Can I read Verification of Neural Reachable Tubes via Scenario Optimization and Conformal Prediction on EtoBox?

Verification of Neural Reachable Tubes via Scenario Optimization and Conformal Prediction by Lin, Albert; Bansal, Somil is a scholarly article available to read on EtoBox.

What is Verification of Neural Reachable Tubes via Scenario Optimization and Conformal Prediction about?

Learning-based approaches for controlling safety-critical systems are rapidly growing in popularity; thus, it is important to assure their performance and safety. Hamilton-Jacobi (HJ) reachability analysis is a popular formal verification tool for providing such guarantees, since it can handle general nonlinear system dynamics, bounded adversarial system disturbances, and state and input constraints. However, its computational and memory complexity scales exponentially with the state dimension, making it intractable for large-scale systems. To overcome this challenge, neural approaches, such as DeepReach, have been used to synthesize reachable tubes and safety controllers for high-dimensional systems. However, verifying these neural reachable tubes remains challenging. In this work, we propose two verification methods, based on robust scenario optimization and conformal prediction, to provide probabilistic safety guarantees for neural reachable tubes. Our methods allow a direct trade-off between resilience to outlier errors in the neural tube, which are inevitable in a learning-based approach, and the strength of the probabilistic safety guarantee. Furthermore, we show that split c

Author

Lin, Albert; Bansal, Somil

Published

2023

Language

EN