Stefan Mitsch

2 accepted papers

2024

Provably Safe Neural Network Controllers via Differential Dynamic Logic

Samuel Teuber, Stefan Mitsch, Andre Platzer

NeurIPS 2024poster

While neural networks (NNs) have a large potential as autonomous controllers for Cyber-Physical Systems, verifying the safety of neural network based control systems (NNCSs) poses significant challenges for the practical use of NNs— especially when safety is needed for unbounded time horizons. One r…

Cited by 7 Source ↗PDF ↗code ↗Scholar ↗

2019

A Formal Safety Net for Waypoint-Following in Ground Robots

Rose Bohrer, Yong Kiam Tan, Stefan Mitsch, Andrew Sogokon, André Platzer

RA-L 2019

We present a reusable formally verified safety net that provides end-to-end safety and liveness guarantees for two-dimensional waypoint-following of Dubins-type ground robots with tolerances and acceleration. First, we model a robot in differential dynamic logic and specify assumptions on the contro

Cited by 31 Source ↗Scholar ↗