Autonomous Flight Research Articles

A Survey of Offline- and Online-Learning-Based Algorithms for Multirotor Uavs

Multirotor UAVs are used for a wide spectrum of civilian and public domain applications. Their navigation controllers include onboard sensor suites that facilitate safe, autonomous or semi-autonomous multirotor flight, operation, and functionality under nominal and detrimental conditions and external disturbances, even when flying in uncertain and dynamically changing environments. During the last decade, given the available computational power, different learning-based algorithms have been derived, implemented, and tested to navigate and control, among other systems, multirotor UAVs. Learning algorithms have been and are used to derive data-driven based models, to identify parameters, to track objects, to develop navigation controllers, and to learn the environments in which multirotors operate. Learning algorithms combined with model-based control techniques have proven beneficial when applied to multirotors. This survey summarizes the research published since 2015, dividing algorithms, techniques, and methodologies into offline and online learning categories and then further classifying them into machine learning, deep learning, and reinforcement learning sub-categories. An integral part and focus of this survey is on online learning algorithms as applied to multirotors, with the aim to register the type of learning techniques that are either hard or almost hard real-time implementable, as well as to understand what information is learned, why, how, and how fast. The outcome of the survey offers a clear understanding of the recent state of the art and of the type and kind of learning-based algorithms that may be implemented, tested, and executed in real time.

Cable-driven legged landing gear for unmanned helicopter: Prototype design, optimization and performance assessment

Cable-driven legged landing gear for unmanned helicopter: Prototype design, optimization and performance assessment

Deep learning reduces sensor requirements for gust rejection on a small uncrewed aerial vehicle morphing wing

Uncrewed aerial vehicles are integral to a smart city framework, but the dynamic environments above and within urban settings are dangerous for autonomous flight. Wind gusts caused by the uneven landscape jeopardize safe and effective aircraft operation. Birds rapidly reject gusts by changing their wing shape, but current gust alleviation methods for aircraft still use discrete control surfaces. Additionally, modern gust alleviation controllers challenge small uncrewed aerial vehicle power constraints by relying on extensive sensing networks and computationally expensive modeling. Here we show end-to-end deep reinforcement learning forgoing state inference to efficiently alleviate gusts on a smart material camber-morphing wing. In a series of wind tunnel gust experiments at the University of Michigan, trained controllers reduced gust impact by 84% from on-board pressure signals. Notably, gust alleviation using signals from only three pressure taps was statistically indistinguishable from using six pressure tap signals. By efficiently rejecting environmental perturbations, reduced-sensor fly-by-feel controllers open the door to small uncrewed aerial vehicle missions in cities.

Design methodology and simulation analysis of hybrid fuel cell and battery systems for powering unmanned aircraft systems

Hybrid fuel cell and battery systems are currently among the most promising options for increasing the flight autonomy of unmanned aircraft systems. The ratio between the size of the battery and the fuel cell is a delicate issue in power system design. Both devices are necessary; the battery, with a quick response, to respond to demand peaks, and the fuel cell, with a slow dynamic response, but greater energy density, to increase its autonomy. One of the most important tasks in designing the hybrid system is selecting the appropriate size of each component so that it can respond to peak demands, extend its autonomy as far as possible and reduce its weight.The purpose of this research was to establish a design procedure for hybrid power systems for unmanned aerial systems, which means selecting the best size for each component. The hybrid system's modeling and the dynamic simulation of its response to demand curves are the foundation of this procedure. The simulation results include the consumption of the fuel cell as a function of time, the battery’s charge status and an estimate of its autonomy for each demand curve. The analysis of the simulation results guides the choice of component size, adapting each one to achieve minimum fuel consumption for the characteristic demand curves for which the unmanned aircraft system is designed. After modeling the components of the hybrid system and describing the simulation procedure, this contribution proposes an example of a design for an unmanned aircraft system with a maximum takeoff weight of 20 kg. In this case, the most appropriate size for the fuel cell was 2000 W and a 3000 mAh 10S Lithium-Polymer battery. Fitted with a 12-liter hydrogen tank, stored at a maximum pressure of 300 bar, an estimated autonomy of 1.5 h can be expected.

