Problem Of Unmanned Aerial Vehicles Research Articles

Mathematical Optimization in Innovation Productivity: A Framework and A Case Study on UAV Border Patrolling in Türkiye

Purpose: In this paper, the potential of mathematical optimization (MO) in enhancing innovation productivity is explored. Innovation is a process that converts new ideas and methods into products and services, MO can contribute to innovation management by improving productivity across all stages, from pre-innovation to post-innovation. This paper establishes a connection between MO and innovation productivity while demonstrating an application for a post-innovation phase problem of unmanned aerial vehicles (UAVs). Methodology: A framework for incorporating MO into the design problems of innovation processes is developed. Additionally, a MO model is developed for a case study concerning UAV border patrolling in Türkiye. Findings: Computational experiments demonstrate MO's effectiveness in optimizing UAV routes and strategies, enhancing operational efficiency, and innovation productivity. Optimal recommendations and trade-offs among different mission considerations are obtained in 18 minutes on average (with a median of 5 seconds) over 210 runs. Originality: A link is established between MO and innovation productivity. An operations research problem is introduced for UAV operations in border patrolling in Türkiye. The codebase and data are openly provided for readers to apply the model in their research.

Generative adversarial network based resource optimization for UAV jamming assisted cognitive covert communication

This paper discusses a resource optimization problem for unmanned aerial vehicle (UAV) jamming assisted cognitive covert communication. Specially, the secondary users adopt underlay strategy for spectrum access and the UAV transmits the noise signal to confuse the underlay detection of eavesdropper. According to the dynamic game characteristics in the covert communication process, a new generative adversarial network-based covert communication resource optimization algorithm (GAN-RO) is proposed for the joint optimization of UAV’s trajectory and power in cognitive covert communication assisted by UAV’s interference. The generator simulates the legitimate user to generate the resource allocation scheme, while the discriminator imitates the eavesdropper to detect covert communication. The dynamic game process between the generator and discriminator can obtain covert communication schemes by achieving Nash equilibrium. Simulation results indicate that the proposed GAN-RO algorithm can obtain a near-optimal resource optimization scheme with a rapid converge speed for non-ideal UAV jamming assisted cognitive covert communication system.

Disturbance rejection based on discrete-time adaptive preview control for unmanned aerial vehicle shipboard landing under structure damage

This article studies the shipboard landing control problem for unmanned aerial vehicle with external disturbance and structure damage. A novel discrete-time adaptive preview architecture is presented, where the model reference adaptive control is improved by introducing the preview control method, so that both the uncertainties (caused by the airwake and structure damage) and the control lag could be well compensated simultaneously. The proposed scheme guarantees a more rapid, accurate, and robust performance. For application, the reference input signal is generated by fusing the deck motion prediction information and glide path command. The effectiveness of the algorithm is validated by a longitudinal landing simulation.

Dynamic output feedback control for UAVs with limited network bandwidth: A GA-assisted design approach

This paper studies the dynamic output feedback (OF) control problem for unmanned aerial vehicles (UAVs) with limited network bandwidth by a genetic-algorithm-assisted design approach. In order to make full use of the limited network bandwidth, only partial measurement information is transmitted to the controller via the sensor-to-controller network. Round-Robin protocol is introduced to administrate the transmission rule. Sufficient conditions are presented to make sure that the closed-loop UAV system is exponentially stable with the required L2-gain performance. However, due to the nonlinear coupling terms of the dynamic OF controller parameters and some redundant variables in the system modeling, the established conditions are non-convex and difficult to be solved. Fortunately, genetic algorithms (GA) show good performance in solving optimization problem with nonlinear and non-convex constraints. Therefore, this paper skillfully combines GA with linear matrix inequality techniques to solve the established conditions. Finally, all the dynamic OF controller parameters and the minimal L2-gain can be obtained simultaneously. At the end of this paper, an UAV networked control example and a numerical example are performed to verify the effectiveness and superiorities of our method.

