Set Of Unmanned Aerial Vehicles Research Articles

Green Edge Intelligence for Smart Management of a FANET in Disaster-Recovery Scenarios

Disruption of the ground communication infrastructure in emergency scenarios makes post-disaster rescue operations very complicate. This paper proposes to use edge intelligence to support rescue operators in managing these emergency scenarios. A set of Unmanned Aerial Vehicles (UAV), organized as Flying Ad-Hoc network (FANET), autonomously takeoff and land to provide emergency operators with edge computing services. A charging station for batteries is supplied by a renewable-energy generator. The FANET Controller applies model-based Reinforcement Learning to decide how many UAVs have to take off, according to the current edge-computing service requests and the power availability, and a forecast of them. The optimal management policy has to provide the necessary level of edge-computing avoiding wide use of satellite channels in a short-time horizon during low green-energy generation and high service request periods. Results highlight that the optimal policy is an efficient modification of the greedy one, i.e., the policy enabling the takeoff of all the necessary UAVs without being care of challenging events in the future. A deep analysis has revealed that the level of modification depends on the combination of the edge-computing service request and the green power availability.

Deploying the Minimum Number of Rechargeable UAVs for a Quarantine Barrier

To control the rapid spread of COVID-19, we consider deploying a set of Unmanned Aerial Vehicles (UAVs) to form a quarantine barrier such that anyone crossing the barrier can be detected. We use a charging pile to recharge UAVs. The problem is scheduling UAVs to cover the barrier, and, for any scheduling strategy, estimating the minimum number of UAVs needed to cover the barrier forever. We propose breaking the barrier into subsegments so that each subsegment can be monitored by a single UAV. We then analyze two scheduling strategies, where the first one is simple to implement and the second one requires fewer UAVs. The first strategy divides UAVs into groups with each group covering a subsegment. For this strategy, we derive a closed-form formula for the minimum number of UAVs. In the case of insufficient UAVs, we give a recursive function to compute the exact coverage time and give a dynamic-programming algorithm to allocate UAVs to subsegments to maximize the overall coverage time. The second strategy schedules all UAVs dynamically. We prove a lower and an upper bound on the minimum number of UAVs. We implement a prototype system to verify the proposed coverage model and perform simulations to investigate the performance.

Smart Zero-Touch Management of UAV-Based Edge Network

The next generation of wireless communications networks, namely 6G, will be aimed at realizing a fully connected world, and at providing ubiquitous connectivity to people and objects even in remote areas that are very far from the structured Internet core network. These goals include the definition and the design of intelligent communications environments mainly characterized by pervasive artificial intelligence and large-scale automation. The target of this paper is the design of a management framework for edge networks realized with Flying Ad-Hoc Networks (FANET) consisting of a set of Unmanned Aerial Vehicles (UAVs) to provide a remote geographic area with computing and networking facilities for delay-sensitive applications. To this purpose, each UAV is equipped with a Computing Element (CE) to process jobs received through vertical offloading from ground devices. In addition, horizontal offload among UAVs of the FANET is introduced for load balancing purposes, to guarantee that the FANET computation delay for each received job is minimized and is almost independent of the activity state of the area covered by the UAV receiving that job. The proposed FANET management framework is based on Deep Reinforcement Learning (DRL) to allow zero-touch adaptation to the time-variant activity state of the area covered by each UAV. Numerical results demonstrate the power of the proposed framework and the enhancements achieved with respect to the current literature.

