Nonuniform abstractions, refinement and controller synthesis with novel BDD encodings
For researchers in formal methods and control, this work offers an incremental improvement in scalability for LTL control synthesis.
This paper presents a control synthesis algorithm for dynamical systems using nonuniform abstraction-refinement and a novel BDD encoding, demonstrating effectiveness through benchmark results.
This paper presents a control synthesis algorithm for dynamical systems to satisfy specifications given in a fragment of linear temporal logic. It is based on an abstraction-refinement scheme with nonuniform partitions of the state space. A novel encoding of the resulting transition system is proposed that uses binary decision diagrams for efficiency. We discuss several factors affecting scalability and present some benchmark results demonstrating the effectiveness of the new encodings. These ideas are also being implemented on a publicly available prototype tool, ARCS, that we briefly introduce in the paper.