# Planning trajectory for UAVs using the self-organizing migrating algorithm

## TL;DR

This paper introduces a new method for UAVs to plan safe and efficient flight paths in complex environments using a swarm intelligence algorithm.

## Contribution

A novel cost function and self-organizing migrating algorithm for real-time UAV trajectory planning in dynamic settings.

## Key findings

- UAVs successfully avoid collisions and reach targets in simulations with multiple obstacles and ten UAVs.
- The proposed method scales to large swarms without centralized control.
- The approach balances target proximity and obstacle avoidance effectively.

## Abstract

Ensuring efficient and safe trajectory planning for UAVs in complex and dynamic environments is a critical challenge, especially for UAVs that are increasingly deployed in applications like environmental monitoring, disaster management, and surveillance. The primary complications in the safe control of UAVs include real-time obstacle avoidance, adaptation to unpredictable environmental changes, and coordination among multiple UAVs to prevent collisions. This paper addresses these challenges by proposing a novel approach for UAV trajectory planning that integrates obstacle avoidance and target acquisition. We introduce a new cost function designed to minimize the distance to the target while maximizing the distance from obstacles, effectively balancing these competing objectives to ensure safety and efficiency. To optimize this cost function, we employ the self-organizing migrating algorithm, a swarm intelligence algorithm inspired by the cooperative and competitive behaviors observed in natural organisms. Our method enables UAVs to autonomously generate safe and efficient paths in real-time, adapt to dynamic changes, and scale to large swarms without relying on centralized control. Simulation results across three scenarios-including a complex environment with ten UAVs and multiple obstacles-demonstrate the effectiveness of our approach. The UAVs successfully reach their targets while avoiding collisions, confirming the reliability and robustness of the proposed method. This work contributes to advancing autonomous UAV operations by providing a scalable and adaptable solution for trajectory planning in challenging environments.