基于能量神经网络的安全设计学习
Safe-by-Design Learning via Energy-based Neural Networks
- The Italian Institute of Artificial Intelligence for Industry（意大利人工智能工业研究所）
- University of Colorado Boulder（科罗拉多大学博尔德分校）
- TU Delft（代尔夫特理工大学）
机构由 AI 辅助整理，请以论文原文为准。
中文总结 AI 辅助
本文提出基于能量现代Hopfield网络与端口哈密顿神经ODE的安全设计架构，通过构造障碍函数保证安全性，在多个基准包括12维纳米无人机上实现最先进性能并提升鲁棒性。
中文摘要 AI 辅助
学习具有安全保证的动力系统的神经网络模型是其在安全关键环境中部署的基本要求。安全性通常通过证明状态空间中期望子集的不变性来建立，确保在该子集中初始化的每条轨迹在允许输入下始终被限制在该子集内。然而，现有框架要么依赖计算成本高昂的事后验证，要么采用缺乏正式正确性保证的安全强制机制。在本文中，我们引入了一种基于能量的现代Hopfield网络的新型神经架构，以保证安全设计，同时保留足够的表达能力来建模复杂的非线性动力学。具体来说，我们将现代Hopfield网络与端口哈密顿神经ODE集成，通过设计能够构建障碍函数，从而产生显式的允许输入集和定量鲁棒性半径。在多个基准测试中，包括一个12维纳米无人机模型，我们的框架实现了最先进的性能，同时生成比现有类似方法更鲁棒于外部干扰的认证不变集。
英文摘要
Learning neural-network models of dynamical systems with safety guarantees is a fundamental requirement for their deployment in safety-critical settings. Safety is commonly established by proving the invariance of a desired subset in state-space, ensuring that every trajectory initialized in this subset remains confined to it for all time under admissible inputs. Existing frameworks, however, either rely on computationally expensive post-hoc verification or employ safety-enforcing mechanisms without formal correctness guarantees. In this paper, we introduce a novel neural architecture grounded in energy-based modern Hopfield networks to guarantee safety-by-design while retaining sufficient expressiveness to model complex nonlinear dynamics. Specifically, we integrate modern Hopfield networks with a port-Hamiltonian neural ODE, enabling by design the construction of barrier functions yielding explicit admissible-input sets and quantitative robustness radii. Across several benchmarks, including an 12-dimensional nanodrone model, our framework achieves state-of-the-art performance while producing certified invariant sets that are more robust to external solicitations than comparable existing approaches.
