Efficient Interaction-Aware Interval Analysis of Neural Network Feedback Loops

arXiv:2307.14938v3 Announce Type: replace-cross
Abstract: In this paper, we propose a computationally efficient framework for interval reachability of systems with neural network controllers. Our approach leverages inclusion functions for the open-loop system and the neural network controller to embed the closed-loop system into a larger-dimensional embedding system, where a single trajectory over-approximates the original system's behavior under uncertainty. We propose two methods for constructing closed-loop embedding systems, which account for the interactions between the system and the controller in different …

abstract analysis arxiv cs.lg cs.sy eess.sy embed embedding feedback framework functions inclusion interval loop loops math.oc network neural network paper replace systems trajectory type