sky

Resources & Open Material

Toolboxes, video lectures, and interactive tutorials

Software & Toolboxes

Pyro
Pyro: The Python Toolbox for Robotics

An open-source library bridging control theory and modern AI—features modeling, synthesis, and reinforcement learning simulation.

View on GitHub →
Casadi
Colab Interactive Tutorials

Run robotics code directly in your browser with zero setup.

Open Educational Material (en français!)

Commande optimale et apprentissage par renforcement (vidéos)
Modélisation et commande en robotique (vidéos)
Systèmes asservis (vidéos)
Notes
Notes de cours : Modélisation et commande en robotique (PDF)
Notes
Notes de cours : Commande optimale et apprentissage par renforcement (PDF)

Cours universitaires (UdeS)

Commande optimale
GRO860 - Commande optimale et apprentissage par renforcement
GMC714
GMC714 - Robotique: Modélisation et commande
Université de Sherbrooke — fiche cours GRO203
GRO203 : Cinématique des robots
Université de Sherbrooke — fiche cours GRO211
GRO211 : Algèbre linéaire pour la robotique
Université de Sherbrooke — fiche cours GRO501
GRO501 : Systèmes asservis
Université de Sherbrooke — fiche cours GRO640
GRO640 : Cinématique différentielle des robots manipulateurs

Colab Interactive Tutorials

Run robotics code directly in your browser with zero setup. These tutorials use the Pyro toolbox for simulations.

Pyro toolbox

Pyro tutorial no. 1: basic functionality
Pyro tutorial no. 1: basic functionality
Pyro tutorial no. 2: custom dynamic classes
Pyro tutorial no. 2: custom dynamic classes
Pyro tutorial no. 3: closed-loop systems and the controller class
Pyro tutorial no. 3: closed-loop systems and the controller class
Pyro tutorial no. 4: manipulator robot class
Pyro tutorial no. 4: manipulator robot class

Optimal control

Optimal control overview (pendulum swing-up)
Optimal control overview (pendulum swing-up)
LQR vs. dynamic programming
LQR vs. dynamic programming
Trajectory optimization (direct collocation)
Trajectory optimization (direct collocation)
Optimal swing-up with a custom cost function
Optimal swing-up with a custom cost function
Trajectory optimization with CasADi
Trajectory optimization with CasADi
Minimum-time optimal policy for a mass
Minimum-time optimal policy for a mass
Policy evaluation for a minimum-time problem
Policy evaluation for a minimum-time problem
LQR: finite vs. infinite horizon
LQR: finite vs. infinite horizon

Robot arm control

2-DoF robot controlled with a PID
2-DoF robot controlled with a PID
2-DoF robot: custom controller template
2-DoF robot: custom controller template
2-DoF robot: kinematic controllers
2-DoF robot: kinematic controllers
2-DoF robot: impedance controllers
2-DoF robot: impedance controllers
5-DoF robot: redundant manipulator control
5-DoF robot: redundant manipulator control

Classical control

PID on a second-order system
PID on a second-order system
Phase plane analysis
Phase plane analysis

Machine learning

Diffusion in 2D
Diffusion in 2D
Diffusion policy
Diffusion policy

Dynamics (Pyro)

Planar plane dynamics
Planar plane dynamics

Reinforcement learning

Drone learning to fly with PPO
Drone learning to fly with PPO
Cost-to-go approximation
Cost-to-go approximation