Transfer Learning for Barrier Certificates
Transfer Learning for Barrier Certificates
复制标题
DOI：
10.1109/cdc49753.2023.10384302
复制
发表时间：
2023-12
期刊：
影响因子：
--
通讯作者：
Alireza Nadali;Ashutosh Trivedi;Majid Zamani
中科院分区：
文献类型：
--
作者：
Alireza Nadali;Ashutosh Trivedi;Majid Zamani
动力系统安全验证的原则性方法需要形式上的保证。障碍证书是以归纳可验证不变量的形式搜索安全证明的有效工具。然而，查找屏障证书是一个昂贵且耗时的过程，需要人工专业知识来选择各种模板、超参数和决策过程。是否有可能将在寻找障碍证书和控制算法方面获得的知识从给定环境(源环境)转移到不同但相关的环境(目标环境)？本文提出了一种转移学习方法，使障碍证书(任何模板)以神经网络的形式从源环境适应到目标环境。利用网络的Lipschitz连续性，给出了形式化保证网络正确性的有效条件。为了验证该方法的有效性，我们将其应用于两个案例研究，即倒立摆、直流电机和室温控制。我们的结果表明，迁移学习可以成功地将障碍证书从源环境适配到目标环境，减少了对人类专业知识的需求，并加快了验证过程。
A principled approach to safety verification of dynamical systems demands formal guarantees. Barrier certificates are an effective tool for searching safety proofs in the form of inductively verifiable invariants. However, finding barrier certificates is an expensive and time-consuming process that demands human expertise in selecting various templates, hyperparameters, and decision procedures. Is it possible to transfer the knowledge gained in finding a barrier certificate and control algorithm from a given environment (source environment) to a different but related environment (target environment)? This paper presents a transfer learning approach to adapt the barrier certificates (of any template) in the form of neural networks from the source to the target environment. We derive a validity condition to formally guarantee the correctness of network by leveraging its Lipschitz continuity. To demonstrate the effectiveness of our approach, we apply it to two case studies, namely the inverted pendulum, DC motor and Room temperature control. Our results show that transfer learning can successfully adapt barrier certificates from the source to the target environment, reducing the need for human expertise and speeding up the verification process.