Stochastic World Models for Verifying Vision-Based Neural Feedback Systems
[Sztuczna inteligencja] Autorzy: I. Samuel Akinwande, Mykel J. Kochenderfer, Clark Barrett
Verifying a vision-based neural feedback system requires a model of the observations its controller acts upon. Such a model must capture the variation the sensor produces, while remaining tractable for closed-loop analysis. Generative adversarial networks (GANs) have served as perception surrogates, but they are large, reproduce complex scenes poorly, and are hard to verify. We explore stochastic world models as a richer class of perception surrogates. We train a world model with physically grounded latents, built from operations that standard verifiers bound. It reproduces held-out frames more faithfully than GAN surrogates with up to 130 times as many parameters. To verify these surrogates, we develop a procedure that combines falsification, adaptive refinement, symbolic, and backward analyses. On an emergency braking benchmark with a GAN surrogate, our procedure resolves the entire s…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja