Adaptive Shielding via Parametric Safety Proofs

A major challenge to deploying cyber-physical systems with learning-enabled controllers is to ensure their safety, especially in the face of changing environments that necessitate runtime knowledge acquisition. Model-checking and automated reasoning have been successfully used for shielding, i.e., to monitor un-trusted controllers and override potentially unsafe decisions, but only at the cost of hard tradeoffs in terms of expressivity, safety, adaptivity, precision and runtime efficiency. We propose a programming-language framework that allows experts to statically specify adaptive shields for learning-enabled agents, which enforce a safe control envelope that gets more permissive as knowledge is gathered at runtime. A shield specification provides a safety model that is parametric in the current agent’s knowledge. In addition, a nondeterministic inference strategy can be specified using a dedicated domain-specific language, enforcing that such knowledge parameters are inferred at runtime in a statistically-sound way. By leveraging language design and theorem proving, our proposed framework empowers experts to design adaptive shields with an unprecedented level of modeling flexibility, while providing rigorous, end-to-end probabilistic safety guarantees.