Automaton-Guided Control Synthesis for Signal Temporal Logic Specifications

This paper presents an algorithmic framework for control synthesis for continuous dynamical systems subject to signal temporal logic (STL) specifications. We propose a novel algorithm to obtain a time-partitioned finite automaton from an STL specification, and introduce a multi-layered framework that utilizes this automaton to guide a sampling-based search tree both spatially and temporally. Our approach is able to synthesize a controller for nonlinear dynamics and polynomial predicate functions. We prove the correctness and probabilistic completeness of our algorithm, and illustrate the efficacy and efficiency of our framework on several case studies. Our results show an order of magnitude speedup over the state of the art.

Automated summary

This paper presents an algorithmic framework for control synthesis for continuous dynamical systems with signal temporal logic (STL) specifications. The authors propose a novel algorithm to obtain a time-partitioned finite automaton from an STL specification, and introduce a multi-layered framework that utilizes this automaton to guide a sampling-based search tree in both spatial and temporal dimensions. The approach is able to synthesize a controller for nonlinear dynamics and polynomial predicate functions, and the authors prove the correctness and probabilistic completeness of the algorithm. The efficacy and efficiency of the framework are demonstrated through several case studies, showing a significant speedup compared to the state of the art.