turning motion, with a simple command driven demo so I can run a few example scripts and see the robot move in simulation. Please include the full locomotion stack, body motion planning, foot placement, swing leg motion, and force based control for the stance legs. It should also show useful plots after each run, like timing, forces, torques, and the robot’s motion over time.

Make it easy to install and run from the repo root, and set it up so the package can be imported cleanly in Python. If you need to check the latest docs for MuJoCo, Pinocchio, or CasADi, feel free to look them up online.

Are you gonna build this?

make sure you review the code using coderabbit

Try freeSponsored — opens CodeRabbit in a new tab