Collision avoidance in target encirclement and tracking of unmanned aerial vehicles under a dynamic event-triggered formation control

This paper addresses the dynamic event-triggered fixed-time distributed control problem of unmanned aerial vehicle (UAV) formation for target encirclement and tracking with collision avoidance. A fixed-time radial basis function (RBF) neural network (NN) adaptive disturbance observer is designed for faster estimation and compensation of the lumped disturbances from the UAV formation system. By extending the lemmas of interconnected systems and fixed-time, a novel fixed-time interconnected system lemma is proposed. Then, a dynamic event-triggered control algorithm is proposed to establish the stability of the complex closed-loop interconnected system for target encirclement and formation tracking in fixed time and to demonstrate that the convergence time of the system is independent of the initial state. Subsequently, a risk avoidance mechanism is incorporated into the event-triggered fixed-time control framework to avoid collisions within the UAV formation. The proposed control strategy has been rigorously mathematically demonstrated. Finally, using a visual simulation platform, several simulations are presented to illustrate the remarkable performance and superiority of the proposed control method.

Credible Gaussian sum cubature Kalman filter based on non-Gaussian characteristic analysis

Toward the pose estimation problem of unmanned aerial vehicles (UAVs) flight over water, a credible Gaussian-sum cubature Kalman filter (CGSCKF) based on non-Gaussian characteristic analysis for nonlinear non-Gaussian system is proposed. In the framework of the proposed scheme, a data characteristic analysis based on multi-peak distribution degree, skewness and kurtosis is applied to evaluate the non-Gaussian intensity of noise, and a Gaussian mixture reduction (GMR) method based on the improved monarch butterfly optimization (IMBO) is proposed to improve the filtering accuracy in the case of weak non-Gaussian noise (Gaussian-like noise). In addition, considering the problem of inconsistency between the practical and the theoretic system model, the process noise and measurement noise are estimated online, and the credibility of filtering result, which is obtained by Gaussian-sum cubature Kalman filter (GSCKF), is measured by comparing the filtering error covariance with the true error covariance. Some comparison simulations and experiments with classical algorithms are provided, justifying that the proposed scheme has better performance in the pose estimation of UAV.

Pursuit Problem of Unmanned Aerial Vehicles

The study examines scenarios involving a single pursuer tracking a single evader, as well as situations where multiple pursuers are involved in chasing multiple evaders. We formulate this problem as a search and pursuit problem for unmanned aerial vehicles (UAVs). Game theory offers a mathematical framework to model and examine strategic interactions involving multiple decision-makers. By employing game theory principles to address the search and pursuit problem, our objective is to optimize the efficiency of strategies for detecting and capturing unmanned aerial vehicles (UAVs).

Analysis of UAV path planning effectiveness and evaluation index scores combined with urban logistics scenarios

Using logistics drones for distribution is an optional solution to the problems of saturated logistics industry, insufficient transportation capacity, and high work pressure on employees in real cities. In a realistic urban environment, it is of practical significance to establish a logistics drone path planning model to improve the efficiency of logistics drones by fully considering the multiple requirements of both logistics service parties, such as time and location, and aiming at minimizing transportation costs. Aiming at this problem, this paper analyzes and studies the path planning problem of unmanned aerial vehicles based on the factors that need to be considered in actual life logistics distribution. Firstly, the actual scenario requirements of logistics UAV applications are analyzed and a path planning algorithm for this scenario is enumerated. Subsequently, mathematical models are established from both path planning and customer satisfaction to assess the performance of logistics drones. Then, a comparative analysis of four existing classical path planning algorithms is conducted, and simulated annealing algorithm is used to optimize logistics delivery scenarios for path planning. Finally, combining the mathematical model and simulated annealing algorithm constructed in the previous article, logistics UAV simulation experiments are conducted in urban distribution scenarios and an ideal path planning model is obtained. The work of this article provides a certain reference basis for logistics companies in the application of logistics UAVs and the selection of path planning methods.

Autonomous aerial obstacle avoidance using LiDAR sensor fusion.

