Sampling-based Reachability Analysis: A Random Set Theory Approach with Adversarial Sampling
arXiv:2008.10180
Abstract
Reachability analysis is at the core of many applications, from neural network verification, to safe trajectory planning of uncertain systems. However, this problem is notoriously challenging, and current approaches tend to be either too restrictive, too slow, too conservative, or approximate and therefore lack guarantees. In this paper, we propose a simple yet effective sampling-based approach to perform reachability analysis for arbitrary dynamical systems. Our key novel idea consists of using random set theory to give a rigorous interpretation of our method, and prove that it returns sets which are guaranteed to converge to the convex hull of the true reachable sets. Additionally, we leverage recent work on robust deep learning and propose a new adversarial sampling approach to robustify our algorithm and accelerate its convergence. We demonstrate that our method is faster and less conservative than prior work, present results for approximate reachability analysis of neural networks and robust trajectory optimization of high-dimensional uncertain nonlinear systems, and discuss future applications.
arXiv commentIn Conference on Robot Learning (CoRL) 2020
References in corpus (7)
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- OSQP: An Operator Splitting Solver for Quadratic Programs
- Input Convex Neural Networks
- Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach
- Performance Bounds for the Scenario Approach and an Extension to a Class of Non-convex Programs
- A Real-Time Approach for Chance-Constrained Motion Planning with Dynamic Obstacles
- Learning-based Model Predictive Control for Safe Exploration