Optimal Deep Reinforcement Learning for Intrusion Detection in UAVs

In recent years, progressive developments have been observed in recent technologies and the production cost has been continuously decreasing. In such scenario, Internet of Things (IoT) network which is comprised of a set of Unmanned Aerial Vehicles (UAV), has received more attention from civilian to military applications. But network security poses a serious challenge to UAV networks whereas the intrusion detection system (IDS) is found to be an effective process to secure the UAV networks. Classical IDSs are not adequate to handle the latest computer networks that possess maximum bandwidth and data traffic. In order to improve the detection performance and reduce the false alarms generated by IDS, several researchers have employed Machine Learning (ML) and Deep Learning (DL) algorithms to address the intrusion detection problem. In this view, the current research article presents a deep reinforcement learning technique, optimized by Black Widow Optimization (DRL-BWO) algorithm, for UAV networks. In addition, DRL involves an improved reinforcement learning-based Deep Belief Network (DBN) for intrusion detection. For parameter optimization of DRL technique, BWO algorithm is applied. It helps in improving the intrusion detection performance of UAV networks. An extensive set of experimental analysis was performed to highlight the supremacy of the proposed model. From the simulation values, it is evident that the proposed method is appropriate as it attained high precision, recall, F-measure, and accuracy values such as 0.985, 0.993, 0.988, and 0.989 respectively.

Cluster-Based Routing Protocols for Flying Ad Hoc Networks (FANETs)

Flying Ad-Hoc Network (FANET) is a set of Unmanned Aerial Vehicles (UAVs) inter-connected wirelessly. FANETs self-organize and provide low-cost, adaptable, and simple-to-implement flying nodes, enabling them to complete complicated tasks more quickly and collectively. The high mobility of nodes and the highly dynamic topology pose challenges to communication design, particularly when creating a routing protocol for UAV networks; this has inspired researchers to contribute and develop this technology. Hierarchical routing technique known as clustering is necessary to offer scalability, survivability, and distribute payload among UAVs to maintain the performance. This study has proposed a comprehensive survey of the cluster-based routing protocols (CBRPs) in terms of their strengths, weaknesses, specific applications, method, number of nodes, and future improvements for serving FANETs. Moreover, 21 CBRPs based FANETs were reviewed in terms of their topology, challenges, scalability, characteristics, clustering strategy, outstanding features, cluster head (CH) selection, routing metrics, and performance measures. In addition, open issues that need to be addressed in future studies in the field of routing protocols for UAV networks were also debated.

Efficient data collection and tracking with flying drones

Data collection is an important mechanism for wireless sensor networks to be viable. This paper addresses the Aerial Data Collection Problem (ADCP) from a set of mobile wireless sensors located on the ground, using a fleet of flying devices. The objective is i) to deploy a set of Unmanned Aerial Vehicles (UAVs) in a 3D space to cover and collect data from all the mobile wireless sensors at each time step through a ground-to-air communication, ii) to send these data to a central base station using multi-hop wireless air-to-air communications through the network of UAVs, iii) while minimizing the total deployment cost (communication and deployment) over time. The Aerial Data Collection Problem (ADCP) is a complex time and space coverage, and connectivity problem. We first present a mixed-integer linear program solving ADCP optimally for small instances. Then, we develop a second model solved by column generation for larger instances, with optimal or heuristic pricing programs. Results show that our approach provides very accurate solutions minimizing the data collection cost. Moreover, only a very small number of columns are generated throughout the resolution process, showing the efficiency of our approach.

Heterogeneous UAV Cells: An Effective Resource Allocation Scheme for Maximum Coverage Performance

This paper develops an effective approach for the 3D deployment of a heterogeneous set of unmanned aerial vehicles (UAVs) acting as aerial base stations that provide maximum wireless coverage for ground users in a given geographical area. This problem is addressed in two steps. First, in order to maximize the utilization of each UAV, its optimal flight altitude is found based on the UAV's transmit power which provides maximum coverage radius on the ground. The UAVs are classified into separate groups based on their transmit powers and optimal flight altitudes. Next, given a repository of UAVs belonging to different classes, the proposed technique finds an optimal subset of the available UAVs along with their optimal 3D placement to provide the maximum network coverage for a given area on the ground with the minimum power consumption. This optimization problem is proved to be NP-hard, for which a novel algorithm is proposed to solve the problem. Simulation results demonstrate the effectiveness of the proposed solution and provide valuable insights into the performance of the Heterogeneous UAV-supported small cell networks.

