Search results

Because of the various advantages of reinforcement learning (RL) mentioned above, this study uses RL to train unmanned aerial vehicles to perform two tasks: target search and cooperative obstacle avoidance.

This study draws inspiration from the recurrent state-space model and recurrent models (RPM) to propose a simpler yet highly effective model called the unmanned aerial vehicles prediction model (UAVPM). The main objective is to assist in training the UAV representation model with a recurrent neural network, using the soft actor-critic algorithm.

This study proposes a generalized actor-critic framework consisting of three modules: representation, policy and value. This architecture serves as the foundation for training UAVPM. This study proposes the UAVPM, which is designed to aid in training the recurrent representation using the transition model, reward recovery model and observation recovery model. Unlike traditional approaches reliant solely on reward signals, RPM incorporates temporal information. In addition, it allows the inclusion of extra knowledge or information from virtual training environments. This study designs UAV target search and UAV cooperative obstacle avoidance tasks. The algorithm outperforms baselines in these two environments.

It is important to note that UAVPM does not play a role in the inference phase. This means that the representation model and policy remain independent of UAVPM. Consequently, this study can introduce additional “cheating” information from virtual training environments to guide the UAV representation without concerns about its real-world existence. By leveraging historical information more effectively, this study enhances UAVs’ decision-making abilities, thus improving the performance of both tasks at hand.

The purpose of this paper is to improve autonomous flight performance of a fixed-wing unmanned aerial vehicle (UAV) via simultaneous morphing wingtip and control system design conducted with optimization, computational fluid dynamics (CFD) and machine learning approaches.

The main wing of the UAV is redesigned with morphing wingtips capable of dihedral angle alteration by means of folding. Aircraft dynamic model is derived as equations depending only on wingtip dihedral angle via Nonlinear Least Squares regression machine learning algorithm. Data for the regression analyses are obtained by numerical (i.e. CFD) and analytical approaches. Simultaneous perturbation stochastic approximation (SPSA) is incorporated into the design process to determine the optimal wingtip dihedral angle and proportional-integral-derivative (PID) coefficients of the control system that maximizes autonomous flight performance. The performance is defined in terms of trajectory tracking quality parameters of rise time, settling time and overshoot. Obtained optimal design parameters are applied in flight simulations to test both longitudinal and lateral reference trajectory tracking.

Longitudinal and lateral autonomous flight performances of the UAV are improved by redesigning the main wing with morphing wingtips and simultaneous estimation of PID coefficients and wingtip dihedral angle with SPSA optimization.

This paper originally discusses the simultaneous design of innovative morphing wingtip and UAV flight control system for autonomous flight performance improvement. The proposed simultaneous design idea is conducted with the SPSA optimization and a machine learning algorithm as a novel approach.

The purpose of this paper is to construct an event-triggered finite-time fault-tolerant formation tracking controller, which can achieve a time-varying formation control for multiple unmanned aerial vehicles (UAVs) during actuator failures and external perturbations.

First, this study developed the formation tracking protocol for each follower using UAV formation members, defining the tracking inaccuracy of the UAV followers’ location. Subsequently, this study designed the multilayer event-triggered controller based on the backstepping method framework within finite time. Then, considering the actuator failures, and added self-adaptive thought for fault-tolerant control within finite time, the event-triggered closed-loop system is subsequently shown to be a finite-time stable system. Furthermore, the Zeno behavior is analyzed to prevent infinite triggering instances within a finite time. Finally, simulations are conducted with external disturbances and actuator failure conditions to demonstrate formation tracking controller performance.

It achieves improved performance in the presence of external disturbances and system failures. Combining limited-time adaptive control and event triggering improves system stability, increase robustness to disturbances and calculation efficiency. In addition, the designed formation tracking controller can effectively control the time-varying formation of the leader and followers to complete the task, and by adding a fixed-time observer, it can effectively compensate for external disturbances and improve formation control accuracy.

A formation-following controller is designed, which can handle both external disturbances and internal actuator failures during formation flight, and the proposed method can be applied to a variety of formation control scenarios and does not rely on a specific type of UAV or communication network.

This paper aims to study the agent learning from expert demonstration data while incorporating reinforcement learning (RL), which enables the agent to break through the limitations of expert demonstration data and reduces the dimensionality of the agent’s exploration space to speed up the training convergence rate.

Firstly, the decay weight function is set in the objective function of the agent’s training to combine both types of methods, and both RL and imitation learning (IL) are considered to guide the agent's behavior when updating the policy. Second, this study designs a coupling utilization method between the demonstration trajectory and the training experience, so that samples from both aspects can be combined during the agent’s learning process, and the utilization rate of the data and the agent’s learning speed can be improved.

