2021/05/17 by Pierre-François Massiani, Massiani, Pierre-François, Steve Heim +3 · 1 citation
Computer Science · Decision Sciences · Engineering · #FOS: Electrical engineering #Risk and Safety Analysis #Safety Systems Engineering in Autonomy #Software Reliability and Analysis Research #Systems and Control (eess.SY) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2105.08143
openalex publication_date 2021/05/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Enforcing safety for dynamical systems is challenging, since it requires constraint satisfaction along trajectory predictions. Equivalent control constraints can be computed in the form of sets that enforce positive invariance, and can thus guarantee safety in feedback controllers without predictions. However, these constraints are cumbersome to compute from models, and it is not yet well established how to infer constraints from data. In this paper, we shed light on the key objects involved in learning control constraints from data in a model-free setting. In particular, we discuss the family of constraints that enforce safety in the context of a nominal control policy, and expose that these constraints do not need to be accurate everywhere. They only need to correctly exclude a subset of the state-actions that would cause failure, which we call the critical set.