Safe Optimal Control Using Stochastic Barrier Functions and Deep Forward-Backward SDEs
Abstract
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.
Cite
Text
Pereira et al. "Safe Optimal Control Using Stochastic Barrier Functions and Deep Forward-Backward SDEs." Conference on Robot Learning, 2020.Markdown
[Pereira et al. "Safe Optimal Control Using Stochastic Barrier Functions and Deep Forward-Backward SDEs." Conference on Robot Learning, 2020.](https://mlanthology.org/corl/2020/pereira2020corl-safe/)BibTeX
@inproceedings{pereira2020corl-safe,
title = {{Safe Optimal Control Using Stochastic Barrier Functions and Deep Forward-Backward SDEs}},
author = {Pereira, Marcus and Wang, Ziyi and Exarchos, Ioannis and Theodorou, Evangelos},
booktitle = {Conference on Robot Learning},
year = {2020},
pages = {1783-1801},
volume = {155},
url = {https://mlanthology.org/corl/2020/pereira2020corl-safe/}
}