Progressive closed-loop chance-constrained control

Chance-constrained control is a difficult problem even if the considered system dynamics are linear. The difficulty stems from the facts that the chance constraints are difficult to evaluate and that the control law is nonlinear due to the constraints. In this paper, we present a novel approach to chance-constrained control, where we solve the unconstrained control problem first and then use a progressive method to gradually introduce the chance constraints. This has significant advantages compared to traditional methods, because we do not require a feasible initial solution for the numerical optimization algorithm. Finally, we evaluate the novel method and compare it to an approach from literature.