Note: This content is accessible to all versions of every browser. However, this browser does not seem to support current Web standards, preventing the display of our site's design details.


Neural approximation of PDE solutions: An application to reachability computations


B. Djeridane, J. Lygeros

IEEE Conference on Decision and Control, Dec 13-15, San Diego, USA., pp. 3034-3039

We consider the problem of computing viability sets for nonlinear continuous systems. Our main goal is to deal with the ”curse of dimensionality”, the exponential growth of the computation in the dimension of the state space. The viability problem is formulated as an optimal control problem whose value function is known to be a viscosity solution to a particular type of Hamilton Jacobi partial differential equation. We propose a trial solution based on a Feed-Forward Neural Network for the Hamilton Jacobi equation with the given boundary conditions. We use random extractions from the state space to generate training points and then employ the r-algorithm for non smooth optimization to train the network. We illustrate the method on a 2 dimensional example from aerodynamic envelope protection.


Type of Publication:


J. Lygeros

File Download:

Request a copy of this publication.
(Uses JavaScript)
% Autogenerated BibTeX entry
@InProceedings { DjeLyg:2006:IFA_2569,
    author={B. Djeridane and J. Lygeros},
    title={{Neural approximation of PDE solutions: An application to
	  reachability computations}},
    booktitle={IEEE Conference on Decision and Control},
    address={Dec 13-15, San Diego, USA.},
Permanent link