发表机构
The Pennsylvania State University（宾夕法尼亚州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出将流匹配生成模型与控制障碍函数安全保证结合的模块化推理框架，通过修改流匹配去噪过程实现本质安全，在不降低模型成功率的前提下完成安全验证。
AI 中文摘要
本文提出一种模块化推理框架，将流匹配（Flow Matching）生成模型与形式化控制障碍函数（Control Barrier Function, CBF）安全保证相结合。与现有对模型最终输出施加外部安全过滤器的方法不同，我们的方法在模型内部修改流匹配去噪过程，从本质上生成安全轨迹。通过采用平滑的对数求和指数聚合障碍，我们对整个动作块实施安全约束。该聚合障碍确保计算开销的最小增加，且不改变模型的语义意图。我们证明，在该框架内，生成分布与目标分布之间的2-瓦瑟斯坦距离保持有界。我们的方法无需特定安全数据集或代价高昂的模型重训练，为安全推理提供了通用解决方案。我们在两个机器人操作平台和一个2D导航基准上验证了该方法，确认我们的框架在不降低模型成功率的前提下实现了可靠的安全性。
英文摘要
This article presents a modular inference framework that integrates Flow Matching generative models with formal Control Barrier Function (CBF) safety guarantees. Unlike existing methods that apply external safety filters to a model's final output, our approach modifies the Flow Matching denoising process within the model to inherently generate safe trajectories. By employing a smooth Log-Sum-Exponential aggregate barrier, we enforce safety over entire action chunks. This aggregate barrier ensures a minimal increase in computational overhead and does not alter the semantic intent of the model. We show that, within the proposed framework, the 2-Wasserstein distance between the generated distribution and the target distribution remains bounded. Our method eliminates the need for safety-specific datasets or costly model retraining, providing a versatile solution for safe inference. We validate the approach on two robotic manipulation platforms and a 2D navigation benchmark, verifying that our framework achieves reliable safety without degrading the success rate of the model.
