Search and Rescue in a Maze-like Environment with Ant and Dijkstra Algorithms

11/17/2021
by   Z. Husain, et al.
0

With the growing reliability of modern Ad Hoc Networks, it is encouraging to analyze potential involvement of autonomous Ad Hoc agents in critical situations where human involvement could be perilous. One such critical scenario is the Search and Rescue effort in the event of a disaster where timely discovery and help deployment is of utmost importance. This paper demonstrates the applicability of a bio-inspired technique, namely Ant Algorithms (AA), in optimizing the search time for a near optimal path to a trapped victim, followed by the application of Dijkstra's algorithm in the rescue phase. The inherent exploratory nature of AA is put to use for a faster mapping and coverage of the unknown search space. Four different AA are implemented, with different effects of the pheromone in play. An inverted AA, with repulsive pheromones, was found to be the best fit for this particular application. After considerable exploration, upon discovery of the victim, the autonomous agents further facilitate the rescue process by forming a relay network, using the already deployed resources. Hence, the paper discusses a detailed decision making model of the swarm, segmented into two primary phases, responsible for the search and rescue respectively. Different aspects of the performance of the agent swarm are analyzed, as a function of the spatial dimensions, the complexity of the search space, the deployed search group size, and the signal permeability of the obstacles in the area.

READ FULL TEXT

page 3

page 10

page 17

page 18

page 19

page 25

research
08/11/2020

An ad-hoc social network generation approach

The use of social networks is still confined to infrastructure-based net...
research
08/09/2022

Ad Hoc Teamwork in the Presence of Adversaries

Advances in ad hoc teamwork have the potential to create agents that col...
research
12/26/2022

Deployment of UAVs for Optimal Multihop Ad-hoc Networks Using Particle Swarm Optimization and Behavior-based Control

This study proposes an approach for establishing an optimal multihop ad-...
research
02/18/2022

Route Discovery and Capacity of Ad hoc Networks

Throughput capacity of large ad hoc networks has been shown to scale adv...
research
02/11/2022

Automated Architecture Search for Brain-inspired Hyperdimensional Computing

This paper represents the first effort to explore an automated architect...
research
03/29/2022

Efficiently Evolving Swarm Behaviors Using Grammatical Evolution With PPA-style Behavior Trees

Evolving swarm behaviors with artificial agents is computationally expen...
research
07/12/2018

Achieving Connectivity Between Wide Areas Through Self-Organising Robot Swarm Using Embodied Evolution

Abruptions to the communication infrastructure happens occasionally, whe...

Please sign up or login with your details

Forgot password? Click here to reset