Learning Safety Filters for Unknown Discrete-Time Linear Systems
Machine Learning
2023-05-09 v2 Systems and Control
Systems and Control
Optimization and Control
Probability
Machine Learning
Abstract
A learning-based safety filter is developed for discrete-time linear time-invariant systems with unknown models subject to Gaussian noises with unknown covariance. Safety is characterized using polytopic constraints on the states and control inputs. The empirically learned model and process noise covariance with their confidence bounds are used to construct a robust optimization problem for minimally modifying nominal control actions to ensure safety with high probability. The optimization problem relies on tightening the original safety constraints. The magnitude of the tightening is larger at the beginning since there is little information to construct reliable models, but shrinks with time as more data becomes available.
Cite
@article{arxiv.2111.00631,
title = {Learning Safety Filters for Unknown Discrete-Time Linear Systems},
author = {Farhad Farokhi and Alex S. Leong and Mohammad Zamani and Iman Shames},
journal= {arXiv preprint arXiv:2111.00631},
year = {2023}
}