This paper introduces a new formulation for stochastic optimal control and stochastic dynamic optimization that ensures safety with respect to state and control constraints. The proposed methodology brings together concepts such as Forward-Backward Stochastic Differential Equations, Stochastic Barrier Functions, Differentiable Convex Optimization and Deep Learning. Using the aforementioned concepts, a Neural Network architecture is designed for safe trajectory optimization in which learning can be performed in an end-to-end fashion. Simulations are performed on three systems to show the efficacy of the proposed methodology.
@article{arxiv.2009.01196,
title = {Safe Optimal Control Using Stochastic Barrier Functions and Deep Forward-Backward SDEs},
author = {Marcus Aloysius Pereira and Ziyi Wang and Ioannis Exarchos and Evangelos A. Theodorou},
journal= {arXiv preprint arXiv:2009.01196},
year = {2021}
}