2 citations · 5 across the 29 of their papers we have counts for
12 papers · 1 filter
Safe-by-Design Learning via Energy-based Neural Networks
Simone Betteti, Morteza Lahijanian, Luca Laurenti
Learning neural-network models of dynamical systems with safety guarantees is a fundamental requirement for their deployment in safety-critical settings. Safety is commonly establi…
Clustered Randomized Smoothing for Stochastic Prediction Functions
Eduardo Figueiredo, Frederik Mathiesen, Julian Schumann +3
Modern stochastic predictors can model rich, multi-modal outcome distributions. However, this expressive power comes with challenges in ensuring robust predictions a critical r…
Evaluating randomized smoothing as a defense against adversarial attacks in trajectory prediction
Julian F. Schumann, Eduardo Figueiredo, Frederik Baymler Mathiesen +3
Accurate and robust trajectory prediction is essential for safe and efficient autonomous driving, yet recent work has shown that even state-of-the-art prediction models are highly…
Efficient Distribution Learning with Error Bounds in Wasserstein Distance
Eduardo Figueiredo, Steven Adams, Luca Laurenti
The Wasserstein distance has emerged as a key metric to quantify distances between probability distributions, with applications in various fields, including machine learning, contr…
Verification of Unknown Dynamical Systems via Autoencoder Latent Space
Robert Reed, Luca Laurenti, Morteza Lahijanian
Formal verification provides a powerful framework for proving that dynamical systems satisfy their specifications. However, these techniques face scalability challenges in high-dim…
discretize_distributions: Efficient Quantization of Gaussian Mixtures with Guarantees in Wasserstein Distance
Steven Adams, Elize Alwash, Luca Laurenti
We present discretize_distributions, a Python package that efficiently constructs discrete approximations of Gaussian mixture distributions and provides guarantees on the approxima…
Scalable Verification of Neural Control Barrier Functions Using Linear Bound Propagation
Nikolaus Vertovec, Frederik Baymler Mathiesen, Thom Badings +2
Control barrier functions (CBFs) are a popular tool for safety certification of nonlinear dynamical control systems. Recently, CBFs represented as neural networks have shown great…
Certified Neural Approximations of Nonlinear Dynamics
Frederik Baymler Mathiesen, Nikolaus Vertovec, Francesco Fabiano +2
Neural networks hold great potential to act as approximate models of nonlinear dynamical systems, with the resulting neural approximations enabling verification and control of such…
Error Bounds for Physics-Informed Neural Networks in Fokker-Planck PDEs
Chun-Wei Kong, Luca Laurenti, Jay McMahon +1
Stochastic differential equations are commonly used to describe the evolution of stochastic processes. The state uncertainty of such processes is best represented by the probabilit…
Error Bounds For Gaussian Process Regression Under Bounded Support Noise With Applications To Safety Certification
Robert Reed, Luca Laurenti, Morteza Lahijanian
Gaussian Process Regression (GPR) is a powerful and elegant method for learning complex functions from noisy data with a wide range of applications, including in safety-critical do…
Finite Neural Networks as Mixtures of Gaussian Processes: From Provable Error Bounds to Prior Selection
Steven Adams, Andrea Patanè, Morteza Lahijanian +1
Infinitely wide or deep neural networks (NNs) with independent and identically distributed (i.i.d.) parameters have been shown to be equivalent to Gaussian processes. Because of th…
Data-Driven Permissible Safe Control with Barrier Certificates
Rayan Mazouz, John Skovbekk, Frederik Baymler Mathiesen +3
This paper introduces a method of identifying a maximal set of safe strategies from data for stochastic systems with unknown dynamics using barrier certificates. The first step is…