Enabling Multi-Mission Interoperable UAS Using Data-Centric Communications.

We claim the strong potential of data-centric communications in Unmanned Aircraft Systems (UAS), as a suitable paradigm to enhance collaborative operations via efficient information sharing, as well as to build systems supporting flexible mission objectives. In particular, this paper analyzes the primary contributions to data dissemination in UAS that can be given by the Data Distribution Service (DDS) open standard, as a solid and industry-mature data-centric technology. Our study is not restricted to traditional UAS where a set of Unmanned Aerial Vehicles (UAVs) transmit data to the ground station that controls them. Instead, we contemplate flexible UAS deployments with multiple UAV units of different sizes and capacities, which are interconnected to form an aerial communication network, enabling the provision of value-added services over a delimited geographical area. In addition, the paper outlines an approach to address the issues inherent to the utilization of network-level multicast, a baseline technology in DDS, in the considered UAS deployments. We complete our analysis with a practical experience aiming at validating the feasibility and the advantages of using DDS in a multi-UAV deployment scenario. For this purpose, we use a UAS testbed built up by heterogeneous hardware equipment, including a number of interconnected micro aerial vehicles, carrying single board computers as payload, as well as real equipment from a tactical UAS from the Spanish Ministry of Defense.

Heterogeneous Aerial Platform Adaptive Mission Planning Using Genetic Algorithms

The focus of this study was to examine an automated mission planner that utilized a heterogeneous set of small aerial assets simultaneously surveying several Points of Interest (POI). The concept mission was to aerially search for an unknown Target of Interest (TOI) located amongst a set of POIs. In order to develop a planning system that is capable of meeting mission requirements, an adaptive mission planner, based on a Genetic Algorithm (GA), was investigated that seeks to task a heterogeneous set of unmanned aerial vehicles. Initially, a set of fixed wing UAVs were tasked to survey a set of POIs in search of a TOI, a POI that requires additional or long term surveillance. Once a TOI was located, a multi-rotor UAV was deployed to visit the TOI and additional POIs. Remaining POIs that were not tasked to the multi-rotor UAV were then re-tasked amongst the fixed wing aircraft set. The mission planner was implemented using a GA that planned initial and post TOI identification UAV paths. Mission simulations were conducted and the mission time increase was analyzed against different TOI locations and number of UAVs searching. Simulation results indicated that the deployment of a multi-rotor UAV not only provided additional surveillance of the TOI, but reduced overall mission times as well.

Simultaneous sensor selection and routing of unmanned aerial vehicles for complex mission plans

Military reconnaissance missions often employ a set of unmanned aerial vehicles (UAVs) equipped with sensors to gather intelligence information from a set of known targets. UAVs are limited by the number of sensors they can hold; also attaching a sensor adds weight to the aircraft which in turn reduces the flight time available during a mission. The task of optimally assigning sensors to UAVs and routing them through a target field to maximize intelligence gain is a generalization of the team orienteering problem studied in the vehicle routing literature. This work presents a mathematical programming model for simultaneous sensor selection and routing of UAVs, which solves optimally using CPLEX for simple missions. Larger missions required the development of three heuristics, which were augmented by Column Generation. Results from a performance study indicated that the heuristics quickly found good solutions. Column Generation improved the solution in many instances, with minimal impact on overall solution time. The rapid nature of the overall solution approach allows it to be used in other mission planning tasks. A fleet sizing application is discussed as an example of its flexible usage.

Control theoretic analysis of a target search problem by a team of search vehicles

This article considers a target search problem by a set of unmanned aerial vehicles (UAVs). The problem is modelled as a discrete state, continuous-time Markov process. Convergence properties are investigated by using the eigenvalues and eigenvectors of a state transition rate matrix without explicitly solving differential equations or calculating matrix exponentials. The paper also studies the effect of cueing on convergence rate using eigenvalues analysis and optimal control theoretic perspective.