Multi-Layered Abstraction-Based Controller Synthesis for Continuous-Time Systems

Kyle Hsu, Rupak Majumdar, Kaushik Mallik, Anne-Kathrin Schmuck

Abstract: We present multi-layered abstraction-based controller synthesis, which extends standard abstraction-based controller synthesis (ABCS) algorithms for continuous-time control systems by simultaneously maintaining several "layers" of abstract systems with decreasing precision. The resulting abstract multi-layered controller uses the coarsest abstraction whenever this is feasible, and dynamically adjusts the precision---by moving to a more precise abstraction and back to a coarser abstraction---based on the structure of the given control problem. Abstract multi-layered controllers can be refined to controllers with non-uniform resolution using feedback refinement relations established between each abstract layer and the concrete system, resulting in a sound ABCS method. We provide multi-layered controller synthesis algorithms for reachability, safety, and generalized Büchi specifications; our approach can be generalized to any ω-regular objective. Our algorithms are complete relative to single-layered synthesis on the finest layer. We empirically demonstrate that multi-layered synthesis can outperform standard (single-layer) ABCS algorithms on a number of examples, despite the additional cost of constructing multiple abstract systems.