Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Genetic Algorithm Based System for Path Planning with Unmanned Aerial Vehicles Swarms in Cell-Grid Environments

Alejandro Puente-Castro, Enrique Fernandez-Blanco, Daniel Rivero

TL;DR

This work addresses UAV swarm path planning in obstacle-filled, grid-based environments by introducing a genetic algorithm–based system that synchronizes multi-UAV movements through Epochs. The Movement Map encoding, along with a fitness function that rewards complete map coverage and penalizes unvisited cells, enables scalable planning across six maps with 1–4 UAVs. Results show the GA approach often outperforms reinforcement-learning baselines, achieving full coverage with fewer epochs and lower variance, and maintaining low training times on CPU hardware. The study demonstrates robust coverage efficiency, highlighting the method's applicability to surveillance, mapping, and search-and-rescue tasks, while outlining concrete avenues for extending revisit behavior and asynchronous coordination in future work.

Abstract

Path Planning methods for autonomously controlling swarms of unmanned aerial vehicles (UAVs) are gaining momentum due to their operational advantages. An increasing number of scenarios now require autonomous control of multiple UAVs, as autonomous operation can significantly reduce labor costs. Additionally, obtaining optimal flight paths can lower energy consumption, thereby extending battery life for other critical operations. Many of these scenarios, however, involve obstacles such as power lines and trees, which complicate Path Planning. This paper presents an evolutionary computation-based system employing genetic algorithms to address this problem in environments with obstacles. The proposed approach aims to ensure complete coverage of areas with fixed obstacles, such as in field exploration tasks, while minimizing flight time regardless of map size or the number of UAVs in the swarm. No specific goal points or prior information beyond the provided map is required. The experiments conducted in this study used five maps of varying sizes and obstacle densities, as well as a control map without obstacles, with different numbers of UAVs. The results demonstrate that this method can determine optimal paths for all UAVs during full map traversal, thus minimizing resource consumption. A comparative analysis with other state-of-the-art approach is presented to highlight the advantages and potential limitations of the proposed method.

Genetic Algorithm Based System for Path Planning with Unmanned Aerial Vehicles Swarms in Cell-Grid Environments

TL;DR

This work addresses UAV swarm path planning in obstacle-filled, grid-based environments by introducing a genetic algorithm–based system that synchronizes multi-UAV movements through Epochs. The Movement Map encoding, along with a fitness function that rewards complete map coverage and penalizes unvisited cells, enables scalable planning across six maps with 1–4 UAVs. Results show the GA approach often outperforms reinforcement-learning baselines, achieving full coverage with fewer epochs and lower variance, and maintaining low training times on CPU hardware. The study demonstrates robust coverage efficiency, highlighting the method's applicability to surveillance, mapping, and search-and-rescue tasks, while outlining concrete avenues for extending revisit behavior and asynchronous coordination in future work.

Abstract

Path Planning methods for autonomously controlling swarms of unmanned aerial vehicles (UAVs) are gaining momentum due to their operational advantages. An increasing number of scenarios now require autonomous control of multiple UAVs, as autonomous operation can significantly reduce labor costs. Additionally, obtaining optimal flight paths can lower energy consumption, thereby extending battery life for other critical operations. Many of these scenarios, however, involve obstacles such as power lines and trees, which complicate Path Planning. This paper presents an evolutionary computation-based system employing genetic algorithms to address this problem in environments with obstacles. The proposed approach aims to ensure complete coverage of areas with fixed obstacles, such as in field exploration tasks, while minimizing flight time regardless of map size or the number of UAVs in the swarm. No specific goal points or prior information beyond the provided map is required. The experiments conducted in this study used five maps of varying sizes and obstacle densities, as well as a control map without obstacles, with different numbers of UAVs. The results demonstrate that this method can determine optimal paths for all UAVs during full map traversal, thus minimizing resource consumption. A comparative analysis with other state-of-the-art approach is presented to highlight the advantages and potential limitations of the proposed method.

Paper Structure

This paper contains 11 sections, 2 equations, 2 figures, 13 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Background
  3. Materials and Method
  4. Problem Formulation
  5. Genetic Algorithms
  6. Maps
  7. Model
  8. Limitations
  9. Results
  10. Conclusions
  11. Future Work

Figures (2)

  • Figure 1: The flight environment maps. Black cells represent obstacles, while white cells indicate areas that UAVs in the swarm must cover. The diversity in map designs allows testing under varying complexity levels.
  • Figure 2: Paths obtained for each UAV on map 6. Paths are shown differentiated for each UAV for easier visualization. In fact, these paths are executed simultaneously..