Pith. sign in

REVIEW 2 cited by

Scalable Surrogate Verification of Image-based Neural Network Control Systems using Composition and Unrolling

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.18554 v3 pith:WEMFSYZI submitted 2024-05-28 cs.LG cs.ROcs.SYeess.SY

classification cs.LGcs.ROcs.SYeess.SY
keywords systemcontrolnetworkanalysiserrorneuralapproachcgan
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Verifying safety of neural network control systems that use images as input is a difficult problem because, from a given system state, there is no known way to mathematically model what images are possible in the real-world. We build on recent work that considers a surrogate verification approach, training a conditional generative adversarial network (cGAN) as an image generator in place of the real world. This enables set-based formal analysis of the closed-loop system, providing analysis beyond simulation and testing. While existing work is effective on small examples, excessive overapproximation both within a single control period and across multiple control periods limits its scalability. We propose approaches to overcome these two sources of error. First, we overcome one-step error by composing the system's dynamics along with the cGAN and neural network controller, without losing the dependencies between input states and the control outputs as in the monotonic analysis of the system dynamics. Second, we reduce multi-step error by repeating the single-step composition, essentially unrolling multiple steps of the control loop into a large neural network. We then leverage existing network verification tools to compute accurate reachable sets for multiple steps, avoiding the accumulation of abstraction error at each step. We demonstrate the effectiveness of our approach in terms of both accuracy and scalability using two case studies: an autonomous aircraft taxiing system and an advanced emergency braking system. On the aircraft taxiing system, the converged reachable set is 175% larger using the prior baseline method compared with our proposed approach. On the emergency braking system, with 24x the number of image output variables from the cGAN, the baseline method fails to prove any states are safe, whereas our improvements enable set-based safety analysis.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Towards General Language-Conditioned Latent Safety Filters

    cs.RO 2026-07 conditional novelty 6.0 of 10

    A single Hamilton-Jacobi safety filter conditioned on language constraints reduces violations in simulated pick-and-place, wiping, and stacking, with partial transfer to unseen constraint instances.

  2. Learning Ensembles of Vision-based Safety Control Filters

    cs.LG 2024-12 conditional novelty 5.0 of 10

    Ensembles of vision-based safety filters with diverse backbones and aggregation methods improve safe/unsafe classification accuracy over individual models on the DeepAccident dataset.

Pith tools