Nodes self-deployment for coverage maximization in mobile robot networks using an evolving neural network

  • Authors:

  • Carmelo Costanzo;Valeria Loscrí;Enrico Natalizio;Tahiry Razafindralambo

  • Affiliations:

  • Department of Electronics, Computer and Systems, University of Calabria, Rende 87036, Italy;Department of Electronics, Computer and Systems, University of Calabria, Rende 87036, Italy;POPS Team, INRIA Lille - Nord Europe, Villeneuve d'Ascq 59650, France;POPS Team, INRIA Lille - Nord Europe, Villeneuve d'Ascq 59650, France

  • Venue:
  • Computer Communications
  • Year:
  • 2012

Quantified Score

Hi-index 0.24

Visualization

Abstract

There are many critical issues arising in wireless sensor and robot networks (WSRN). Based on the specific application, different objectives can be taken into account such as energy consumption, throughput, delay, coverage, etc. Also many schemes have been proposed in order to optimize a specific quality of service (QoS) parameter. With the focus on the self-organizing capabilities of nodes in WSRN, we propose a movement-assisted technique for nodes self-deployment. Specifically, we propose to use a neural network as a controller for nodes mobility and a genetic algorithm for the training of the neural network through reinforcement learning [27]. This kind of scheme is extremely adaptive, since it can be easily modified in order to consider different objectives and QoS parameters. In fact, it is sufficient to consider a different kind of input for the neural network to aim for a different objective. All things considered, we propose a new method for programming a WSRN and we show practically how the technique works, when the coverage of the network is the QoS parameter to optimize. Simulation results show the flexibility and effectiveness of this approach even when the application scenario changes (e.g., by introducing physical obstacles).