Research papers · 2022.09
Towards Guaranteed Safety Assurance of Automated Driving Systems with Scenario Sampling: An Invariant Set Perspective (Extended Version)
Towards Guaranteed Safety Assurance of Automated Driving Systems With Scenario Sampling: An Invariant Set Perspective
Overview
The paper reformulates scenario-sampling safety assessment as data-driven invariant-set validation and quantification. It analyzes finite-sample guarantees and algorithmic completeness for validating an ODD or finding safe subdomains, with simulation demonstrations.
Author-supplied source information
Author-supplied information on arXiv.
A shorter version of this manuscript has been accepted by the IEEE Transactions on Intelligent Vehicles
Version: arXiv v3 — manuscript revision