CNCS Center for Nonlinear and Complex Systems
   Search Help Login pdf version printable version

Publications [#289484] of Silvia Ferrari

Papers Published

  1. Ferrari, S; Daugherty, G, A Q-learning approach to automated unmanned air vehicle demining, The Journal of Defense Modeling and Simulation: Applications, Methodology, Technology, vol. 9 no. 1 (January, 2012), pp. 83-92, SAGE Publications, ISSN 1548-5129 [doi]
    (last updated on 2021/09/05)

    Abstract:
    This paper develops a novel Q-learning approach to unmanned aerial vehicle (UAV) navigation, or path planning, for sensing applications in which an infrared (IR) sensor or camera is installed onboard the UAV for the purpose of detecting and classifying multiple, stationary ground targets. The main advantage of this approach over existing path planning techniques is that the optimal guidance policy is learned via the Q-function, without explicit knowledge of the system models and environmental conditions. As a result, the onboard guidance algorithm can adapt to different sensors, vehicle dynamics, and environmental conditions, without designer intervention, and without the need for accurate modeling of every system component. The approach is demonstrated through a demining application in which a UAV-based IR sensor is capable of determining the optimal altitude for properly detecting and classifying targets buried in a complex region of interest. © 2012 The Society for Modeling and Simulation International.