Uncrewed aerial vehicle with onboard winch system for rapid, cost-effective, and safe oceanographic profiling in hazardous and inaccessible areas

Interactions between coastal waters and marine-terminating glaciers in the Polar Regions play a significant role in global sea level rise fueled by a rapidly warming Arctic.The risk of glacier calving, and the abundance of ice, can make it impossible for surface vessels to access the waters near glacier termini. Alternative methods using manned aircraft are expensive. As a result, oceanographic measurements are limited near glacier termini.We present an uncrewed aerial vehicle (UAV) with an on-board winch system that allows oceanographic profiling in remote, hazardous areas using a commercial conductivity, temperature, and depth (CTD) sensor payload. The UAV is optimized for easy handling and deployment and is capable of high-speed and efficient cruise flight. An autopilot system provides pilot assistance and autonomous flight capabilities. The total weight of the UAV including payload is 6.5 kg with an endurance of 24 min.Testing of the system was conducted in South Greenland during winter conditions in March 2023 with successful profiles collected near a glacier terminus (<5 m) and in small openings in ice mélange (2.2 m). The system proved capable, reliable, and efficient. Further development of the system will allow other sensors for an even more flexible measurement suite.

Evaluation of the use of polylactic acid in 3d printing for the construction of an unmanned aerial vehicle in the department of cordoba

The use of polylactic acid (PLA) in the technology of fused deposition modeling (FDM), better known as 3D printing, to create all kinds of parts, from prototypes and simple pieces to highly technical end products, is a significant contender due to its wide range of properties compared to other petrochemical-based composite materials. The aim of this study was to evaluate the use of polylactic acid (PLA) for the construction of unmanned aerial vehicles (UAVs) through 3D printing. Power and force calculations for the UAV were performed, and a structural analysis using SolidWorks software was conducted to calculate maximum and minimum stresses and determine optimal manufacturing parameters. Additionally, an aerodynamic analysis using ANSYS software was carried out to determine the drag coefficient and the forces acting on the UAV. It was found that the force exerted by the motors on the arms is 13,63 N, and the power is 536 N. In the structural analysis, it was determined that the minimum stresses are located in the chassis arms, while the maximum stresses are found where the chassis is attached, with a value of 6,604 MPa and a safety factor of 3,23. In the aerodynamic analysis, a drag force of 1 N and a flight power of 108,44 N were calculated. The UAV achieved a flight height of 48 m and a flight autonomy of 17 minutes, concluding that 3D printing technology is a viable and cost-effective alternative.

Autonomous flight strategy of an unmanned aerial vehicle with multimodal information for autonomous inspection of overhead transmission facilities

AbstractThis study proposes an innovative method for achieving autonomous flight to inspect overhead transmission facilities. The proposed method not only integrates multimodal information from novel sensors but also addresses three essential aspects to overcome the existing limitations in autonomous flights of an unmanned aerial vehicle (UAV). First, a novel deep neural network architecture titled the rotational bounding box with a multi‐level feature pyramid transformer is introduced for accurate object detection. Second, a safe autonomous method for the transmission tower approach is proposed by using multimodal information from an optical camera and 3D light detection and ranging. Third, a simple yet accurate control strategy is proposed for tracking transmission lines without necessitating gimbal control because it keeps the UAV's altitude in sync with that of the transmission lines. Systematic analyses conducted in both virtual and real‐world environments confirm the effectiveness of the proposed method. The proposed method not only enhances the performance of autonomous flight but also provides a safe operating platform for inspection personnel.

