Research papers · Posted 2021.03.12 · Preprint

Generating and Characterizing Scenarios for Safety Testing of Autonomous Vehicles

Zahra Ghodsi, Siva Kumar Sastry Hari, Iuri Frosio, Timothy Tsai, Alejandro Troccoli, Stephen W. Keckler, Siddharth Garg, Anima Anandkumar · arXiv · English

Overview

The method explores feasible paths and safe trajectories from different starting times to quantify accident-avoidance complexity. It characterizes NGSIM driving data and adversarial simulations, comparing scenario rankings with human judgments.

Version: v1

Generating and Characterizing Scenarios for Safety Testing of Autonomous Vehicles

Overview

Participation enquiry

Your enquiry has been sent.

Generating and Characterizing Scenarios for Safety Testing of Autonomous Vehicles

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