Search Results for author:
Found 14 papers, 8 papers with code
Synthesis of Hierarchical Controllers Based on Deep Reinforcement Learning Policies
We propose a novel approach to the problem of controller design for environments modeled as Markov decision processes (MDPs).
Shielded Reinforcement Learning for Hybrid Systems
We experimentally demonstrate superiority of the pre-shielding approach.
The inverse problem for neural networks
We study the problem of computing the preimage of a set under a neural network with piecewise-affine activation functions.
Synthesis of Parametric Hybrid Automata from Time Series
We propose an algorithmic approach for synthesizing linear hybrid automata from time-series data.
Open- and Closed-Loop Neural Network Verification using Polynomial Zonotopes
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.
Verification of Neural-Network Control Systems by Integrating Taylor Models and Zonotopes
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.
SpecRepair: Counter-Example Guided Safety Repair of Deep Neural Networks
Deep neural networks (DNNs) are increasingly applied in safety-critical domains, such as self-driving cars, unmanned aircraft, and medical diagnosis.
Into the Unknown: Active Monitoring of Neural Networks
To address this challenge, we introduce an algorithmic framework for active monitoring of a neural network.
Efficient reachability analysis of parametric linear hybrid systems with time-triggered transitions
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.
Outside the Box: Abstraction-Based Monitoring of Neural Networks
Neural networks have demonstrated unmatched performance in a range of classification tasks.
Reachability analysis of linear hybrid systems via block decomposition
Reachability analysis aims at identifying states reachable by a system within a given time horizon.
Systems and Control Dynamical Systems Optimization and Control
JuliaReach: a Toolbox for Set-Based Reachability
We present JuliaReach, a toolbox for set-based reachability analysis of dynamical systems.
Systems and Control Dynamical Systems
Reach Set Approximation through Decomposition with Low-dimensional Sets and High-dimensional Matrices
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
Instrumenting an SMT Solver to Solve Hybrid Network Reachability Problems
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.
