Autonomous Unmanned Aerial Vehicles Research Articles

Reinforcement Learning-Based Security/Safety UAV System for Intrusion Detection Under Dynamic and Uncertain Target Movement

Autonomous security unmanned aerial vehicles (UAVs) have recently gained popularity as an effective solution for accomplishing target/intrusion detection and tracking tasks with little or no human intervention. In this context, we aim at developing an autonomous UAV system for detecting a dynamic and uncertain intrusion within an area, in which the intruder/target moves from one location to another within the area according to an unknown random distribution. The problem of finding an uncertain target while considering the energy causality constraint of the UAV&#x2019;s battery and the uncertainty of the target movement is mathematically formulated as a search benefit maximization problem, which cannot be directly optimized due to the uncertain unknown target movement. Thus, we reformulate the optimization problem as a Markov-decision process that can be solved using reinforcement learning (RL) techniques. Then, we implement an RL-based algorithm to solve the reformulated benefit maximization problem by enabling the UAV to autonomously learn the dynamics of the intruder/target. Specifically, different design variants of the RL-based algorithm are implemented that differ in the used temporal difference methods (i.e., Q-learning or state-action-reward-state-action), and in the exploration algorithms (convergence-based or <formula><tex>$\epsilon$</tex></formula>-greedy). Simulation results show RL algorithms&#x2019; superiority and effectiveness over existing random and circular target detection algorithms.

Challenges and Opportunities for Autonomous UAV Inspection in Solar Photovoltaics

Challenges and Opportunities for Autonomous UAV Inspection in Solar Photovoltaics

Autonomous UAV Visual Navigation Using an Improved Deep Reinforcement Learning

Autonomous UAV Visual Navigation Using an Improved Deep Reinforcement Learning

Coupling an Autonomous UAV With a ML Framework for Sustainable Environmental Monitoring and Remote Sensing

Many countries face problems in monitoring plant problems and monitoring large environments, as until now, there is no accurate means of aerial monitoring through which concerned parties can benefit from watersheds, monitor large agricultural areas, and make wise environmental decisions regarding them. This paper describes a pioneering approach to develop smart agriculture using multimission drones equipped with dual cognitive modules (brains) that are powered by a machine learning (ML) framework. The first brain uses deep reinforcement learning (DRL) principles to enable autonomous flight, allowing drones to navigate complex agricultural terrain with agility and flexibility. The second brain is responsible for precise and crucial agricultural tasks: counting trees, detecting water locations, and observing and analyzing plants using the Faster R‐CNN algorithm. The system is linked with the ground station for control and command, as well as it includes an Internet of Things (IoT) infrastructure equipped with sensors that collect soil parameters, which then get sent via 5G Wi‐Fi. The dual architecture of the drones, combined with the ground‐level IoT system, creates a comprehensive framework that not only enhances agricultural technologies but also aligns with environmental conservation goals, embodying a paradigm shift towards a greener and more sustainable future. Obtained results show reasonable results with an accuracy rate of 98%.

Autonomous UAV Exploration and Mapping in Uncharted Terrain Through Boundary-Driven Strategy

Autonomous UAV Exploration and Mapping in Uncharted Terrain Through Boundary-Driven Strategy

Autonomous UAV Implementation for Facial Recognition and Tracking in GPS-Denied Environments

Autonomous UAV Implementation for Facial Recognition and Tracking in GPS-Denied Environments

A Survey on Sensor- and Communication-Based Issues of Autonomous UAVs

A Survey on Sensor- and Communication-Based Issues of Autonomous UAVs

Paper] Deep Learning based Hierarchical Object Detection System Adopting a Depth Correction Scheme for High-Resolution Aerial Images Towards Realization of Autonomous UAV Flight

Paper] Deep Learning based Hierarchical Object Detection System Adopting a Depth Correction Scheme for High-Resolution Aerial Images Towards Realization of Autonomous UAV Flight

Efficient Autonomous UAV Exploration Framework with Limited FOV Sensors for IoT Applications

Efficient Autonomous UAV Exploration Framework with Limited FOV Sensors for IoT Applications

Design a border Surveillance System based on Autonomous Unmanned Aerial Vehicles (UAV)

Design a border Surveillance System based on Autonomous Unmanned Aerial Vehicles (UAV)

Task offloading and trajectory control techniques in unmanned aerial vehicles with Internet of Things – An exhaustive review

