Research papers · Posted 2023.02.27 · Preprint

SAFR-AV: Safety Analysis of Autonomous Vehicles using Real World Data -- An end-to-end solution for real world data driven scenario-based testing for pre-certification of AV stacks

Sagar Pathrudkar, Saadhana Venkataraman, Deepika Kanade, Aswin Ajayan, Palash Gupta, Shehzaman Khatib, Vijaya Sarathi Indla, Saikat Mukherjee · arXiv · English

Overview

SAFR-AV links large-scale driving-data ingestion, scenario search, digital-twin construction, and software-in-the-loop testing. Scenario-parameter distributions support coverage optimization; the authors position the platform as enabling pre-certification workflows.

Version: v1

SAFR-AV: Safety Analysis of Autonomous Vehicles using Real World Data -- An end-to-end solution for real world data driven scenario-based testing for pre-certification of AV stacks

Overview

Participation enquiry

Your enquiry has been sent.

SAFR-AV: Safety Analysis of Autonomous Vehicles using Real World Data -- An end-to-end solution for real world data driven scenario-based testing for pre-certification of AV stacks

Overview

Related resources

Assuring Learning-Enabled Cyber-Physical Systems with Foundation Models: A Neuro-Symbolic Agenda for Testing, Verification, and Runtime Assurance

Engineering Psychological Safety in Autonomous Vehicles: A Systems-Theoretic Framework for Psychological Safety in Autonomous Vehicles and its Validation in Real-World Scenarios

LLM-Guided Transformation of Non-Critical Driving Scenes into Safety-Critical Scenarios Using Augmented Reality