The method is superior to other algorithms in terms of convergence speed and decision stability, avoiding training from scratch for reward values, and breaking through the restrictions brought by demonstration data.

The agent can adapt to dynamic scenes through exploration and trial-and-error mechanisms based on the experience of demonstrating trajectories. The demonstration data set used in IL and the experience samples obtained in the process of RL are coupled and used to improve the data utilization efficiency and the generalization ability of the agent.

This paper aims to present numerical simulations for a series of flight processes for the postlaunching stage of the “balloon-borne UAV system.” It includes the balloon further ascent motion after airborne launching. In terms of unmanned aerial vehicles (UAVs), the tailspin state and the charge-out process with an anti-tailspin parachute-assisted suspending are analyzed. Then, the authors conduct trajectory optimization simulations for the long-distance gliding process.

The balloon kinematics model and the parachute Kane multibody dynamic model are established. Using steady-state tailspin to reduced-order analysis and achieving change-out simulation by parachute suspension dynamic model. A reentry optimization control problem is developed and the Radau pseudo-spectral method is used to calculate the glide trajectory.

The established dynamic model and trajectory optimization method can effectively simulate the motion process of balloons and UAVs. The system mass reduction for launching UAVs will not cause damage to the balloon structure. The anti-tailspin parachute can reduce the UAV attack angles effectively. The UAV can glide to the designated target position by adjusting the attack angle and sideslip angle. The farthest flight distance after launching from 20 km height is 94 km and the gliding time is 40 min, which demonstrates the potential application advantage of high-altitude launching.

The research content and related conclusions of this article achieve a closed-loop analysis of the flight mission chain for the “balloon-borne UAV system,” which provides simulation references for relevant balloon launching experiments.

This paper establishes a complete set of numerical simulation models and can effectively analyze various postlaunching behaviors.

Quadrotors have been applied in various fields. However, because the quadrotor is subject to multiple disturbances, consisting of external disturbances, actuator faults and parameter uncertainties, it is difficult to control the unmanned aerial vehicle (UAV) to achieve high-precision tracking performance. This paper aims to design a safety controller that uses observer and neural network method to improve the tracking performance of UAV under multiple disturbances. The experiments prove that this method is effective.

First, to actively estimate and compensate the synthetic uncertainties of the system, a finite-time extended state observer is investigated, and the disturbances are transformed into the extended state of the system for estimation. Second, an adaptive neural network controller that does not accurately require the dynamic model knowledge is designed based on the estimated value, where the weights of the neural network can be dynamically adjusted by the adaptive law. Furthermore, the finite-time bounded convergence of the proposed observer and the stability of the system are proved through homogeneous theory and Lyapunov method.

The figure-“8” climbing flight simulation and real flight experiments illustrate that the proposed safety control strategy has good tracking performance.

This paper proposes the safety control structure of the UAV, which combines the extended state observer with the neural network method. Numerical simulation results and actual flight experiments demonstrate the effectiveness of the proposed control strategy.

Nowadays, food problems are likely to arise because of the increasing global population and decreasing arable land. Therefore, it is necessary to increase the yield of agricultural products. Pesticides can be used to improve agricultural land products. This study aims to make the spraying of cherry trees more effective and efficient with the designed artificial intelligence (AI)-based agricultural unmanned aerial vehicle (UAV).

Two approaches have been adopted for the AI-based detection of cherry trees: In approach 1, YOLOv5, YOLOv7 and YOLOv8 models are trained with 70, 100 and 150 epochs. In Approach 2, a new method is proposed to improve the performance metrics obtained in Approach 1. Gaussian, wavelet transform (WT) and Histogram Equalization (HE) preprocessing techniques were applied to the generated data set in Approach 2. The best-performing models in Approach 1 and Approach 2 were used in the real-time test application with the developed agricultural UAV.

In Approach 1, the best F1 score was 98% in 100 epochs with the YOLOv5s model. In Approach 2, the best F1 score and mAP values were obtained as 98.6% and 98.9% in 150 epochs, with the YOLOv5m model with an improvement of 0.6% in the F1 score. In real-time tests, the AI-based spraying drone system detected and sprayed cherry trees with an accuracy of 66% in Approach 1 and 77% in Approach 2. It was revealed that the use of pesticides could be reduced by 53% and the energy consumption of the spraying system by 47%.

An original data set was created by designing an agricultural drone to detect and spray cherry trees using AI. YOLOv5, YOLOv7 and YOLOv8 models were used to detect and classify cherry trees. The results of the performance metrics of the models are compared. In Approach 2, a method including HE, Gaussian and WT is proposed, and the performance metrics are improved. The effect of the proposed method in a real-time experimental application is thoroughly analyzed.

