Minimal Assumptions Refinement for GR(1) Specifications

TL;DR

This paper introduces an efficient algorithm for minimal assumption refinement in reactive synthesis, improving the process of finding the simplest assumptions needed for realizability in LTL specifications.

Contribution

It proposes a novel algorithm for minimal assumption refinement with low overhead, enhancing existing assumption refinement techniques in reactive synthesis.

Findings

Algorithm computes minimal assumptions with little time overhead.

Embedding the algorithm results in shorter solutions in benchmarks.

Hybrid variant speeds up the identification of minimal assumptions.

Abstract

Reactive synthesis is concerned with finding a correct-by-construction controller from formal specifications, typically expressed in Linear Temporal Logic (LTL). The specifications describe assumptions about an environment and guarantees to be achieved by the controller operating in that environment. If a controller exists, given the assumptions, the specification is said to be realizable. This paper focuses on finding a minimal set of assumptions that guarantee realizability in the context of counterstrategy-guided assumption refinement procedures. Specifically, we introduce the notion of minimal assumptions refinements and provide an algorithm that provably computes these with little time overhead. We show experimentally, using common benchmarks, that embedding our algorithm in state-of-the-art approaches for assumption refinement results in consistently shorter solutions than without such embedding, and allows to explore a higher number of candidate solutions. We also propose a hybrid variant for dealing with the higher sparsity of solutions in the space of minimal refinements and show that its application speeds up the identification of a solution.