Abstract | ||
---|---|---|
This paper proposes a distributed multi-agent framework for discovering and optimizing evacuation routes on demand. Our framework assumes mobile ad hoc networks (MANETs) composed of smartphones with geo-location capabilities. On the network, heterogeneous mobile agents cooperatively insert knowledge about crowd in our mass evacuation framework. They are relying exclusively on crowd sourcing; therefore our framework is layout independent and adaptable for any situation. The mobile agents take advantage of ant colony optimization (ACO) in order to collect such knowledge. Once users reach safe areas, they distribute agents to inform the directions of the locations of the safe areas. On the other hand, evacuating users distribute agents to search safe areas, based on guidance given by the agents from the safe areas. Once each searching agent reaches the safe area, it traces its path backwardly collecting geographical information of intermediate nodes for composing an evacuation route. During the backward travel, agents lay down pheromone as they migrate back based on the ACO algorithm, strengthening quasi-optimal physical routes, and hence guiding succeeding agents. A characteristic of pheromone in this family of algorithms is that it lessens during run-time, keeping the information about successful escape routes current, as is essential in an evacuation scenario. We have implemented a simulator based on our framework in order to show the effectiveness of our technique. We discuss the behaviors of our system with various settings on the simulator for real world implementation in the near future. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1007/978-3-662-44994-3_7 | Lecture Notes in Computer Science |
Field | DocType | Volume |
Ant colony optimization algorithms,Mobile ad hoc network,Route planning,On demand,Computer science,As is,Mobile agent,Global position system,Distributed computing | Journal | 8790 |
ISSN | Citations | PageRank |
0302-9743 | 1 | 0.40 |
References | Authors | |
10 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Alejandro Avilés del Moral | 1 | 2 | 0.75 |
Munehiro Takimoto | 2 | 92 | 21.45 |
Yasushi Kambayashi | 3 | 124 | 29.76 |