• Home
  • Search
  • Cost-Effective Autonomous Drone Navigation Using Reinforcement Learning: Simulation and Real-World Validation
  • Cite Icon5
  • https://doi.org/10.3390/app15010179Copy DOI Icon

Cost-Effective Autonomous Drone Navigation Using Reinforcement Learning: Simulation and Real-World Validation

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Artificial intelligence (AI) is used in tasks that usually require human intelligence. The motivation behind this study is the growing interest in deploying AI in public spaces, particularly in autonomous vehicles such as flying drones, to address challenges in navigation and control. The primary challenge lies in developing a robust, cost-effective system capable of autonomous navigation in real-world environments, handling obstacles, and adapting to dynamic conditions. To tackle this, we propose a novel approach integrating machine learning (ML) algorithms, specifically, reinforcement learning (RL), with a comprehensive simulation and testing framework. Reinforcement learning machine algorithms designed to solve problems requiring optimization of the solution for the highest possible reward were used. It was assumed that the algorithms do not have to be created from scratch, but they need a well-defined training environment that will appropriately reward or punish the actions taken. This study aims to develop and implement a novel approach to autonomous drone navigation using machine learning (ML) algorithms. The primary innovation lies in the comprehensive integration of ML algorithms with a real-world drone control system, encompassing both simulations and real-world testing. A vital component of this approach is creating a multi-stage training environment that accurately replicates actual flight conditions and progressively increases the complexity of scenarios, ensuring a robust evaluation of algorithm performance. This research also introduces a new approach to optimizing system cost and accessibility. It involves using commercially available, cost-effective drones and open-source or free simulation tools, significantly reducing entry barriers for potential users. A critical aspect of this study is to assess whether affordable components can provide sufficient accuracy and stability without compromising system quality. The authors developed a system capable of autonomously determining optimal flight paths and controlling the drone, allowing it to avoid obstacles and respond to dynamic conditions in real time. The performance of the trained algorithms was confirmed through simulations and real-world flights, which allowed for assessing their usefulness in practical drone navigation scenarios.

Similar Papers
  • Research Article
  • Citations9

Integrating machine learning algorithms into audit processes: Benefits and challenges

  • Jun 15, 2024
  • Finance & Accounting Research Journal
  • Beatrice Oyinkansola Adelakun +3
  • Research Article
  • Citations4

Fashion Design Classification Based on Machine Learning and Deep Learning Algorithms: A Review

  • Jun 15, 2024
  • Indonesian Journal of Computer Science
  • Ahmed Shushi +1
  • Research Article
  • Citations13

Image-based and ML-driven analysis for assessing blueberry fruit quality.

  • Feb 01, 2025
  • Heliyon
  • Marcelo Rodrigues Barbosa Júnior +5
  • Research Article
  • Citations14

Application of Machine Learning Algorithms to a Well Defined Clinical Problem: Liver Disease

  • Oct 01, 2017
  • International Journal of E-Health and Medical Communications
  • Sakshi Takkar +2
  • Research Article
  • Citations14

Gender Prediction with the Parameters Obtained from Pelvis Computed Tomography Images and Machine Learning Algorithms

  • Jul 01, 2022
  • Journal of the Anatomical Society of India
  • Yusuf Secgin +3
  • Research Article
  • Citations24

Availability of Evidence for Predictive Machine Learning Algorithms in Primary Care

  • Sep 12, 2024
  • JAMA Network Open
  • Margot M Rakers +10
  • Research Article
  • Citations4

The State of Machine Learning in Outcomes Prediction of Transsphenoidal Surgery: A Systematic Review

  • Nov 23, 2022
  • Journal of Neurological Surgery. Part B, Skull Base
  • Darrion B Yang +7
  • PDF
  • Research Article
  • Citations11

Towards Sustainable Energy Systems Considering Unexpected Sports Event Management: Integrating Machine Learning and Optimization Algorithms

  • Apr 26, 2023
  • Sustainability
  • Lei Zhang +1
  • Research Article

FPGA-BASED HARDWARE ACCELERATION OF MACHINE LEARNING ALGORITHM FOR REAL-TIME IMAGE PROCESSING

  • Oct 01, 2023
  • ICTACT Journal on Microelectronics
  • Devanathan B +3
  • Research Article
  • Citations77

Application of machine learning in predicting survival outcomes involving real-world data: a scoping review

  • Nov 13, 2023
  • BMC medical research methodology
  • Yinan Huang +3
  • Conference Article

Effects of Expression Recognition with Machine and Deep Learning Algorithms on Psychotherapy

  • Dec 06, 2025
  • Gulay Cicek +2
  • Book Chapter
  • Citations8

Machine Learning Principles

  • Jan 01, 2020
  • Farhad Balali +3
  • Research Article
  • Citations5

Human vs. machine vs. core lab for the assessment of coronary atherosclerosis with lumen and vessel contour segmentation with intravascular ultrasound.

  • Apr 19, 2022
  • The international journal of cardiovascular imaging
  • Ronald D Bass +16
  • Research Article
  • Citations25

A Two-Stage Machine Learning Algorithm for Retrieving Multiple Aerosol Properties Over Land: Development and Validation

  • Jan 01, 2023
  • IEEE Transactions on Geoscience and Remote Sensing
  • Mengdan Cao +3
  • Research Article
  • Citations4

Effect of High-Intensity Statin Therapy on Atherosclerosis (IBIS-4): Manual Versus Automated Methods of IVUS Analysis

  • Apr 15, 2023
  • Cardiovascular Revascularization Medicine
  • Ronald D Bass +13
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.