AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

OVERT: An Algorithm for Safety Verification of Neural Network Control Policies for Nonlinear Systems

Chelsea Sidrane, Amir Maleki, Ahmed Irfan, Mykel J. Kochenderfer

JMLR 2022 · Probabilistic and scientific modeling › Dynamical systems · approach: Stable contractive dynamics · 32 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use OVERT reachable set computation instead of NNVclosed-loop verification · S1 single pendulumruntime (s) and property proof: 483 -> 99Improved
use OVERT reachable set computation instead of NNVclosed-loop verification · T1 TORAruntime: Time Out -> 232Improved
use OVERT feasibility framing instead of dRealclosed-loop verification · S1 single pendulumruntime (s): Time Out -> 77Improved
use OVERT feasibility framing instead of dRealclosed-loop verification · T1 TORAruntime (s): 12655 -> 79Improved
use feasibility framing instead of reachable-set framingOVERT · S1 single pendulumruntime (s): 99 -> 77Improved
use feasibility framing instead of reachable-set framingOVERT · T1 TORAruntime (s): 232 -> 79Improved
use hybrid symbolic queries instead of naive one-step concrete sets (ablation)OVERT reachability · S1/S2 single pendulumsafety property provenImproved
use hybrid symbolic queries instead of naive one-step concrete sets (ablation)OVERT reachability · S2 single pendulumruntime (minutes): less than 4 minutes -> just under 12 minutesHurt
use hybrid symbolic queries instead of concrete sets (ablation)OVERT reachability · Adaptive cruise controlreachable set tightnessMixed
increase number of linear segments n in the overapproximation (ablation)OVERT MIP · benchmarksMIP solve difficultyNo clear effect
increase neural network size (T1 to T3 TORA) (ablation)OVERT reach · TORAruntimeHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy