An adaptive static-sensor network deployment strategy for detecting mobile targets. Kashino, Z., Vilela, J., Kim, J. Y., Nejat, G., & Benhabib, B. In Proceedings of the IEEE International Symposium on Safety, Security, and Rescue Robotics, pages 1–8, Lausanne, Switzerland, October, 2016.
doi  abstract   bibtex   1 download  
The mobile-target search problem has been, typically, addressed in the literature through the sole use of mobile agents. Recently, however, it has been shown that the use of static-sensor networks could significantly contribute to the likelihood of detecting a mobile target and in a shorter time. In this paper, thus, we propose a novel adaptive and optimal static-sensor network deployment strategy to detect un-trackable targets in unstructured environments. The strategy utilizes a probabilistic target-motion model representative of the demographic group to which the target belongs and realtime location history information to construct a target-location probability distribution function over the search region. The novelty of our strategy lies in the utilization of a time-varying target-location probability distribution in order to deploy sensors in a manner that is both maximally adaptive and optimal for every deployment. Network deployment for a wilderness search and rescue problem is also presented in detail as an example case. Furthermore, numerous factors that may influence the performance of our deployment strategy are discussed, including a network coverage comparative study.
@inproceedings{kashino_adaptive_2016,
	address = {Lausanne, Switzerland},
	title = {An adaptive static-sensor network deployment strategy for detecting mobile targets},
	copyright = {All rights reserved},
	doi = {10.1109/SSRR.2016.7784269},
	abstract = {The mobile-target search problem has been, typically, addressed in the literature through the sole use of mobile agents. Recently, however, it has been shown that the use of static-sensor networks could significantly contribute to the likelihood of detecting a mobile target and in a shorter time. In this paper, thus, we propose a novel adaptive and optimal static-sensor network deployment strategy to detect un-trackable targets in unstructured environments. The strategy utilizes a probabilistic target-motion model representative of the demographic group to which the target belongs and realtime location history information to construct a target-location probability distribution function over the search region. The novelty of our strategy lies in the utilization of a time-varying target-location probability distribution in order to deploy sensors in a manner that is both maximally adaptive and optimal for every deployment. Network deployment for a wilderness search and rescue problem is also presented in detail as an example case. Furthermore, numerous factors that may influence the performance of our deployment strategy are discussed, including a network coverage comparative study.},
	booktitle = {Proceedings of the {IEEE} {International} {Symposium} on {Safety}, {Security}, and {Rescue} {Robotics}},
	author = {Kashino, Z. and Vilela, J. and Kim, J. Y. and Nejat, G. and Benhabib, B.},
	month = oct,
	year = {2016},
	keywords = {Decision support systems, Robots, Safety, Security, adaptive static-sensor network deployment strategy, mobile agents, mobile robots, mobile targets detection, mobile-target search problem, optimal static-sensor network deployment strategy, probabilistic target-motion model, probability, rescue robots, robot vision, sensor fusion, target-location probability distribution function, wilderness search and rescue problem},
	pages = {1--8},
}

Downloads: 1