Imitation Learning with Stability and Safety Guarantees

Presents a method to learn neural network controllers with certified stability and safety via imitation learning for LTI systems. By merging Lyapunov theory with local quadratic constraints on activations, convex conditions are derived and incorporated into the IL process to jointly minimize IL loss and maximize the certified region of attraction. An ADMM-based algorithm solves the resulting problem. Demonstrated on vehicle lateral control.