Get Started
Home
Topics
Search
Library
Research questionHow can safety assessors scale credibility judgments for virtual-testing toolchains across automated-driving decisions of differing criticality?Automated-driving systems cover complex behaviors and broad operational design domains, making exclusive physical testing impractical. Approval decisions may therefore rely on multi-tool virtual-testing environments whose assumptions, interactions, and limitations are difficult to assess consistently.
Alignment & Safety
Evaluation & Benchmarks
Research Paper
Robotics
Technology
Latest papersRecent research connected to this question, newest first.Virtual Testing of Automated Driving Systems through Credible SimulationsThe source presents a proposed risk-based, lifecycle-oriented framework for assessing automated-driving virtual-testing toolchains, informed by NASA STD-7009. It addresses toolchain management, modelling assumptions and limitations, verification, validation, and sensitivity analysis, with proportional acceptance thresholds for different uses. The framework is demonstrated for automated driving and described as applicable to related road-safety simulation studies; the input does not provide empirical validation of its effectiveness.research paper · Sep 3, 2026
Related questions
How can low-cost platforms enable reproducible testing of end-to-end autonomous-driving policies across simulation and physical vehicles?How can safety-critical AI demonstrate complete coverage of high-dimensional operational design domains?How can autonomous-driving planners be stress-tested in realistic closed-loop scenarios that expose failures missed by nominal benchmarks?How can safety evaluations measure language-model behavior without triggering evaluation-aware changes in decisions?