Stochastic Reachability of Uncontrolled Systems via Probability Measures: Approximation via Deep Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sivaramakrishnan, Karthik, Sivaramakrishnan, Vignesh, Devonport, Rosalyn Alex, Oishi, Meeko M. K.
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909424908500992
author Sivaramakrishnan, Karthik
Sivaramakrishnan, Vignesh
Devonport, Rosalyn Alex
Oishi, Meeko M. K.
author_facet Sivaramakrishnan, Karthik
Sivaramakrishnan, Vignesh
Devonport, Rosalyn Alex
Oishi, Meeko M. K.
contents This paper poses a theoretical characterization of the stochastic reachability problem in terms of probability measures, capturing the probability measure of the state of the system that satisfies the reachability specification for all probabilities over a finite horizon. We achieve this by constructing the level sets of the probability measure for all probability values and, since our approach is only for autonomous systems, we can determine the level sets via forward simulations of the system from a point in the state space at some time step in the finite horizon to estimate the reach probability. We devise a training procedure which exploits this forward simulation and employ it to design a deep neural network (DNN) to predict the reach probability provided the current state and time step. We validate the effectiveness of our approach through three examples.
format Preprint
id arxiv_https___arxiv_org_abs_2304_00598
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Stochastic Reachability of Uncontrolled Systems via Probability Measures: Approximation via Deep Neural Networks
Sivaramakrishnan, Karthik
Sivaramakrishnan, Vignesh
Devonport, Rosalyn Alex
Oishi, Meeko M. K.
Optimization and Control
Systems and Control
This paper poses a theoretical characterization of the stochastic reachability problem in terms of probability measures, capturing the probability measure of the state of the system that satisfies the reachability specification for all probabilities over a finite horizon. We achieve this by constructing the level sets of the probability measure for all probability values and, since our approach is only for autonomous systems, we can determine the level sets via forward simulations of the system from a point in the state space at some time step in the finite horizon to estimate the reach probability. We devise a training procedure which exploits this forward simulation and employ it to design a deep neural network (DNN) to predict the reach probability provided the current state and time step. We validate the effectiveness of our approach through three examples.
title Stochastic Reachability of Uncontrolled Systems via Probability Measures: Approximation via Deep Neural Networks
topic Optimization and Control
Systems and Control
url https://arxiv.org/abs/2304.00598