S-RAF: A simulation-based robustness assessment framework for responsible autonomous driving

Omeiza, Daniel; Somaiya, Pratik; Pattison, Jo-Ann; Ten-Holter, Carolyn; Jirotka, Marina; Stilgoe, Jack; Kunze, Lars

Abstract

As artificial intelligence (AI) technology advances, ensuring the robustness and safety of AI-driven systems has become paramount. However, varying perceptions of robustness among AI developers create misaligned evaluation metrics, complicating the assessment and certification of safety-critical and complex AI systems such as autonomous driving (AD) agents. To address this challenge, we introduce Simulation-Based Robustness Assessment Framework (S-RAF) for autonomous driving. S-RAF leverages the CARLA Driving simulator to rigorously assess AD agents across diverse conditions, including faulty sensors, environmental changes, and complex traffic situations. By quantifying robustness and its relationship with other safety-critical factors, such as carbon emissions, S-RAF aids developers and stakeholders in building safe and responsible driving agents, and streamlining safety certification processes. Furthermore, S-RAF offers significant advantages, such as reduced testing costs, and the ability to explore edge cases that may be unsafe to test in the real world.

• Presentation Conference Type: Conference Paper (published)
• Conference Name: AAAI Fall Symposia
• Start Date: Nov 7, 2024
• End Date: Nov 9, 2024
• Acceptance Date: Aug 16, 2024
• Online Publication Date: Nov 8, 2024
• Publication Date: Nov 8, 2024
• Deposit Date: Apr 14, 2025
• Journal: Proceedings of the AAAI Symposium Series
• Print ISSN: 2994-4317
• Peer Reviewed: Peer Reviewed
• Volume: 4
• Issue: 1
• Pages: 89-96
• Book Title: Proceedings of the 2024 AAAI Fall Symposia
• DOI: https://doi.org/10.1609/aaaiss.v4i1.31776
• Public URL: https://uwe-repository.worktribe.com/output/14304557