In recent years, unmanned aerial vehicles (UAVs), commonly known as drones, have gained increasing interest in both academia and industries. The evolution of UAV technologies, such as artificial intelligence, component miniaturization, and computer vision, has decreased their cost and increased availability for diverse applications and services. Remarkably, the integration of computer vision with UAVs provides cutting-edge technology for visual navigation, localization, and obstacle avoidance, making them capable of autonomous operations. However, their limited capacity for autonomous navigation makes them unsuitable for global positioning system (GPS)-blind environments. Recently, vision-based approaches that use cheaper and more flexible visual sensors have shown considerable advantages in UAV navigation owing to the rapid development of computer vision. Visual localization and mapping, obstacle avoidance, and path planning are essential components of visual navigation. The goal of this study was to provide a comprehensive review of vision-based UAV navigation techniques. Existing techniques have been categorized and extensively reviewed with regard to their capabilities and characteristics. Then, they are qualitatively compared in terms of various aspects. We have also discussed open issues and research challenges in the design and implementation of vision-based navigation techniques for UAVs.

Recently, owing to the high mobility and low cost of drones, drone-based delivery systems have shown considerable potential for ensuring flexible and reliable parcel delivery. Several crucial design issues must be considered to design such systems, including route planning, payload weight consideration, distance measurement, and customer location. In this paper, we present a survey of emerging drone routing algorithms for drone-based delivery systems, emphasizing three major drone routing aspects: trajectory planning, charging, and security. We focus on practical design considerations to ensure efficient, flexible, and reliable parcel delivery. We first discuss the potential issues arising when designing such systems. Next, we present a novel taxonomy based on the above-mentioned three aspects. We extensively review each algorithm for drone routing in terms of key features and operational characteristics. Furthermore, we compare the algorithms in terms of their main idea, advantages, limitations, and performance aspects. Finally, we present open research challenges to motivate further research in this field. In particular, we focus on the major aspects that researchers and engineers need to consider in order to design effective and reliable drone routing algorithms for drone-based delivery systems.

A flying ad hoc network (FANETs), also known as a swarm of unmanned aerial vehicles (UAVs), can be deployed in a wide range of applications including surveillance, monitoring, and emergency communications. UAVs must perform real-time communication among themselves and the base station via an efficient routing protocol. However, designing an efficient multihop routing protocol for FANETs is challenging due to high mobility, dynamic topology, limited energy, and short transmission range. Recently, owing to the advantages of multi-objective optimization, Q-learning (QL)-based position-aware routing protocols have improved the performance of routing in FANETs. In his article, we provide a comprehensive review of existing QL-based position-aware routing protocols for FANETs. We rigorously address dynamic topology, mobility models, and the relationship between QL and routing in FANETs, and extensively review the existing QL-based position-aware routing protocols along with their advantages and limitations. Then, we compare the reviewed protocols qualitatively in terms of operational features, characteristics, and performance metrics. We also discuss important open issues and research challenges with potential research directions.

Collaborative unmanned aerial vehicle (UAV) swarm networks can effectively execute various emerging missions such as surveillance and communication coverage. However, due to high mobility and constrained transmission range, packet routing encounters mutual interferences, link breakages, and unexpected delays. In such networks, routing performance is coupled with trajectory control, frequency allocation, and relay selection. In this study, we propose a joint trajectory control, frequency allocation, and packet routing (JTFR) algorithm, in which link utility is maximized by considering the link stability, signal-to-interference-plus-noise ratio, queuing delay, and residual energy of UAVs. The proposed JTFR employs adaptive distributed multi-agent deep deterministic policy gradient coupled with the swarming behavior to obtain the optimal solution. For each UAV, an actor network is established by utilizing a long short-term memory-based state representation layer containing two-hop neighbor information to adopt the dynamic time-varying topology. Subsequently, a scalable multi-head attentional critic network is set up to adaptively adjust the actor network policy of each UAV by collaborating with neighbors. The extensive simulation results show that JTFR outperforms existing routing protocols by 30–60% less end-to-end delay, 15–32% better packet delivery ratio, and 20–46% less energy consumption.

In an air–ground integrated network (AGIN), low-altitude unmanned aerial vehicles (UAVs) and a high-altitude platform (HAP) operate synergistically to support computationally expensive and delay-critical applications of mobile ground devices (GDs). UAVs obtain tasks from GDs, execute the tasks, and offload some of the tasks to the HAP. In AGINs, the trajectory control of a UAV swarm should provide optimal coverage to randomly distributed mobile GDs. The limited resources of UAVs, such as energy, computation, caching, and bandwidth, result in further challenges. Therefore, a joint optimization problem is formulated in this study to minimize the task execution delay and energy consumption of UAVs by optimizing the UAVs trajectory, GD association, task-offloading ratio, and resource allocation. The limited resources, maximum task execution delay, task queue size, and mobility of UAVs are regarded as key constraints. Solving the problem is intricate owing to the complex mixed-integer nonlinear constraints coupled with a large continuous and discrete decision space. To track the dynamics in AGINs and efficiently solve the problem above, we utilize a swarming behavior-integrated multi-agent gated recurrent unit-based actor and multi-head attention-based critic network (SMA-GAC) framework. Results of simulative evaluation show that the proposed SMA-GAC outperforms baseline methods.