Linear model predictive safety certification for learning-based control
It addresses safety assurance for learning-based control in systems with uncertainties, which is critical for real-world applications like robotics or autonomous vehicles, though it is incremental as it builds on existing MPC methods.
The paper tackles the lack of safety guarantees in learning-based controllers by introducing a model predictive safety certification (MPSC) scheme for polytopic linear systems with additive disturbances, which verifies and minimally modifies inputs to ensure constraint satisfaction and allows iterative expansion of safe sets.
While it has been repeatedly shown that learning-based controllers can provide superior performance, they often lack of safety guarantees. This paper aims at addressing this problem by introducing a model predictive safety certification (MPSC) scheme for polytopic linear systems with additive disturbances. The scheme verifies safety of a proposed learning-based input and modifies it as little as necessary in order to keep the system within a given set of constraints. Safety is thereby related to the existence of a model predictive controller (MPC) providing a feasible trajectory towards a safe target set. A robust MPC formulation accounts for the fact that the model is generally uncertain in the context of learning, which allows proving constraint satisfaction at all times under the proposed MPSC strategy. The MPSC scheme can be used in order to expand any potentially conservative set of safe states for learning and we prove an iterative technique for enlarging the safe set. Finally, a practical data-based design procedure for MPSC is proposed using scenario optimization.