Exploring the Automated Mobility Partnership (AMP) Portal's Capabilities for Enhancing Automated Driving Systems Safety Assurance Processes

The Automated Mobility Partnership (AMP) is a consortium of industry and academic stakeholders dedicated to advancing automated driving systems through a comprehensive suite of tools, datasets, and methodologies. The AMP portal contains ten years of U.S. police-reported crash data and over 35 million miles of curated naturalistic driving data, including thousands of annotated crashes and near-crashes. This resource enables data discovery, visualization, processing, and analysis through a secure web portal. This paper briefly describes the AMP portal and examines its utility in developing and evaluating the safety of automated systems using standardized processes. We analyze a hypothetical SAE Level 2 automation scenario with hands-off capabilities, guided by the Safety of the Intended Functionality (ISO 21448:2022) framework. The results show that AMP is instrumental in identifying triggering conditions, hazards, and functional insufficiencies. The portal uses the naturalistic driving data and publicly available mileage data to generate essential exposure, controllability, and severity metrics for defining risk-based acceptance criteria. By combining vehicle sensor data with environment and driver face video recordings, AMP can also provide evidence to develop driver glance-based criteria for monitoring systems linked to the automated driving functions. While our demonstration showcases the portal's capabilities and potential, further work is required to tailor its tools and methodologies for verification and validation activities. Future AMP efforts shall also integrate VTTI’s and industry-owned data with advanced automated driving systems, adapt tools for international contexts lacking certain data, and facilitate integration into user companies’ safety management systems.