随着自动驾驶系统（ADS）的快速发展，其系统安全性、可靠性及法规符合性面临新的挑战。测试与验证作为ADS研发的关键环节，为系统在复杂真实场景中的安全运行提供方法支撑。本报告将介绍自动驾驶系统测试与验证的前沿框架，包括基于场景的仿真测试、结构化实车验证，以及面向AI/ML驱动感知与决策模块的验证方法，并重点讨论其与国际标准的衔接以及可追溯、可量化安全证据的重要性。
The rapid advancement of Automated Driving Systems (ADS) has introduced significant challenges in ensuring safety, reliability, and regulatory compliance. Verification and Validation are the cornerstone of ADS development, providing systematic approaches to demonstrate performance in complex real-world scenarios. This presentation provides a concise overview of state-of-the-art Verification and Validation frameworks for ADS, including scenario-based simulation for edge-case coverage, structured on-road validation, and evaluation of Al/ML-driven perception and decision-making modules. It emphasizes alignment with international standards and the growing need for traceable and quantifiable safety evidence.
