arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.06983eess.SYcs.SY
收藏

针对复杂STL规范的基于优化的模型检测与轨迹合成

Optimization-Based Model Checking and Trace Synthesis for Complex STL Specifications

Sota Sato, Jie An, Zhenya Zhang, Ichiro Hasuo

AI总结:

本研究提出一种基于混合整数线性规划的信号时序逻辑有界模型检测算法,采用新型语义编码,具备可扩展性、可中断性和参数挖掘能力,在复杂STL公式场景下性能更优,可应用于汽车等领域。

摘要:

我们提出了一种利用混合整数线性规划(MILP)的信号时序逻辑(STL)有界模型检测算法。核心技术要素是我们提出的新型STL语义MILP编码,该编码借鉴了近期基于SMT的STL模型检测工作中的稳定划分思想。假设我们的(连续时间)系统模型可编码为MILP——典型例子包括矩形混合自动机(精确编码)和具有闭式解的混合动力学(近似编码)——我们的MILP编码可生成一种基于优化的模型检测算法,该算法具备可扩展性、支持随时/中断运行,且可适配参数挖掘。实验评估表明,我们的算法尤其在复杂STL公式场景下具有性能优势,证明了其在汽车等领域的实用价值。

英文摘要:

We present a bounded model checking algorithm for signal temporal logic (STL) that exploits mixed-integer linear programming (MILP). A key technical element is our novel MILP encoding of the STL semantics; it follows the idea of stable partitioning from the recent work on SMT-based STL model checking. Assuming that our (continuous-time) system models can be encoded to MILP -- typical examples are rectangular hybrid automata (precisely) and hybrid dynamics with closed-form solutions (approximately) -- our MILP encoding yields an optimization-based model checking algorithm that is scalable, is anytime/interruptible, and accommodates parameter mining. Experimental evaluation shows our algorithm's performance advantages especially for complex STL formulas, demonstrating its practical relevance e.g. in the automotive domain.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