F.A. Khan, S. Khan, D. Turgut, and L. Bölöni. Greedy Path Planning for Maximizing Value of Information in Underwater Sensor Networks. In IEEE P2MNet'14, pp. 39–44, September 2014.
Underwater sensor networks (UWSNs) face specific challenges due to the transmission properties in the underwater environment. Radio waves propagate only for short distances under water, and acoustic transmissions have limited data rate and relatively high latency. One of the possible solutions to these challenges involves the use of autonomous underwater vehicles (AUVs) to visit and offload data from the individual sensor nodes. We consider an underwater sensor network visually monitoring an offshore oil platform for hazards such as oil spills from pipes and blowups. To each observation chunk (image or video) we attach a numerical value of information (VoI). This value monotonically decreases in time with a speeed which depends on the urgency of the captured data. An AUV visits different nodes along a specific path and collects data to be transmitted to the customer. Our objective is to develop path planners for the movement of the AUV which maximizes the total VoI collected. We consider three different path planners: the lawn mower path planner (LPP), the greedy planner (GPP) and the random planner (RPP). In a simulation study we compare the total VoI collected by these algorithms and show that the GPP outperforms the other two proposed algorithms on the studied scenarios.
@inproceedings{Khan-2014-P2MNet,
author = "F.A. Khan and S. Khan and D. Turgut and L. B{\"o}l{\"o}ni",
title = "Greedy Path Planning for Maximizing Value of Information in Underwater Sensor Networks",
booktitle = "IEEE P2MNet'14",
pages = "39-44",
month = "September",
year = "2014",
abstract = {
Underwater sensor networks (UWSNs) face specific challenges due to the transmission properties in the underwater environment. Radio waves propagate only for short distances under water, and acoustic transmissions have limited data rate and relatively high latency. One of the possible solutions to these challenges involves the use of autonomous underwater vehicles (AUVs) to visit and offload data from the individual sensor nodes. We consider an underwater sensor network visually monitoring an offshore oil platform for hazards such as oil spills from pipes and blowups. To each observation chunk (image or video) we attach a numerical value of information (VoI). This value monotonically decreases in time with a speeed which depends on the urgency of the captured data. An AUV visits different nodes along a specific path and collects data to be transmitted to the customer. Our objective is to develop path planners for the movement of the AUV which maximizes the total VoI collected. We consider three different path planners: the lawn mower path planner (LPP), the greedy planner (GPP) and the random planner (RPP). In a simulation study we compare the total VoI collected by these algorithms and show that the GPP outperforms the other two proposed algorithms on the studied scenarios.
},
}
Generated by bib2html.pl (written by Patrick Riley, Lotzi Boloni ) on Sun Mar 03, 2024 18:41:15