Advancements in UAV image semantic segmentation: A comprehensive literature review

Unmanned Aerial Vehicles (UAVs) have revolutionized data acquisition across various domains, presenting immense potential for image processing and semantic segmentation. This literature review encompasses a thorough exploration of advancements, techniques, challenges, and datasets pertaining to UAV image semantic segmentation. It begins by introducing the fundamental concepts of UAVs, highlighting their pivotal role in capturing high-resolution imagery that serves diverse applications. The integration of deep learning algorithms with UAVs is emphasized, unlocking new horizons in autonomous flight, security, and environmental monitoring. Delving into the core principles of semantic segmentation, the review elucidates the critical task of classifying every pixel in an image. Convolutional Neural Networks (CNNs) are presented as the cornerstone technology, tracing their evolution from traditional CNNs to the highly adaptable Fully Convolutional Networks (FCNs). A substantial portion of the review is dedicated to FCNs, underscoring their ability to process images of varying dimensions while maintaining spatial coherence in the output. Their pivotal role in semantic segmentation, encompassing both classification and localization, is articulated. The subsequent sections delve into a comprehensive survey of state-of-the-art models, including SegNet, PSPNet, DeepLabNet, EfficientNet, DenseNet-C, and LinkNet. Each model's unique strengths and applications contribute to the evolving landscape of semantic segmentation tasks. The versatility of the U-Net architecture takes center stage in the latter parts of the review. Its fundamental structure is elucidated, followed by a comprehensive examination of its manifold adaptations—3D-U-Net, ResU-Net, U-Net++, Adversarial U-Net, Cascaded U-Net, and Improved U-Net 3+. These modifications address intrinsic challenges such as limited receptive fields and class imbalances, propelling U-Net to the forefront of image segmentation techniques. The subsequent sections pivot toward the application of U-Net in UAV image segmentation, illustrating its efficacy in diverse tasks, including land cover and crop classification. Nevertheless, persisting challenges, such as the scarcity of annotated datasets and the need for model generalization across varied environmental conditions, remain key areas of concern. The review culminates by underlining the significance of large, authentic datasets and data augmentation techniques. Furthermore, a brief exploration of publicly available UAV image datasets is presented, enhancing our understanding of the resources accessible for training and evaluating models. This comprehensive literature review encapsulates the dynamism of UAV image processing and semantic segmentation, illuminating recent developments and avenues for future research in this burgeoning field.

ERROR ANALYSIS OF VISUAL ODOMETRY FOR A SMALL SIZE UNMANNED AERIAL VEHICLE

Abstract. Usage of small size Unmanned Aerial Vehicle (UAV) with autonomous flight capability became widespread at both civil and military applications because of its low costs and ease of use. However, inertial or GPS based positioning and orientation sensors can be disabled at battlefields and the UAV losses its path in a short time. Visual odometry becomes a solution for the aforementioned hassle. Real-time detection of ground control points, matching the same control points at the stereo pair images and correcting the position and orientation data with least square adjustment are the challenges of visual odometry. In this study, error analysis of position and orientation of a UAV flying through mountainous region which cannot obtain any augmenting data for position and orientation is conducted by error propagation law. The flight of UAV is simulated with exact initial position and orientation data. Optic images of ground obtained by nadir directed camera are georeferenced using the digital elevation model of the region, interior and exterior camera parameters. The digital elevation model is used to correct the relief displacement. The stereo-pair image is obtained when the UAV flies 200 m and image coordinates of the common control points are detected by colinearity equations. Position and orientation of UAV is corrected by least square adjustment and the process is repeated for each obtained image acquired at 200 m interval. The analysis revealed that the precisions of horizontal and vertical positioning becomes 75 and 200 meter, respectively. The precision of roll angle becomes worse than 0.5 degree, while the precisions of pitch and yaw angle are estimate to be better that 0.1 degree.

