MPC Controller Skill

SkillAI & models

Expert skill for Model Predictive Control implementation and tuning

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; ahel provides instructions and does not run this skill.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the MPC Controller Skill skill

What this skill tells your AI

The instructions your AI receives, as published by a5c-ai/babysitter in library/specializations/robotics-simulation/skills/mpc-controller/SKILL.md and read by ahel’s review.

Overview

Expert skill for designing, implementing, and tuning Model Predictive Controllers for robotic systems, including both linear and nonlinear MPC.

Capabilities

Derive kinematic and dynamic robot models
Formulate MPC optimization problems (QP, NLP)
Configure CasADi for symbolic differentiation
Set up ACADO code generation for real-time MPC
Implement constraint handling (velocity, acceleration, collision)
Configure cost function weights (tracking, control effort)
Implement warm starting for fast convergence
Set up NMPC for nonlinear systems
Configure terminal constraints and costs
Optimize solver parameters for real-time execution

Target Processes

mpc-controller-design.js
trajectory-optimization.js
dynamic-obstacle-avoidance.js
path-planning-algorithm.js

Dependencies

CasADi
ACADO Toolkit
OSQP
qpOASES
Ipopt

Usage Context

This skill is invoked when processes require advanced model-based control, trajectory tracking with constraints, or real-time optimization-based control strategies.

Output Artifacts

MPC formulation code
CasADi symbolic models
ACADO generated code
QP/NLP solver configurations
Cost function tuning parameters
Constraint specifications

Signals

GitHub stars: 2k
Forks: 112
Last commit: Sep 2026

Advanced

Item type: skill
Key: mpc-controller-skill
Source: github.com/a5c-ai/babysitter

github.com/a5c-ai/babysitter