Drone-based services have been gaining large interest due to their mobility without the need for a heavy infrastructure and their flexibility with various sensors/actuators. Because drones heavily depend on continuous sensor data and commands from ground control stations, ensuring drone operation reliability and security is a crucial concern. Traditional security measures often fall short due to the limited resources and battery limitations of drones. This paper explores the use of Recurrent Neural Networks (RNNs) by focusing on Long Short-Term Memory (LSTM) networks for their temporal and sequential analysis capabilities. We leverage these capabilities for anomaly detection in drone sensor data and received commands, which we refer to as Denial of Usage Detection Engine IDS (DUDE-IDS) to enhance drone operational security and reliability. We integrated the proposed DUDE-IDS into the drone mission computer to monitor data flows and detect potential threats in real-time. Experimental results demonstrate the effectiveness of this approach in identifying anomalies, thereby mitigating risks, associated with GPS spoofing, Man-in-the-Middle (MITM), replay, and Denial-of-Service (DoS) attacks with 98\% accuracy. We also experimented with resource utilization and power consumption under different configurations, which demonstrate the applicability in active drone operations in real-time.

The integration of the Internet of Things (IoT) with Unmanned Aerial Vehicles (UAVs), commonly known as drones, has resulted in an emerging technology known as the Internet of Drone Things (IoDT). This field permeates many vertical domains such as emergency response, agriculture, surveillance, and urban planning and we observe a large interest both from academia and industry towards IoDT. Nevertheless, IoDT is still an immature topic with many open questions, including the cost of building an IoDT-based environment, expertise, safety, and algorithm development. Therefore, studies using a physical testbed are not well-desired, and hence simulators are the preferred choices. However, current simulators that can be used for the IoDT environments are general-purpose, too resource-intensive, and lack fine control mechanisms for IoDT components, with some requiring expensive licensing. As a solution, we present a new IoDT simulator that is lightweight, flexible, and easy to use, addressing the expense and complexity of current systems. This simulator assists in developing high-level algorithms without the overhead of current simulators. With fine-grain controls of IoDT components such as sensors, actuators, and communication protocols, the simulator provides an extensible simulation environment. We present two scenarios, package delivery, and disaster monitoring, to demonstrate the usefulness of our simulator. This work outlines the potential impact of our simulator in reducing the entry barriers to research and development of IoDT, making advanced IoDT solutions more accessible and cost-effective.

Internet of Things (IoT) and Operational Technology (OT)  are becoming essential parts of next-generation smart environments, including Industry 4.0 thanks to their capabilities of monitoring and/or controlling industrial devices, processes, and events. It is expected that there will be around 75 billion such devices, especially considering 5G (and 6G in the future) networking. However, security is one of the major concerns, especially because most legacy devices/equipment have little to no security measures applied. And, replacing all the equipment with new ones continuously is not a feasible solution to enforce security measures. One alternative is enforcing Zero Trust Architecture (ZTA) principles in these environments based on the ``never trust, always verify'' principle. Applying ZT for an OT environment through its network (by continuously monitoring and checking the activities based on ZTA-based policies) can improve the sustainability and security of the IoT/OT-based environments because no major changes would be needed in the existing infrastructures while improving security. For this reason, we propose an architecture that monitors the network behavior and compares them with the devices' proposed identities (their IP and MAC addresses). We first monitor the network behaviors, create flows, and select the best features. Then, we identify the individual devices using supervised machine learning techniques such as Gradient Boosting Classifier as they are lightweight and fast in detection compared to alternatives. Our results show high accuracy, precision, and recall values in our experiments. Using different scenarios, we evaluated our idea and if a device behaves differently than the proposed behavior, we are able to detect and put a firewall rule that blocks the device network traffic on the gateway.

