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.

  

Stochastic reachability for surveillance systems: design, implementation and potential extensions via approximate dynamic programming (ADP)

Author(s):

N. Kariotoglou
Conference/Journal:

Polytechnic University of Bucharest, Romania
Abstract:

In this talk we present a stochastic reachability formulation to the surveillance problems of target tracking and acquisition. Our approach involves solving an optimal control problem for Markov decision processes via dynamic programming which is computationally intractable when posed for a collection of surveillance agents. To alleviate this problem we present a task allocation mechanism that decouples agent objectives making solutions tractable but sub-optimal. We verify our results via experiments on a two-camera, two-evader system. In the last part of the talk we present an optimization based approach to ADP which aims to deal, in a more general sense, with computational tractability of dynamic programs arising in stochastic reachability

Year:

2014
Type of Publication:

(06)Talk
Supervisor:

J. Lygeros

File Download:

Request a copy of this publication.
(Uses JavaScript)
% No recipe for automatically generating a BibTex entry for (06)Talk
Permanent link