The obstacle avoidance problem of unmanned aerial vehicle (UAV) mainly refers to the design of a method that can safely reach the target point from the starting point in an unknown flight environment. In this paper, we mainly propose an obstacle avoidance method composed of three modules: environment perception, algorithm obstacle avoidance and motion control. Our method realizes the function of reasonable and safe obstacle avoidance of UAV in low-altitude complex environments. Firstly, we use the light detection and ranging (LiDAR) sensor to perceive obstacles around the environment. Next, the sensor data is processed by the vector field histogram (VFH) algorithm to output the desired speed of drone flight. Finally, the expected speed value is sent to the quadrotor flight control and realizes autonomous obstacle avoidance flight of the drone. We verify the effectiveness and feasibility of the proposed method in 3D simulation environment.

Adaptive attitude control of UAV based on neural network compensation

Aiming at the problem of unmanned aerial vehicle (UAV) attitude control with insufficient robustness and anti-disturbance, this paper proposes a UAV attitude control method combining incremental nonlinear dynamic inverse (INDI) and neural network (NN) adaptive compensation. Firstly, the attitude model of UAV with time scale separation is proposed. On this basis, the INDI control law is derived, and the angular acceleration information required by INDI method is feedback by the filter. Then, the adaptive NN compensation structure is introduced to eliminate the uncertainty caused by model mismatch, sensor delay and external disturbance. Finally, the UAV simulation is carried out. The result shows that this method improves robustness and anti-disturbance of original INDI method without changing structure and parameters of controller, and has a certain adaptive compensation ability for system uncertainty.

Learning-Based UAV Coverage-Aware Path Planning in Large-scale Urban Environments

In our research, the coverage-aware path planning problem of unmanned aerial vehicles (UAVs) in large-scale urban environments is studied. The goal of our research is to train the intelligent UAV to autonomously cover the area with satisfactory communication quality and finally arrive at the objective place without colliding with numerous skyscrapers. Such a multi-objective path planning problem is regularly non-convex and thus hard to converge. To this end, a distributed deep reinforcement learning (DRL)-based approach called Distributed-RPPO is developed to address the problem. To be specific, firstly we formulate our proposed problem as a Markov decision process (MDP). Since communication connectivity is the core constraint, a proximal policy optimization (PPO)-based SIR prediction network is designed for guiding the UAV to cover the area with superior communication connectivity, using only the UAV’s current location. Then we combine the PPO algorithm with the Long short-term memory (LSTM) structure to solve the basic navigation problem while only the historical interactive data is exploited for updating the parameter vector of the entire network. Simulation results demonstrate that our approach is capable of allowing the UAV to execute coverage-aware path planning tasks in large-scale urban environments. Furthermore, the learning efficiency is greatly improved compared to existing DRL-based approaches.

Reinforcement learning-based multi-strategy cuckoo search algorithm for 3D UAV path planning

Unmanned aerial vehicles are applied extensively in various fields due to their advantages of low-cost, high-maneuverability, and easy-operation. However, the path planning problem of unmanned aerial vehicles, which directly determines the flight safety and efficiency, still remains challenging when building and optimizing the path model. To further study the path planning problem, we firstly construct it as a constrained optimization problem. The objective function considers the costs of path length and threat, and the constraints involve the collision and turning angle. Additionally, we employ the theory of B-Spline curve to represent the planned paths to facilitate the optimization of established model. Then, aiming at the poor searchability and slow convergence speed of current optimization methods, we propose a reinforcement learning-based multi-strategy cuckoo search algorithm. Specifically, we establish an innovative reinforcement learning-based multi-strategy mechanism and a reinforced switch parameter based on the theory of reinforcement learning. To verify the effectiveness of the proposed algorithm, extensive experiments are carried out on the CEC’17 benchmark test and different three-dimensional path planning problems. Detailed statistical analysis of the experimental results confirm the superiority of our proposed algorithm to the other well-established algorithms.