Drones have become essential to various industries due to their capabilities in inspections, transportation, mapping, and delivery. As the drone market expands rapidly, so does the need for robust security measures to safeguard against cyberattacks. This paper introduces DUDE-IDS, a novel intrusion detection system (IDS) specifically designed for drones. Firstly, we introduce a time interval approach for generating labeled data. Then, we propose new features that can capture time-related patterns in drones’ network data. This approach enriches the representation of network flows, providing a better understanding of the dynamics of cyberattacks over time. DUDE-IDS takes advantage of knowledge derived from the time interval approach and the augmented feature set, which leads to improved detection capabilities. It utilizes supervised machine learning to analyze network traffic and detect anomalies, achieving high accuracy (95.84%), precision (96.18%), recall (95.84%), and F1 scores (95.62%).

The Micro Air Vehicle Link (MAVLink) protocol plays a crucial role in enabling communication between drones and Ground Control Stations (GCS). With the increasing adoption of drones, the security and integrity of MAVLink protocol have also become paramount. This paper delves into the fundamental aspects of MAVLink, highlighting its security challenges and proposing potential solutions to enhance its resilience against cyber threats. The study presents findings on the vulnerabilities of the MAVLink protocol and introduces a novel approach to securing communications on the MAVLink protocol for drones. The paper evaluates different Authenticated Encryption with Associated Data (AEAD) schemes and their impact on the performance of MAVLink, emphasizing the importance of encryption and authentication for ensuring data security.

Path-planning for drones in areas with complex and unknown environments, constrained by various obstacles, presents a significant challenge in drone operations. This problem extends beyond merely finding an appropriate path from the starting point to the destination; it also involves selecting the ideal path among all available options based on given conditions. In this paper, we propose a novel smart path planning algorithm based on the Breadth-First Search (BFS) algorithm, taking into account both swarm energy and task completion. Performance metrics include the percentage of tasks completed, unachievable, and incomplete. Our novel algorithm demonstrates a significant improvement over traditional methods, outperforming them by an average of 10-15% in task completion. In extreme cases, this margin increases to nearly 20%. Analysis of unachievable tasks reveals that our method greatly reduces their occurrence. This research underscores the potential of our novel algorithm in enhancing operational performance for drone-based tasks, especially in hazardous contexts. 

The global drone market is growing rapidly as drones are being utilized for surveillance, transportation, search and rescue, military, etc. Similarly, the demand for drone swarms is also increasing both in the defense and commercial sectors. However, controlling a drone swarm is a challenging problem that requires a robust communication network, advanced management algorithms, and cutting-edge technology. In this paper, we focus on the drone swarm control strategy by transforming the drone swarm into a structured formation through abstraction in a hierarchical way so that a swarm is divided into subgroups where each subgroup has a leader to process the calculations and broadcast required information to the other sub-group members. This results in the ultimate coherency and alignment of the swarm. Our results have shown that the structured transformation of swarm architecture is much more efficient than the general structure regarding the number of required messages. 

The usage and application areas of Unmanned Aerial Vehicles (UAVs) are increasing such as military services, live streaming events, aerial photography, agriculture, firefighting, product delivery, asset inspections, and so on owing to bringing along the many benefits with it. According to Federal Aviation Administration (FAA), 865,660 drones (or UAVs) are registered and of these, 340,247 are commercial drones, 521,819 are recreational drones, 3,594 are paper registrations.

This paper presents a high switching frequency FPGA implementation of Maximum Torque Per Ampere (MTPA) and Flux Weakening which are branch of Field Oriented Control (FOC) method for 3-phase machine drives. A common architecture has been constructed for both BrushLess DC motors (BLDC) and Permanent Magnet Synchronous Motors (PMSM). For this purpose, the controller module was implemented using Space Vector Modulation (SVM) technique. The user interface module was designed to provide real-time torque-time, speed-time, and current-time plots for the user. This interface runs on the PS part of the FPGA and interacts with the user through a UART. The entire system has been verified through simulation. 

This paper presents an FPGA implementation of Field Oriented Control (FOC) method with high switching frequency for 3-phase machine drives. A common architecture has been constructed for both BrushLess DC motors (BLDC) and Permanent Magnet Synchronous Motors (PMSM). For this purpose, the controller module has been implemented by using a hardware efficient algorithm, namely, Coordinate Rotation Digital Computer (CORDIC). The result of this implementation has been compared with the literature, and we claim that this paper’s FPGA design has better performance in terms of area and speed with respect to other FPGA-based FOC designs.