Drones have become an important element within hospitality and tourism. The purpose of this study is to identify the corpus of knowledge and create a research agenda that establishes appropriate guidelines for future study of drone application in hospitality and tourism.

This work has been undertaken using a mixed-methods approach that combines quantitative and qualitative research and includes a review of the literature related to the study of drone use in hospitality and tourism.

The mixed-methods review identified gaps in the research, potential areas of study to enhance the scientific literature and potential uses of drones in tourism and hospitality for researchers, consumers and industry professionals.

This study makes an original contribution by establishing an integrated framework, which led to a synthesis of the research corpus and provided a holistic conceptualisation of the relationship between tourism and drones. In addition, the research agenda proposed will help boost and consolidate this emerging field of research.

无人机已经成为接待和旅游中的一个重要元素。本研究的主要目的是确定知识库, 并建立一个研究议程, 为未来无人机在酒店和旅游业的应用研究建立适当的指导方针。

这项工作采用了混合方法, 将定量和定性研究结合起来, 包括对与酒店和旅游业中无人机使用研究有关的文献进行回顾。

混合方法审查确定了研究中的差距、加强科学文献的潜在研究领域, 以及研究人员、消费者和行业专业人士在旅游和酒店业的无人机应用潜力。

这项研究通过建立一个综合框架做出了原创性的贡献, 它综合合成了研究语料库, 并对旅游和无人机之间的关系提供了一个整体的概念化。此外, 提出的研究议程将有助于促进和巩固这一新兴的研究领域。

Los drones se han convertido en un elemento importante dentro de la hostelería y el turismo. El objetivo principal de este estudio es identificar el corpus de conocimiento y crear una agenda de investigación que establezca las directrices adecuadas para el estudio futuro de la aplicación de los drones en la hostelería y el turismo.

Este trabajo se ha realizado utilizando un enfoque de métodos mixtos que combina la investigación cuantitativa y cualitativa e incluye una revisión de la literatura relacionada con el estudio del uso de drones en hostelería y turismo.

La revisión de métodos mixtos identificó lagunas en la investigación, áreas potenciales de estudio para mejorar la literatura científica y potencial de las aplicaciones de los drones en el turismo y la hostelería para investigadores, consumidores y profesionales del sector.

Este estudio aporta una contribución original al establecer un marco integrado, que conduce a una síntesis del corpus de investigación y proporciona una conceptualización holística de la relación entre el turismo y los drones. Además, la agenda de investigación propuesta contribuirá a impulsar y consolidar este campo de investigación emergente.

This study presents a systematic literature review (SLR) of the interdisciplinary literature on drones in last-mile delivery (LMD) to extrapolate pertinent insights from and into the logistics management field.

Rooting their analytical categories in the LMD literature, the authors performed a deductive, theory refinement SLR on 307 interdisciplinary journal articles published during 2015–2022 to integrate this emergent phenomenon into the field.

The authors derived the potentials, challenges and solutions of drone deliveries in relation to 12 LMD criteria dispersed across four stakeholder groups: senders, receivers, regulators and societies. Relationships between these criteria were also identified.

This review contributes to logistics management by offering a current, nuanced and multifaceted discussion of drones' potential to improve the LMD process together with the challenges and solutions involved.

The authors provide logistics managers with a holistic roadmap to help them make informed decisions about adopting drones in their delivery systems. Regulators and society members also gain insights into the prospects, requirements and repercussions of drone deliveries.

This is one of the first SLRs on drone applications in LMD from a logistics management perspective.

The purpose of this paper is to provide a detailed insight into the global military robot industry with an emphasis on products and their applications.

Following an introduction which includes a brief historical account, this provides an industry overview, including various market dimensions and a discussion of the geopolitical and technological factors driving market development. The three following sections provide details of land, airborne and marine robots, their capabilities and deployments in recent conflicts. Finally, brief conclusions are drawn.

Military robots which operate on land, in the air and at sea constitute a multi-billion dollar industry which is growing rapidly. It is being driven by geopolitical tensions, notably the military-technology arms race between China and the USA and the conflict in Ukraine, together with technological progress, particularly in AI. Many robots possess multi-functional capabilities, and the leading application is presently intelligence, surveillance and reconnaissance. An increasing number of heavily armed robots are being developed, and AI has the potential to impart these with the capacity to deliver lethal force without human intervention. Although heavily criticised in some quarters, this capability has probably already been deployed on the battlefield. With ever-growing military budgets, escalating political tensions and technological innovations, robots will play an increasingly significant role in future conflicts.

This provides a detail account of military robots and their role in modern warfare.