Adaptive cylinder vector particle swarm optimization with differential evolution for UAV path planning

Particle swarm optimization (PSO) algorithm has a potential to solve route planning problem for unmanned aerial vehicle (UAV). However, the traditional PSO algorithm is easy to fall into local optimum under the complicated environments with multiple threats. In order to improve the performance in different complicated environments, a novel and effective PSO algorithm with adaptive adjustment of the parameters, cylinder vector and different evolution operator, named ACVDEPSO, is proposed and demonstrated to be effective for route planning problem for UAV. In the proposed ACVDEPSO, the velocity of the particle is converted to its cylinder vector for the convenience of the path search. It is worth highlighting that the parameters of ACVDEPSO algorithm are automatically chosen by the time and the fitness values of the particles. Furthermore, a challenger based on differential evolution operator is introduced to reduce the probability of falling into local optimum and accelerate the algorithm convergence speed. The simulation experiments have been conducted in real digital elevation model (DEM) maps to test the performance of the ACVDEPSO. The experiment results validate that the optimization performance of the ACVDEPSO outperforms the other comparison methods, which can efficiently generate a higher quality path for UAV under the complicated 3D environments.

Secure Control Design for Networked Control Systems With Nonlinear Dynamics Under Time-Delay-Switch Attacks

A continuous controller is developed for a centralized network control system (NCS), which is composed of agents with nonlinear dynamics subject to a time-delay-switch (TDS) attack and additive disturbances. Since the state tracking error is unmeasurable during TDS attacks, controllers cannot use the state tracking error to coordinate the NCS. Therefore, a novel error signal is designed to address this unique challenge and enable the NCS to achieve a formation control objective. Furthermore, a TDS attack mitigation strategy is developed, which uses both learning- and model-based approaches to estimate an agent’s state for TDS attack detection and compensation. Lyapunov–Krasovskii functionals are used in the stability analysis to prove that the tracking errors converge to a steady-state residual, which is a function of the system uncertainty and TDS attack properties. The leader–follower formation control problem for unmanned aerial vehicles based on a pure pursuit guidance law is selected for a simulation study to validate the performance of the proposed method.

Real-time online trajectory planning and guidance for terminal area energy management of unmanned aerial vehicle

<p style='text-indent:20px;'>Aiming at the energy management problem of unmanned aerial vehicles (UAVs) in the terminal area energy management (TAEM) phase, a real-time online trajectory planning and guidance strategy based on judging energy is proposed. The trajectory planning strategy estimates the flight profile online in real time by judging the energy and changing the radius of the heading alignment circle. In addition, guidance instructions are also obtained at once. In the S-turn stage, the lateral guidance adopts a closed loop control mode with a fixed bank angle. In the remaining stage, the lateral guidance adopts a closed loop control mode for tracking the azimuth angle. In all stages, the longitudinal guidance adopts a closed loop control mode for tracking the flight path angle and flight height. The trajectory planning strategy is able to quickly generate a reference trajectory for testing cases with large variations not only in the initial energy but also in the energy of the flight process. The simulation results show that the proposed trajectory planning and guidance strategy can effectively manage a UAV's energy in the TAEM phase, ensuring that the UAV lands safely.</p>

Robust Trajectory and Resource Optimization in UAV-Enabled IoT Networks under Probabilistic LoS Channel in Presence of Jammers

This paper studies the anti-jamming problem of unmanned aerial vehicle (UAV)-enabled Internet of Things (IoT) communication networks in the presence of a jammer under the accurate probabilistic line-of-sight (LoS) model. Our goal is to maximize the information collection throughput of the system under the assumption that only the jammer's approximate location is known. To this end, we formulate a throughput maximization problem by optimizing the UAV trajectory, the IoT devices' transmit power, and communication scheduling under the accurate real-time probabilistic LoS channel. However, the proposed optimization problem is non-convex and coupled, and hence intractable to be solved. In order to tackle the problem, a robust iterative algorithm is proposed by leveraging the block coordinate descent (BCD) method, the successive convex approximation (SCA) technology, the difference of convex (D.C) programming approach, and the S-procedure. Extensive simulation results show that our proposed algorithm significantly improves the system throughput while achieving a practical anti-jamming effect compared with the benchmark algorithms.

