Automated Driving Systems (ADS) have emerged as a transformative technology with the potential to revolutionize transportation, improve road safety, and enhance mobility. By leveraging advanced sensors, computing capabilities, and artificial intelligence algorithms, ADS can navigate vehicles autonomously, reducing human error and optimizing driving efficiency. However, the widespread adoption of ADS hinges on ensuring their safety and reliability in real-world traffic conditions. Testing ADS presents a complex and multifaceted challenge, as traditional testing methods are insufficient to comprehensively evaluate the performance and safety of these advanced systems. Therefore, it is essential to employ a systematic and standardized test methodology designed for evaluating ADS with the aim to simulate real-world conditions and ensuring the safety of passengers, pedestrians, and other road users. On the one hand, potential risks are to be evaluated and respective triggers to be identified. On the other hand, relevant scenarios are to be collected, resulting in the creation of a hazard and risk-based critical scenario database.

The ISO 21448 Road Vehicles – Safety of the intended functionality (short SOTIF) defines a guideline for the methodology of testing autonomous cars and highly automated driving functions by considering the entire environment including weather, road conditions, surrounding landscape, object texture and possible inappropriate drivers. The aim is to provide a documentation of different scenarios, the safety analysis of these scenarios, the verification of the safety situations and triggering events, as well as the validation of the vehicle for the environment with applied safe systems.

Besides that, the development of a scenario-based safety evaluation framework, such as the one provided by ISO 34502:2022 [1], is of the utmost importance. This framework offers a structured approach to managing the evaluation of ADS through scenario-based safety assessments. By defining a set of scenarios that encompass a broad range of driving conditions, traffic scenarios, and potential hazards, this framework provides a comprehensive and systematic methodology to assess the safety and reliability of ADS.

Within the Whitepaper “Test Methodology for Evaluating Automated Driving Systems: A Scenario-Based Safety Evaluation Framework”, we will delve into the challenges associated with testing ADS and discuss the importance of employing a robust and standardized test methodology. We will explore the significance of creating a hazard and risk-based critical scenario database and highlight the value of a framework, such as ISO 34502:2022 [1], in managing the scenario-based safety evaluation of Automated Driving Systems. By addressing these challenges and proposing effective methodologies, we describe a platform which serves as a framework for safe and responsible deployment of ADS, ushering in a new era of transportation innovation.