A precise localization algorithm for unmanned aerial vehicles integrating visual-internal odometry and cartographer

Accurate positioning in space is an important foundation for ensuring the stability of autonomous flight and successful mapping and navigation of unmanned aerial vehicles (UAVs). At present, the SLAM algorithm based on the Cartographer algorithm for real-time positioning and mapping is widely used in fields such as robot navigation and autonomous driving. However, in the context of UAV applications, this algorithm has a high dependence on the amount of point cloud information in the surrounding environment, and cannot achieve precise positioning in open spaces with insufficient lighting and fewer feature points, resulting in significant mapping errors. In order to solve the problem of low positioning estimation accuracy in the Cartographer algorithm in above environment, this paper proposes a precise positioning algorithm for UAVs that integrates VIO and Cartographer. This algorithm can continuously output more accurate position estimation information during UAV flight, compensating for the problem of inaccurate position estimation caused by partial feature loss or coordinate system drift in point clouds. In addition, this algorithm ensures navigation obstacle avoidance in narrow spaces by improving positioning accuracy and mapping accuracy, making it more applicable in the field of UAVs. Finally, the effectiveness of the proposed positioning algorithm was verified through experimental analysis of the Cartographer dataset and practical testing of UAVs in real scenarios.

Vee-Tail Preliminary Design Methodology for Class I mini- UAV

Unmanned Air Vehicles (UAVs) are becoming increasingly popular and widely used in a variety of industries. They can be used for tasks such as agriculture, construction, delivery, surveillance, rescue operations, mapping, wildlife tracking and many more. With the advancements in technology, UAVs are becoming more autonomous and able to perform tasks with minimal human intervention, so are widely used for military and law enforcement purposes. V-tail configurations are commonly used on UAVs due to their advantages in control and stability performance, as well as their ability to reduce drag and improve overall efficiency. However, research on V-tail design and sizing is limited, particularly for Class I mini-UAVs. The objective of this paper is to identify a methodology for a V-tail sizing of a Class I Mini UAV (NATO classification), which refers to the Conceptual and Preliminary Design of the UAV. The methodology will follow the design of a V-tail from the characteristics of the conventional tail of the UAV. Once the characteristics of the conventional tail were extracted, V-tail geometric characteristics (reference area, aspect ratio, mean aerodynamic chord, tail span, dihedral angle), were computed. Therefore, the aerodynamic characteristics of the V-tail have to be extracted, first as an isolated tail, and then as an installed tail. The stability derivatives of the V-tail are then calculated. The methodology for the analytical aerodynamic characteristics and stability derivatives, is a combination of NACA Report No.823 and Marcello R. Napolitano methodologies. Paul E. Purser and John P. Campbell provide design methods for V-tail on a NACA report, which include some of the desired stability derivatives. The rest of them will be calculated with Napolitano’s method. Marcello R. Napolitano gives a methodology for conventional tail sizing; thus, the equations of its methodology have to convert for a V-tail configuration. Furthermore, the aerodynamic characteristics and stability derivatives of the designed V-tail will be verified by Low Fidelity Aerodynamics simulation (XFLR5 software), and then by High Fidelity Aerodynamics by means of CFD. The results between low fidelity analytical values and High-Fidelity Aerodynamics values indicate a relative error lower than 20%.

FTDO-based adaptive fuzzy fixed-time tracking control for uncertain unmanned helicopter with output constraints

During the actual flight of unmanned helicopters, there are widespread output constraints, system uncertainties and external disturbances, which bring significant threats to their safe flight. To keep the output constraints from violating predefined boundaries, the barrier Lyapunov function (BLF) is utilized in this paper. The system uncertainties are estimated by the fuzzy logic system (FLS). The compound disturbances composed of the external disturbances and the approximation errors caused by FLS are approximated by the fixed-time disturbance observers (FTDOs). According to the analysis of FTDOs and fixed-time stability theory, the observer errors and state errors converge to a region of the origin in fixed-time, and the appropriate parameters of FTDOs and controller are designed to ensure that the disturbance convergence time is faster than the one of the proposed controller, which further improves the stability of the system. Moreover, the convergence time of the FTDOs FTDOs and the proposed approach only depends on the design parameters under any initial conditions with constrained outputs. The performance of the proposed control approach is verified through the simulation results.

