Abstract
This report presents a structured Robotics Physical Safety Framework based on explicit asset declaration, systematic vulnerability enumeration, and hazard-driven synthetic data generation. The approach bridges classical risk engineering with modern machine learning pipelines, enabling safety envelope learning grounded in a formalized hazard ontology. The key contribution of this framework is the alignment between classical safety engineering, digital twin simulation, synthetic data generation, and machine learning model training.
Abstract (translated)
本报告提出了一种基于明确资产声明、系统性漏洞枚举和危害驱动的合成数据生成的结构化机器人物理安全框架。该方法将传统的风险工程与现代机器学习管道相结合，通过一个形式化的危害本体论来实现安全性界限的学习。此框架的关键贡献在于使传统安全工程、数字孪生模拟、合成数据生成以及机器学习模型训练之间达到一致和协同。
URL
https://arxiv.org/abs/2603.06130
