一种针对自动驾驶紧急制动逻辑的分层形式化建模与安全验证方法、电子设备、计算机可读存储介质及程序
By employing a hierarchical formal modeling and safety verification method, the emergency braking logic of autonomous driving is divided into perception, decision-making, and execution layers. A logical relationship model is constructed and safety attributes are defined, which solves the problems of low verification efficiency and insufficient scenario coverage in existing technologies, and achieves efficient safety analysis and engineering adaptability.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHANGSHU INSTITUTE OF TECHNOLOGY
- Filing Date
- 2026-05-12
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies are insufficient to fully cover all possible scenarios of emergency braking logic in complex traffic environments for autonomous driving, resulting in low verification efficiency and difficulty in discovering potential logical defects and safety hazards. Furthermore, the modeling lacks decoupling and has poor engineering adaptability.
A hierarchical formal modeling approach is adopted to divide the emergency braking logic into a perception trigger layer, a decision-making layer, and an execution constraint layer. Formal modeling is performed on each layer, and logical relationship models between the layers are constructed. System safety attributes are defined and transformed into formally verifiable safety constraints. Safety verification is performed using a formal verification platform.
It improves the verification efficiency of emergency braking logic, ensures safety analysis in the full state space, provides reusable and scalable verification methods, solves the problem of insufficient scenario coverage in traditional testing, quantifies the impact of sensor errors on logic, and enhances the engineering reference value of verification results.
Smart Images
Figure CN122172770B_ABST