# Adaptive Cooperative Search Algorithm for Air Pollution Detection Using Drones

## TL;DR

This paper introduces a new algorithm for using two drones to detect air pollution more efficiently than single drones or linear search methods.

## Contribution

A 3D cube-based adaptive cooperative search algorithm for efficient air pollution detection using multiple drones.

## Key findings

- Cooperative search with two drones reduces CPU time by 2.6 times and search distance by half compared to single drones.
- The proposed method consumes 21 times less CPU time and 23 times less search distance than linear search.
- Multiple drones using the algorithm successfully detected pollution above threshold levels in real-world experiments.

## Abstract

What are the main findings?
Cooperative search using two drones consumes approximately 2.6 times less CPU time than a single-drone search and covers half the search distance.Compared to linear search, the proposed method consumed 21 times less CPU time and required 23 times less search distance.

Cooperative search using two drones consumes approximately 2.6 times less CPU time than a single-drone search and covers half the search distance.

Compared to linear search, the proposed method consumed 21 times less CPU time and required 23 times less search distance.

What is the implication of the main finding?
The study provides insights into drone-assisted target exploration.The proposed algorithm could be extended to more than two drones.

The study provides insights into drone-assisted target exploration.

The proposed algorithm could be extended to more than two drones.

Drones are widely used in urban air pollution monitoring. Although studies have focused on single-drone applications, collaborative applications for air pollution detection are relatively underexplored. This paper presents a 3D cube-based adaptive cooperative search algorithm that allows two drones to collaborate to explore air pollution. The search space is divided into cubic regions, and each drone explores the upper or lower halves of the cubes and collects data from their vertices. The vertex with the highest measurement is selected by comparing the collected data, and an adjacent cube-shaped search area is generated for exploration. The search continues iteratively until any vertex measurement reaches a predefined threshold. An improved algorithm is also proposed to address the divergence and oscillation that occur during the search. In simulations, the proposed method consumed 21 times less CPU time and required 23 times less search distance compared to linear search. Additionally, the cooperative search method using multiple drones was more efficient than single-drone exploration in terms of the same parameters. Specifically, compared to single-drone exploration, the collaborative drone search reduced CPU time by a factor of 2.6 and search distance by approximately a factor of 2. In experiments in real-world scenarios, multiple drones equipped with the proposed algorithm successfully detected cubes containing air pollution above the threshold level. The findings serve as an important reference for research on drone-assisted target exploration, including air pollution detection.