Objectives: This article reviews and provides an exhaustive examination of task offloading and trajectory control techniques in unmanned aerial vehicles (UAVs) integrated with Internet of Things (IoT), highlighting their significance and impact on the UAV ecosystem. The paper begins by introducing the fundamental concepts of UAVs, IoT, and their integration, emphasizing the potential benefits and challenges of this union. Subsequently, it delves into an extensive exploration of task offloading, a critical aspect that optimizes UAV operations by distributing tasks between the UAV and edge/cloud computing resources. Various task offloading strategies, including computation offloading, data offloading, and control offloading, is discussed in detail, elucidating their role in optimizing resource utilization, energy efficiency, and real-time decision-making in UAVs.Methods: The review comprehensively covers trajectory control techniques, which are essential for ensuring UAVs can navigate through dynamic environments safely and efficiently. This study outlines the use of IoT technologies, such as GPS, sensors, and communication networks, to enable precise trajectory planning, obstacle avoidance, and adaptive path adjustments. It also discusses the integration of machine learning and AI algorithms for autonomous UAV navigation, taking into account environmental factors, mission objectives, and real-time data from IoT sources. The paper further discusses the challenges and potential security concerns associated with IoT integration in UAVs, as well as the emerging trends and future prospects of this dynamic field. It emphasizes the need for standardized protocols and robust cybersecurity measures to ensure the reliability and safety of UAV-IoT systems.Findings: This exhaustive review offers a comprehensive understanding of the synergistic relationship between UAVs and IoT, shedding light on the task offloading and trajectory control techniques that empower these autonomous aerial vehicles. By leveraging IoT technologies, UAVs are poised to continue transforming industries and driving innovation in ways previously unimaginable, making this interdisciplinary field an area of great promise and significance.

Deep learning-based anomaly detection for individual drone vehicles performing swarm missions

This study explores methods for the detection and identification of anomalous instances in individual drone vehicles when performing missions in a swarm formation. Conventional anomaly detection (AD) in unmanned aerial vehicle (UAV) clusters typically involves manual inspection, which is time and resource-inefficient, followed by machine learning techniques. In this study, a novel machine-learning-based framework was proposed for the automatic detection of anomalous individual drones within a swarm and the rapid identification of faulty channels. Considering the imbalance between normal and abnormal states when using real flight data, semi-supervised models were selected. Four models with one-dimensional (1D) convolutions were trained on normal data. These models were based on a variational autoencoder and three popular AD-specific models (AnoGAN, GANomaly, and Skip-GANomaly), and their performances considering several metrics were compared. Data preprocessing was performed according to various scaling methods, and the hyperparameters that affect the training process were determined through Bayesian optimization. After training, AD was performed using a two-step process. First, detection through binary classification was performed by generating a reconstruction of the testing data and thresholding the reconstruction error. After detection, if the data were determined to be abnormal, each of the 16 channels was ranked in terms of its probability of being the source of the anomaly. The proposed scheme for detecting anomalies was tested and verified using real-world flight data, and analysis of the results revealed the major types of faults and identified specific abnormal channels. This has implications on future research of implementing necessary responses to abnormal readings to maintain UAV autonomy.

DEVELOPMENT OF CONTROL LAWS OF UNMANNED AERIAL VEHICLES FOR PERFORMING GROUP FLIGHT AT THE STRAIGHT-LINE HORIZONTAL FLIGHT STAGE

The article proposes an improved approach to controlling groups of unmanned aerial vehicles (UAVs) aimed at increasing the overall efficiency and flexibility of the control process. The use of a heterogeneous external field, which varies both in magnitude and direction, allows achieving greater adaptability and accuracy in controlling a group of UAVs. A vector field for unmanned aerial vehicles determines the direction and intensity of the vehicles' movement in space. Such vector fields can be used to develop UAV control laws, including determining optimal flight paths, controlling speed, avoiding obstacles, and ensuring coordination of a group of UAVs. The subject of the study is the methods of controlling groups of autonomous UAVs, where each vehicle may have different speeds and flight directions. To solve this problem, various methods of using a heterogeneous field have been developed and proposed. Instead of using a homogeneous field that provides a constant flight speed, a vector field is used that adapts to different conditions and characteristics of the vehicles in the group. This method allows for effective group management, ensuring the necessary coordination and interaction between the vehicles. An analysis of recent research and publications in the field of autonomous system control indicates the feasibility of using machine learning, vector fields, and a large amount of data to successfully coordinate the movement of autonomous systems. These approaches make it possible to create efficient and reliable control systems. The aim of the study is to develop laws for controlling the movement of a group of autonomous unmanned aerial vehicles at the stage of straight-line horizontal flight based on natural analogues to improve the efficiency and reliability of their coordinated movement in different conditions. The main conclusions of the research are that the proposed method of controlling groups of UAVs based on a heterogeneous field can be implemented. It takes into account a variety of vehicle characteristics and environmental conditions that are typical for real-world use scenarios. This work opens up prospects for further improving the management of UAV groups and their use in various fields of activity. The article emphasises the relevance of technology development for autonomous unmanned systems, especially in the context of autonomous transport systems.