Helmet Wearing Detection of Motorcycle Drivers Using Deep Learning Network with Residual Transformer-Spatial Attention

Aiming at the existing problem of unmanned aerial vehicle (UAV) aerial photography for riders’ helmet wearing detection, a novel aerial remote sensing detection paradigm is proposed by combining super-resolution reconstruction, residual transformer-spatial attention, and you only look once version 5 (YOLOv5) image classifier. Due to its small target size, significant size change, and strong motion blur in UAV aerial images, the helmet detection model for riders has weak generalization ability and low accuracy. First, a ladder-type multi-attention network (LMNet) for target detection is designed to conquer these difficulties. The LMNet enables information interaction and fusion at each stage, fully extracts image features, and minimizes information loss. Second, the Residual Transformer 3D-spatial Attention Module (RT3DsAM) is proposed in this work, which digests information from global data that is important for feature representation and final classification detection. It also builds self-attention and enhances correlation between information. Third, the rider images detected by LMNet are cropped out and reconstructed by the enhanced super-resolution generative adversarial networks (ESRGAN) to restore more realistic texture information and sharp edges. Finally, the reconstructed images of riders are classified by the YOLOv5 classifier. The results of the experiment show that, when compared with the existing methods, our method improves the detection accuracy of riders’ helmets in aerial photography scenes, with the target detection mean average precision (mAP) evaluation indicator reaching 91.67%, and the image classification top1 accuracy (TOP1 ACC) gaining 94.23%.

Path Planning Research of a UAV Base Station Searching for Disaster Victims' Location Information Based on Deep Reinforcement Learning.

Aiming at the path planning problem of unmanned aerial vehicle (UAV) base stations when performing search tasks, this paper proposes a Double DQN-state splitting Q network (DDQN-SSQN) algorithm that combines state splitting and optimal state to complete the optimal path planning of UAV based on the Deep Reinforcement Learning DDQN algorithm. The method stores multidimensional state information in categories and uses targeted training to obtain optimal path information. The method also references the received signal strength indicator (RSSI) to influence the reward received by the agent, and in this way reduces the decision difficulty of the UAV. In order to simulate the scenarios of UAVs in real work, this paper uses the Open AI Gym simulation platform to construct a mission system model. The simulation results show that the proposed scheme can plan the optimal path faster than other traditional algorithmic schemes and has a greater advantage in the stability and convergence speed of the algorithm.

Cyber-physical framework for UAV intelligent communications

To relieve the communication bottleneck problem of unmanned aerial vehicles (UAVs), this study discusses an intelligent communication framework for UAVs from a cyber-physical perspective where the interdependence among communication, computation, and control is fully exploited. First, we illustrate the coupling effects of computation and control on communication and investigate some related works. Then, a novel cyber-physical framework for UAV communications is proposed, and the key functions of each module are demonstrated. The framework expands the dimension of communication decisions to computation and control and thus can orient and address communication issues more precisely. These provide inspiration for the integrated design of communication, computation, and control. Furthermore, a case study is presented to show the communication optimization based on the proposed framework. Meanwhile, the simulation results verify the effectiveness and superiority of the framework.

Lyapunov-Based Nonlinear Model Predictive Control for Attitude Trajectory Tracking of Unmanned Aerial Vehicles

This paper presents a new Lyapunov-based nonlinear model predictive controller (LNMPC) for the attitude control problem of unmanned aerial vehicles (UAVs), which is essential for their functioning operation. The controller is designed based on a quadratic cost function integrating UAV dynamics and system constraints. An additional contraction constraint is then introduced to ensure closed-loop system stability. That constraint is fulfilled via a Lyapunov function derived from a sliding mode controller (SMC). The feasibility and stability of the LNMPC are finally proved. Simulation and comparison results show that the proposed controller guarantees the system stability and outperforms other state-of-the-art nonlinear controllers such as the backstepping controller (BSC) and SMC. In addition, the proposed controller can be integrated into an existing UAV model in the Gazebo simulator to perform software-in-the-loop tests. The results show that the LNMPC is better than the built-in PID controller of the UAV, which confirms the validity and applicability of our proposed approach.