eduzhai > Applied Sciences > Engineering >

Safe Optimal Control Using Stochastic Barrier Functions and Deep Forward-Backward SDEs

  • king
  • (0) Download
  • 20210507
  • Save

... pages left unread,continue reading

Document pages: 19 pages

Abstract: This paper introduces a new formulation for stochastic optimal control andstochastic dynamic optimization that ensures safety with respect to state andcontrol constraints. The proposed methodology brings together concepts such asForward-Backward Stochastic Differential Equations, Stochastic BarrierFunctions, Differentiable Convex Optimization and Deep Learning. Using theaforementioned concepts, a Neural Network architecture is designed for safetrajectory optimization in which learning can be performed in an end-to-endfashion. Simulations are performed on three systems to show the efficacy of theproposed methodology.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×