1 option
Leveraging the Automated Mobility Partnership (AMP) to Support the Evaluation of Safety of the Intended Functionality (SOTIF) in Automated Driving Systems Virginia Tech. Transportation Institute
- Format:
- Book
- Conference/Event
- Author/Creator:
- Antona-Makoshi, Jacobo, author.
- Conference Name:
- WCX SAE World Congress Experience (2025-04-08 : Detroit, Michigan, United States)
- Language:
- English
- Physical Description:
- 1 online resource cm
- Place of Publication:
- Warrendale, PA SAE International 2025
- Summary:
- The Automated Mobility Partnership (AMP) is a consortium of industry and academic stakeholders dedicated to advancing Automated Driving Systems (ADS) through a comprehensive suite of tools, datasets, and methodologies. The AMP portal integrates events from over 35 million miles of naturalistic driving data including thousands of annotated crashes and near-crashes and a decade of U.S. police-reported crash data curated by the Virginia Tech Transportation Institute. The portal enables data discovery, visualization, processing, and analysis through secured web access. This paper briefly describes the AMP portal and examines its utility in developing and evaluating the safety of ADS using standardized processes. For the examination, we provide examples based on generic automated driving functions, guided by the Safety of the Intended Functionality (SOTIF) framework. The results show that AMP is instrumental in identifying recorded real-world cases in which the hazardous behavior of a system can lead to harm, through the AMP case browser and advanced filtering capabilities. The portal uses the naturalistic driving data to generate essential exposure, controllability, and severity metrics for defining risk-based acceptance criteria and evaluating a system against these 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. Further, the work elaborates on the potential for AMP data-driven scenario generation to support verification and validation activities, as well as on the potential of the data to provide human reference to support post-release monitoring activities
- Notes:
- Vendor supplied data
- Publisher Number:
- 2025-01-8674
- Access Restriction:
- Restricted for use by site license
The Penn Libraries is committed to describing library materials using current, accurate, and responsible language. If you discover outdated or inaccurate language, please fill out this feedback form to report it and suggest alternative language.