Study of on-board equipment of modern uavs

This paper analyzes the development and production of modern unmanned aerial vehicles (UAVs). It is noted that they have the following main systems: glider; propulsion system; power supply system; management system; navigation system; telemetry system; radio communication system. All UAV systems are interconnected and work as one complex mechanism. Depending on the list of combat tasks to be solved, the following devices can be additionally installed on board the UAV: optical-electronic, thermal imaging, radar, radiotechnical, radiation, chemical, bacteriological and other types of reconnaissance systems with small intelligence storage systems; means of setting active radio-electronic jammers; means of aiming and adjusting guided weapons; various means of defeat; means of control and communication with the ground control point; responsible for the state identification system; autonomous flight and automatic landing devices. The work reveals the features of the UAV engine design, it is noted that 4, 6 or more engines are installed on modern helicopter-type UAVs, so-called "multicopters", "quadracopters", "drones". In this work, it is noted that the UAV navigation equipment can have various level of complexity and use several signals coming from sensors of different physical origins to calculate its location. The features of the UAV radio communication system are revealed, which is a set of various lines through which intelligence information of various levels of importance and protection is transmitted. All communication links can use different frequency bands and different relay modes, use different signal-code designs, specially adapted to the importance of the intelligence information being transmitted. It was noted that in the absence of a control command, the UAV goes into autonomous flight mode.

A Method for Modeling and Testing Near-Real-Time System Scenarios

Unmanned platforms are becoming more and more widely used in both civilian and military applications. The flight safety of such aircraft is crucial. Therefore, it becomes necessary to formally model and rigorously test their software. Commencement of an unmanned air vehicle’s (UAV) operation requires it undergoing a certification process, which further heightens the quality requirements. The validation process of the designed system is presented on the example of verifying the correctness of the operational scenario involving the transfer of control over a UAV between two ground control stations (GCSs). The paper introduces the method of designing unmanned aerial vehicles and testing their functionality based on finite-state machines. The architecture description of the system encompasses the use cases view and logical view of the 1+5 architectural views model. The paper concentrates on system requirements and their transformation into unified modeling language (UML) state machine diagrams. The authors present a method of mapping requirements to functions related to flight safety and system dynamics models expressed as communicating extended finite-state machines (CEFSMs). Moreover, the paper shows the rules for testing the correctness of state machine models using methods based on determining flows in directed graphs. It should be emphasized that the paper considers the certification of UAV software components from the system safety viewpoint, which directly affects the airworthiness of the air platform.

Time-varying gain extended state observer-based adaptive optimal control for disturbed unmanned helicopter

In this paper, the robust adaptive optimal tracking control problem is addressed for the disturbed unmanned helicopter based on the time-varying gain extended state observer (TVGESO) and adaptive dynamic programming (ADP) methods. Firstly, a novel TVGESO is developed to tackle the unknown disturbance, which can overcome the drawback of initial peaking phenomenon in the traditional linear ESO method. Meanwhile, compared with the nonlinear ESO, the proposed TVGESO possesses easier and rigorous stability analysis process. Subsequently, the optimal tracking control issue for the original unmanned helicopter system is transformed into an optimization stabilization problem. By means of the ADP and neural network techniques, the feedforward controller and optimal feedback controller are skillfully designed. Compared with the conventional backstepping approach, the designed anti-disturbance optimal controller can make the unmanned helicopter accomplish the tracking task with less energy. Finally, simulation comparisons demonstrate the validity of the developed control scheme.

Control and Position Tracking for UAVs

There has been exponential development of UAV technology and related research areas such as artificial intelligence, which will raise UAVs’ ability for autonomous flights to a higher level [...]

