arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2310.09360cs.LG
收藏

ReLU 神经控制屏障函数的精确验证

Exact Verification of ReLU Neural Control Barrier Functions

Washington University in St. Louis(圣路易斯华盛顿大学)

Hongchao Zhang, Junlin Wu, Yevgeniy Vorobeychik, Andrew Clark

AI总结:

本文提出基于 Nagumo 定理推广的精确条件与算法,通过分段线性分解和非线性规划,实现 ReLU 神经控制屏障函数的安全验证,并利用区间边界传播剪枝提升效率。

摘要:

控制屏障函数(CBF)是非线性系统安全控制的一种常用方法。在基于 CBF 的控制中,系统的期望安全性质被映射为 CBF 的非负性,并且选择控制输入以确保 CBF 在所有时间内保持非负。近年来,将 CBF 表示为神经网络(神经控制屏障函数,简称 NCBF)的机器学习方法,由于神经网络的通用表示能力而显示出巨大潜力。然而,验证学习得到的 CBF 是否保证安全性仍然是一个具有挑战性的研究问题。本文提出了用于验证具有 ReLU 激活函数的前馈 NCBF 安全性的新颖精确条件和算法。这样做的主要挑战在于,由于 ReLU 函数的分段线性特性,NCBF 在某些点处不可微,从而使假设平滑屏障函数的传统安全验证方法失效。我们通过利用 Nagumo 定理的推广形式来证明具有非光滑边界的集合的不变性,从而推导出安全性的充要条件,解决了这一问题。基于该条件,我们提出了一种用于 NCBF 安全性验证的算法,该算法首先将 NCBF 分解为分段线性段,然后求解一个非线性规划来验证每个段以及线性段交点的安全性。我们通过仅考虑安全区域的边界,并使用区间边界传播(IBP)和线性松弛来剪枝段,从而降低了复杂度。我们通过数值研究评估了我们的方法,并与最先进的基于 SMT 的方法进行了比较。我们的代码可在 https://github.com/HongchaoZhang-HZ/exactverif-reluncbf-nips23 获取。

英文摘要:

Control Barrier Functions (CBFs) are a popular approach for safe control of nonlinear systems. In CBF-based control, the desired safety properties of the system are mapped to nonnegativity of a CBF, and the control input is chosen to ensure that the CBF remains nonnegative for all time. Recently, machine learning methods that represent CBFs as neural networks (neural control barrier functions, or NCBFs) have shown great promise due to the universal representability of neural networks. However, verifying that a learned CBF guarantees safety remains a challenging research problem. This paper presents novel exact conditions and algorithms for verifying safety of feedforward NCBFs with ReLU activation functions. The key challenge in doing so is that, due to the piecewise linearity of the ReLU function, the NCBF will be nondifferentiable at certain points, thus invalidating traditional safety verification methods that assume a smooth barrier function. We resolve this issue by leveraging a generalization of Nagumo's theorem for proving invariance of sets with nonsmooth boundaries to derive necessary and sufficient conditions for safety. Based on this condition, we propose an algorithm for safety verification of NCBFs that first decomposes the NCBF into piecewise linear segments and then solves a nonlinear program to verify safety of each segment as well as the intersections of the linear segments. We mitigate the complexity by only considering the boundary of the safe region and by pruning the segments with Interval Bound Propagation (IBP) and linear relaxation. We evaluate our approach through numerical studies with comparison to state-of-the-art SMT-based methods. Our code is available at https://github.com/HongchaoZhang-HZ/exactverif-reluncbf-nips23.

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。

↑