Learning Neural Network Safe Tracking Controllers from Backward Reachable Sets

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Yuezhu, Serry, Mohamed, Liu, Jun, Sivaranjani, S.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908677689049088
author Xu, Yuezhu
Serry, Mohamed
Liu, Jun
Sivaranjani, S.
author_facet Xu, Yuezhu
Serry, Mohamed
Liu, Jun
Sivaranjani, S.
contents The design of tracking controllers that closely follow a reference trajectory while ensuring safety and robustness against disturbances is a challenging problem in the control of autonomous systems. In this work, we propose a neural network-based safe tracking control framework for nonlinear discrete-time systems with reach-avoid specifications in the presence of disturbances. Our approach begins with generation of a nominal trajectory using standard trajectory synthesis approaches, followed by construction of safe zonotopic backward reachable sets along the nominal trajectory. The states lying within the backward reachable sets are guaranteed to satisfy safe reachability specifications. Then, our key insight is to leverage the computed backward reachable sets to inform the architecture and training of a neural network-based tracking controller such that the neural network drives the system's states through these backward reachable sets, thereby improving the likelihood of safe reachability. We perform formal verification with conformal prediction to achieve statistical safety guarantees on the performance of the learned neural controller. The performance of our approach is illustrated through a numerical example on the discrete-time Dubin's car model.
format Preprint
id arxiv_https___arxiv_org_abs_2511_21953
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Neural Network Safe Tracking Controllers from Backward Reachable Sets
Xu, Yuezhu
Serry, Mohamed
Liu, Jun
Sivaranjani, S.
Systems and Control
The design of tracking controllers that closely follow a reference trajectory while ensuring safety and robustness against disturbances is a challenging problem in the control of autonomous systems. In this work, we propose a neural network-based safe tracking control framework for nonlinear discrete-time systems with reach-avoid specifications in the presence of disturbances. Our approach begins with generation of a nominal trajectory using standard trajectory synthesis approaches, followed by construction of safe zonotopic backward reachable sets along the nominal trajectory. The states lying within the backward reachable sets are guaranteed to satisfy safe reachability specifications. Then, our key insight is to leverage the computed backward reachable sets to inform the architecture and training of a neural network-based tracking controller such that the neural network drives the system's states through these backward reachable sets, thereby improving the likelihood of safe reachability. We perform formal verification with conformal prediction to achieve statistical safety guarantees on the performance of the learned neural controller. The performance of our approach is illustrated through a numerical example on the discrete-time Dubin's car model.
title Learning Neural Network Safe Tracking Controllers from Backward Reachable Sets
topic Systems and Control
url https://arxiv.org/abs/2511.21953