Historical and Current Landscapes of Autonomous Quadrotor Control: An Early-Career Researchers’ Guide

The rising demand for autonomous quadrotor flights across diverse applications has led to the introduction of novel control strategies, resulting in several comparative analyses and comprehensive reviews. However, existing reviews lack a comparative analysis of experimental results from published papers, resulting in verbosity. Additionally, publications featuring comparative studies often demonstrate biased comparisons by either selecting suboptimal methodologies or fine-tuning their own methods to gain an advantageous position. This review analyzes the experimental results of leading publications to identify current trends and gaps in quadrotor tracking control research. Furthermore, the analysis, accomplished through historical insights, data-driven analyses, and performance-based comparisons of published studies, distinguishes itself by objectively identifying leading controllers that have achieved outstanding performance and actual deployment across diverse applications. Crafted with the aim of assisting early-career researchers and students in gaining a comprehensive understanding, the review’s ultimate goal is to empower them to make meaningful contributions toward advancing quadrotor control technology. Lastly, this study identifies three gaps in result presentation, impeding effective comparison and decelerating progress. Currently, advanced control methodologies empower quadrotors to achieve a remarkable flight precision of 1 cm and attain flight speeds of up to 30 m/s.

Unmanned air/ground vehicle survey following a radiological dispersal event

AbstractThis paper presents the method and results of surveying a dispersed radioactive field using an unmanned air vehicle (UAV) and an unmanned ground vehicle (UGV). A 35 GBq of La material was distributed in a specific geometric l‐polygon pattern measuring a 120 m 20 m longitudinal rectangle and an 80 m 10 m transverse rectangle. Two methods were used to determine the amount and distribution of the lanthanum over the polygon including 20 plywood coupons distributed over the area and a UGV equipped with a Kromek GR1® driving over the area. The aerial survey was conducted using an unmanned aerial vehicle UAV carrying the Kromek GR1® while flying a traditional grid pattern and circular pattern at different elevations and speeds over the area. The data collected by the UAV were further postprocessed using N‐Visage, a 3D radiation modeling method developed by Createc, to create a model of the ground activity. This model was compared with the reference data collected on the ground by the UGV and was found to be in agreement with 11%.

Development of a 2g butterfly-style flapping-wing micro aerial vehicle

A flapping-wing micro aerial vehicle (FMAV) modeled after a butterfly was developed to realize a palm-sized micro aerial vehicle capable of autonomous flight. It has a wingspan of about 220 mm, a weight of 1.8 g with the drive motor and battery installed, and flaps at a frequency of 7 Hz. The results of flight motion analysis using a high-speed camera showed that this butterfly-style FMAV, which does not rely on an external power source and does not have a tail wing, can fly in a straight line while maintaining a constant altitude with an initial speed given. We were also able to observe the flight trajectory of it, which moved up and down with a flapping motion similar to that of a real butterfly. The development of an FMAV that can fly like an insect is important for the viewpoint of robotics to elucidate the posture control mechanism of insects, which still needs to be clarified. The autonomous flight of this butterfly-style FMAV is significant in this regard.

Rapid trajectory generation for quadrotor with limited motor speed

Planning a safe and dynamic flyable trajectory for unmanned aerial vehicle (UAV) is the precondition for autonomous flight. Considering environmental complexity and flight safety under limited motor speed, we proposed a new time-segmented trajectory planning method, which can ensure motor speed within the allowable range and achieve safe flight. Firstly, the candidate trajectory for quadrotor UAV is expressed by high-order polynomials. Herein, polynomial is used as the expression of trajectory, and nonlinear programming (NLP) is used to calculate polynomial coefficient. Then, two strategies and an initial value calculation method are proposed to improve the efficiency of NLP. Furthermore, aiming at the problem that the initial trajectory of UAV motor cannot meet the current speed limit constraint after the motor speed drops, an adjustment strategy based on feasible trajectory is designed. The method presented in this paper not only enhances flexibility of the flight process, improves solving efficiency of the algorithm but also enables UAV to continue flying when the motor speed is limited. Finally, simulation analysis and comparison illustrate the effectiveness and superiority of the proposed method.