Search Results for author:
Found 10 papers, 2 papers with code
Scaling Learning based Policy Optimization for Temporal Tasks via Dropout
We show how this learning problem is similar to training recurrent neural networks (RNNs), where the number of recurrent units is proportional to the temporal horizon of the agent's task objectives.
Robust Conformal Prediction for STL Runtime Verification under Distribution Shift
To address these challenges, we assume to know an upper bound on the statistical distance (in terms of an f-divergence) between the distributions at deployment and design time, and we utilize techniques based on robust conformal prediction.
Safety Under Uncertainty: Tight Bounds with Risk-Aware Control Barrier Functions
We propose a novel class of risk-aware control barrier functions (RA-CBFs) for the control of stochastic safety-critical systems.
A Neurosymbolic Approach to the Verification of Temporal Logic Properties of Learning enabled Control Systems
In this paper, we present a model for the verification of Neural Network (NN) controllers for general STL specifications using a custom neural architecture where we map an STL formula into a feed-forward neural network with ReLU activation.
Risk-Awareness in Learning Neural Controllers for Temporal Logic Objectives
In this paper, we consider the problem of synthesizing a controller in the presence of uncertainty such that the resulting closed-loop system satisfies certain hard constraints while optimizing certain (soft) performance objectives.
Formalizing and Evaluating Requirements of Perception Systems for Automated Vehicles using Spatio-Temporal Perception Logic
Automated vehicles (AV) heavily depend on robust perception systems.
Risk-Bounded Control with Kalman Filtering and Stochastic Barrier Functions
Our goal is to design controllers that bound the probability of a system failure in finite-time to a given desired value.
Neural Network Repair with Reachability Analysis
Formally verifying the safety and robustness of well-trained DNNs and learning-enabled systems under attacks, model uncertainties, and sensing errors is essential for safe autonomy.
Reachability Analysis of Convolutional Neural Networks
Besides the computation of reachable sets, our approach is also capable of backtracking to the input domain given an output reachable set.
Search-based Test-Case Generation by Monitoring Responsibility Safety Rules
The safety of Automated Vehicles (AV) as Cyber-Physical Systems (CPS) depends on the safety of their consisting modules (software and hardware) and their rigorous integration.
