14 papers
STLSat---An Improved Tableau for Satisfiability Checking of Signal Temporal Logic Formulas
Marco Zamponi, Florian Lammel, Ezio Bartocci +1
Signal Temporal Logic (STL) is a formalism used to describe temporal properties of real-valued signals in cyber-physical systems. In mission- and safety-critical domains, specifica…
ORCAID: Oblique Rule-Based Continuous-Action Interpretation for Deep RL Policies
Ignacio D. Lopez-Miguel, Ezio Bartocci, Thomas Eiter +1
Explainability remains a key issue in reinforcement learning (RL). Distilling an interpretable policy from an agent trained in a complex environment is particularly challenging whe…
Differential Zonotopes for Verifying Global Robustness of DNNs
Anagha Athavale, Samuel Teuber, Matteo Maffei +3
The robustness of deep neural networks (DNNs) is critical in security-sensitive applications, where small input perturbations should not alter model predictions. This property is c…
A Survey on the Verification of Reinforcement Learning Policies
Luca Marzari, Ezio Bartocci, Enrico Marchesini
Reinforcement learning (RL) is increasingly applied in complex, safety-critical domains, yet the lack of rigorous behavioral guarantees for neural network-based policies remains a…
Declarative Scenario-based Testing with RoadLogic
Ezio Bartocci, Alessio Gambi, Felix Gigler +2
Scenario-based testing is a key method for cost-effective and safe validation of autonomous vehicles (AVs). Existing approaches rely on imperative scenario definitions, requiring d…
Towards Safe Learning-Based Non-Linear Model Predictive Control through Recurrent Neural Network Modeling
Mihaela-Larisa Clement, Mónika Farsang, Agnes Poks +4
The practical deployment of nonlinear model predictive control (NMPC) is often limited by online computation: solving a nonlinear program at high control rates can be expensive on…