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 2407.20532eess.SYcs.SY
收藏

面向Hamilton-Jacobi可达性分析的形式化验证神经价值函数可扩展合成方法

Scalable Synthesis of Formally Verified Neural Value Function for Hamilton-Jacobi Reachability Analysis

Yujie Yang, Hanjiang Hu, Tianhao Wei, Shengbo Eben Li, Changliu Liu

AI总结:

针对HJ可达性分析中价值函数合成的可扩展性与可验证性难以兼顾的问题,提出含三阶段训练与三种优化技术的框架,并构建Cersyve-9基准,实现高维场景下可验证神经价值函数的高效合成。

摘要:

Hamilton-Jacobi(HJ)可达性分析为约束控制问题中的安全性保障提供了一种形式化方法,它通过合成价值函数来表示被称为可行域的长期安全集合。早期基于状态空间离散化的合成方法无法扩展到高维问题,而近期使用神经网络逼近价值函数的方法得到的可行域不具备可验证性。为同时实现可扩展性与可验证性,我们提出了一个用于HJ可达性分析的验证型神经价值函数合成框架。该框架包含三个阶段:预训练、对抗训练和验证引导训练。我们设计了三种技术分别应对三类挑战以提升可扩展性:边界引导回溯(BGB)用于提升反例搜索效率,进入状态正则化(ESR)用于扩大可行域,激活模式对齐(APA)用于加速神经网络验证。我们还提供了一个名为Cersyve-9的神经安全证书合成与验证基准,包含9个常用安全控制任务,补充了现有神经网络验证基准。我们的框架在所有任务上成功合成了验证型神经价值函数,且所提出的三种技术相比现有方法展现出更优的可扩展性与效率。

英文摘要:

Hamilton-Jacobi (HJ) reachability analysis provides a formal method for guaranteeing safety in constrained control problems. It synthesizes a value function to represent a long-term safe set called feasible region. Early synthesis methods based on state space discretization cannot scale to high-dimensional problems, while recent methods that use neural networks to approximate value functions result in unverifiable feasible regions. To achieve both scalability and verifiability, we propose a framework for synthesizing verified neural value functions for HJ reachability analysis. Our framework consists of three stages: pre-training, adversarial training, and verification-guided training. We design three techniques to address three challenges to improve scalability respectively: boundary-guided backtracking (BGB) to improve counterexample search efficiency, entering state regularization (ESR) to enlarge feasible region, and activation pattern alignment (APA) to accelerate neural network verification. We also provide a neural safety certificate synthesis and verification benchmark called Cersyve-9, which includes nine commonly used safe control tasks and supplements existing neural network verification benchmarks. Our framework successfully synthesizes verified neural value functions on all tasks, and our proposed three techniques exhibit superior scalability and efficiency compared with existing methods.

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。

↑