no code implementations • 21 Feb 2024 • Florent Delgrange, Guy Avni, Anna Lukina, Christian Schilling, Ann Nowé, Guillermo A. Pérez
We propose a novel approach to the problem of controller design for environments modeled as Markov decision processes (MDPs).
1 code implementation • 28 Aug 2023 • Asger Horn Brorholt, Peter Gjøl Jensen, Kim Guldstrand Larsen, Florian Lorber, Christian Schilling
We experimentally demonstrate superiority of the pre-shielding approach.
1 code implementation • 27 Aug 2023 • Marcelo Forets, Christian Schilling
We study the problem of computing the preimage of a set under a neural network with piecewise-affine activation functions.
1 code implementation • 13 Jul 2022 • Miriam García Soto, Thomas A. Henzinger, Christian Schilling
We propose an algorithmic approach for synthesizing linear hybrid automata from time-series data.
no code implementations • 6 Jul 2022 • Niklas Kochdumper, Christian Schilling, Matthias Althoff, Stanley Bak
We present a novel approach to efficiently compute tight non-convex enclosures of the image through neural networks with ReLU, sigmoid, or hyperbolic tangent activation functions.
1 code implementation • 16 Dec 2021 • Christian Schilling, Marcelo Forets, Sebastian Guadalupe
When considering dynamical systems and neural networks in isolation, there exist precise approaches for that task based on set representations respectively called Taylor models and zonotopes.
1 code implementation • 3 Jun 2021 • Fabian Bauer-Marquart, David Boetius, Stefan Leue, Christian Schilling
Deep neural networks (DNNs) are increasingly applied in safety-critical domains, such as self-driving cars, unmanned aircraft, and medical diagnosis.
1 code implementation • 14 Sep 2020 • Anna Lukina, Christian Schilling, Thomas A. Henzinger
To address this challenge, we introduce an algorithmic framework for active monitoring of a neural network.
1 code implementation • 22 Jun 2020 • Marcelo Forets, Daniel Freire, Christian Schilling
In this paper we present an approach based on conservative set-based enclosure of the dynamics that can handle systems with uncertain parameters and inputs, where the uncertainties are bound to given intervals.
1 code implementation • 20 Nov 2019 • Thomas A. Henzinger, Anna Lukina, Christian Schilling
Neural networks have demonstrated unmatched performance in a range of classification tasks.
no code implementations • 7 May 2019 • Sergiy Bogomolov, Marcelo Forets, Goran Frehse, Kostiantyn Potomkin, Christian Schilling
Reachability analysis aims at identifying states reachable by a system within a given time horizon.
Systems and Control Dynamical Systems Optimization and Control
no code implementations • 30 Jan 2019 • Sergiy Bogomolov, Marcelo Forets, Goran Frehse, Kostiantyn Potomkin, Christian Schilling
We present JuliaReach, a toolbox for set-based reachability analysis of dynamical systems.
Systems and Control Dynamical Systems
no code implementations • 29 Jan 2018 • Sergiy Bogomolov, Marcelo Forets, Goran Frehse, Andreas Podelski, Christian Schilling, Frédéric Viry
Approximating the set of reachable states of a dynamical system is an algorithmic yet mathematically rigorous way to reason about its safety.
Systems and Control Dynamical Systems
no code implementations • 13 Sep 2016 • Daniel Bryce, Sergiy Bogomolov, Alexander Heinz, Christian Schilling
PDDL+ planning has its semantics rooted in hybrid automata (HA) and recent work has shown that it can be modeled as a network of HAs.