.png){kind=icon}
返回
Data-driven abstraction-based control synthesis
.png){kind=icon}
OA
AI
DOI：10.1016/j.nahs.2024.101467.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper studies formal synthesis of controllers for continuous-space systems with unknown dynamics to satisfy requirements expressed as linear temporal logic formulas. Formal abstraction-based synthesis schemes rely on a precise mathematical model of the system to build a finite abstract model, which is then used to design a controller. The abstraction-based schemes are not applicable when the dynamics of the system are unknown. We propose a data-driven approach that computes a growth bound of the system using a finite number of trajectories. The computed growth bound together with the sampled trajectories are then used to construct the abstraction and synthesise a controller. Our approach casts the computation of a growth bound as a robust convex optimisation program (RCP). Since the unknown dynamics appear in the optimisation, we formulate a scenario convex program (SCP) corresponding to the RCP using a finite number of sampled trajectories. We establish a sample complexity result that gives a lower bound for the number of sampled trajectories to guarantee the correctness of the growth bound computed from the SCP with a given confidence. Our sample complexity result requires knowing a possibly conservative bound on the Lipschitz constant of the system. We also provide a sample complexity result for the satisfaction of the specification on the system in closed loop with the designed controller for a given confidence. Our data-driven synthesised controller can provide guarantees on satisfaction of both finite and infinite-horizon specifications. We show that our data-driven approach can be readily used as a model-free abstraction refinement scheme by modifying the formulation of the system's growth bounds and providing similar sample complexity results. The performance of our approach is shown on three case studies.
Keyword:
Abstraction-based methods
Data-driven synthesis
Formal controller synthesis
Sample complexity
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
N
IF:
4.1
论文数:
1.4K
被引数:
3.1K
机构
引用论文
Performance Bounds for the Scenario Approach and an Extension to a Class of Non-Convex Programs场景方法的性能界限以及对一类非凸程序的扩展OAAI
OAAI分享收藏Formal synthesis of closed-form sampled-data controllers for nonlinear continuous-time systems under STL specifications.png)
AUTOMATICAOAAI
AUTOMATICAIF5.9
OAAI分享收藏Temporal logic guided safe model-based reinforcement learning: A hybrid systems approach时序逻辑指导的基于安全模型的强化学习: 一种混合系统方法OAAI
OAAI分享收藏分享收藏
分享收藏
查看更多内容