Learning nonlinear hybrid automata from input--output time-series data
Preprint
Abstract
Learning an automaton that approximates the behavior of a black-box system is a long-studied problem. Besides its theoretical significance, its application to search-based testing and model understanding is recently recognized. We present an algorithm to learn a nonlinear hybrid automaton (HA) that approximates a black-box hybrid system (HS) from a set of input--output traces generated by the HS. Our method is novel in handling (1) both exogenous and endogenous HS and (2) HA with reset associated with each transition. To our knowledge, ours is the first method that achieves both features. We applied our algorithm to various benchmarks and confirmed its effectiveness.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Synthesis of Parametric Hybrid Automata from Time Series2022
- Efficient Black-Box Checking via Model Checking with Strengthened Specifications2021
- Inferring Switched Nonlinear DynamicalSystemsFormal Aspects of Computing, 2021
- Discovery of Dynamics Using Linear Multistep MethodsSIAM Journal on Numerical Analysis, 2021
- Membership-Based Synthesis of Linear Hybrid Automata2019
- Compositional Abstraction-based Synthesis for Cascade Discrete-Time Control SystemsIFAC-PapersOnLine, 2018
- Control design for hybrid systems with TuLiP: The Temporal Logic Planning toolbox2016
- Hybrid Systems and Biology2007
- Learning Cycle-Linear Hybrid Automata for Excitable Cells2007
- On adaptive control processesIRE Transactions on Automatic Control, 1959