Vision-Based Plane Estimation and Following for Building Inspection With Autonomous UAV

Vision-Based Plane Estimation and Following for Building Inspection With Autonomous UAV

Situational-Command Motion Control of an Autonomous Unmanned Aerial Vehicle Searching for Forest Fires in an Unstable Air Environment

Situational-Command Motion Control of an Autonomous Unmanned Aerial Vehicle Searching for Forest Fires in an Unstable Air Environment

Land Survey and Mapping for Agricultural Purpose using UAV

Unmanned Aerial Vehicles (UAVs) are a group of aerial vehicles that include drones. Agriculture has always been the backbone of India’s sustained growth. Land surveying is the most challenging task in the agricultural field in terms of accuracy and time required for surveying using the traditional method. We have built a fully autonomous UAV and calibrated it for agricultural land survey purposes. The navigation and mapping process, in which a predefined path is provided to the UAV flight controller. During its autonomous flight, the drone's camera captures multiple images. Using a threshold-based segmentation method, the cultivated land and uncultivated land areas are determined using this system. Pre-processing of the images, land area segmentation, and post-processing of the images are carried out. The pre-processed image is divided into several distinct regions by applying a colour thresholding technique, which serves as the foundation for the segmentation of land. The results illustrate that the proposed method outperforms the existing method.

Sliding Mode Controller Applied to Autonomous UAV Operation in Marine Small Cargo Transport

Sliding Mode Controller Applied to Autonomous UAV Operation in Marine Small Cargo Transport

A Review of Using Visual Odometery Methods in Autonomous UAV Navigation in GPS-Denied Environment

Abstract This review paper centers on strategies employed for location determination in regions lacking GPS signals. It primarily explores a range of vision-based methods tailored for this purpose, categorizing them accordingly. The article delves into the utilization of optical flow for feature extraction-based Visual Odometry (VO) and delves into advanced optical flow estimation methods that hinge on deep learning techniques. It compares the efficacy and practical applications of frequently utilized visual localization methods while also checking the efficiency of previous researches by reapplying the algorithms to new data and comparing the results.

Real-time assessment of surface cracks in concrete structures using integrated deep neural networks with autonomous unmanned aerial vehicle

Ensuring the structural integrity of civil infrastructures is critical, given the potential hazards presented by cracks. Traditional manual inspections, though common, often face challenges related to accuracy, accessibility, safety, and cost-effectiveness. To address these issues, this study presents a new approach that integrates unmanned aerial vehicles (UAVs) with advanced computer vision techniques. A key feature of our approach is a system where a self-operating UAV is paired with a carefully crafted deep-learning design. This design takes advantage of both the Fast Region-based Convolutional Neural Network (FRCNN) and Residual Network (ResNet) models, allowing for real-time and accurate crack detection from ongoing video feeds. For uninterrupted real-time processing, our UAV is equipped with a data transmission module, sending live video to a computational platform enhanced with our advanced crack-spotting tool. After thorough training using a diverse dataset of 1000 images, our FRCNN-ResNet model was compared to other top models, achieving a precision rate of 93.3% and a quick 59.7ms inference time. Overall, this study offers a notable improvement in how we monitor civil structures, focusing on better safety and cost savings.

Event-Triggered Hierarchical Planner for Autonomous Navigation in Unknown Environment

End-to-end deep neural network (DNN)-based motion planners have shown great potential in high-speed autonomous UAV flight. Yet, most existing methods only employ a single high-capacity DNN, which typically lacks generalization ability and suffers from high sample complexity. We propose a novel event-triggered hierarchical planner (ETHP), which exploits the bi-level optimization nature of the navigation task to achieve both efficient training and improved optimality. Specifically, we learn a depth-image-based end-to-end motion planner in a hierarchical reinforcement learning framework, where the high-level DNN is a reactive collision avoidance rerouter triggered by the clearance distance, and the low-level DNN is a goal-chaser that generates the heading and velocity references in real time. Our training considers the field-of-view constraint and explores the bi-level structural flexibility to promote the spatio–temporal optimality of planning. Moreover, we design simple yet effective rules to collect hindsight experience replay buffers, yielding more high-quality samples and faster convergence. The experiments show that, compared with a single-DNN baseline planner, ETHP significantly improves the success rate and generalizes better to the unseen environment.