Unmanned aerial vehicles (UAVs) applications have increased in popularity in recent years because of their ability to incorporate a wide variety of sensors while retaining cheap operating costs, easy deployment, and excellent mobility. However, controlling UAVs remotely in complex environments limits the capability of the UAVs and decreases the efficiency of the whole system. Therefore, many researchers are working on autonomous UAV navigation where UAVs can move and perform the assigned tasks based on their surroundings. With recent technological advancements, the application of artificial intelligence (AI) has proliferated. Autonomous UAV navigation is an example of an application in which AI plays a critical role in providing fundamental human control characteristics. Thus, many researchers have adopted different AI approaches to make autonomous UAV navigation more efficient. This paper comprehensively surveys and categorizes several AI approaches for autonomous UAV navigation implicated by several researchers. Different AI approaches comprise mathematical-based optimization and model-based learning approaches. The fundamentals, working principles, and main features of the different optimization-based and learning-based approaches are discussed in this paper. In addition, the characteristics, types, navigation models, and applications of UAVs are highlighted to make AI implementation understandable. Finally, the open research directions are discussed to provide researchers with clear and direct insights for further research.

Flying ad-hoc networks (FANET) are one of the most important branches of wireless ad-hoc networks, consisting of multiple unmanned air vehicles (UAVs) performing assigned tasks and communicating with each other. Nowadays FANETs are being used for commercial and civilian applications such as handling traffic congestion, remote data collection, remote sensing, network relaying, and delivering products. However, there are some major challenges, such as adaptive routing protocols, flight trajectory selection, energy limitations, charging, and autonomous deployment that need to be addressed in FANETs. Several researchers have been working for the last few years to resolve these problems. The main obstacles are the high mobility and unpredictable changes in the topology of FANETs. Hence, many researchers have introduced reinforcement learning (RL) algorithms in FANETs to overcome these shortcomings. In this study, we comprehensively surveyed and qualitatively compared the applications of RL in different scenarios of FANETs such as routing protocol, flight trajectory selection, relaying, and charging. We also discuss open research issues that can provide researchers with clear and direct insights for further research.

For heterogeneous demands in fifth-generation (5G) new radio (NR), a massive machine type communication (mMTC), enhanced mobile broadband (eMBB), and ultra-reliable and low-latency communication (URLLC) services have been introduced. To ensure these quality-of-service (QoS) requirements, non-orthogonal multiple access (NOMA) has been introduced in which multiple devices can be served from the same frequency by manipulating the power domain and successive interference cancellation (SIC) technique. To maximize the efficiency of NOMA systems, an optimal resource allocation, such as power allocation and channel assignment, is a key issue that needs to be solved. Although many researchers have proposed multiple solutions, there have been no studies addressing the 5G QoS requirements and three services that coexist in the same network. In this paper, we formulate an optimal power allocation scheme under Karush-Kuhn-Tucker (KKT) optimality conditions incorporating different NOMA constraints to maximize the channel sum-rate and system fairness. We then propose a priority-based channel assignment with a deep Q-learning algorithm to maintain the 5G QoS requirements and increase the network performance. Finally, We conduct extensive simulations with respect to different system parameters and can confirm that the proposed scheme performs better than other existing schemes.

Extended Reality (XR) applications, which may encompass Augmented Reality (AR) and Virtual Reality (VR), commonly involve immersive virtual environments that are based on real physical environments. Transmitting the extensive color and depth image data for representing a physical environment over a communication network to create a corresponding immersive environment at a remote location is very challenging due to the enormous data volumes and the time-constraints of real-time immersion. We explore semantic compression, which conveys the semantic meaning of the data through color-codes (CCs) to reduce the transmitted data volume. The creation of an immersive environment conventionally involves the five steps (with corresponding output): calibration (single-frame point cloud), registration (registered point cloud), volume reconstruction (voxel frame), marching cubes (meshes), and rendering (3D environment). We develop the novel cXR+ semantic compression that splits the volume reconstruction into a client-side virtual network function (VNF) that represents the registered point cloud as CCs for network transmission to a server-side VNF that decodes the CCs to obtain the voxel frames so as to complete the volume reconstruction. We consider an analogous splitting of the calibration into two VNFs with Graph Coloring (GC) compression of the color and depth image data as a comparison benchmark. Additionally, we consider the transmission of the raw and JPG compressed point cloud data as well as the volume reconstruction at the client-side and subsequent transmission of the voxel frames as benchmarks. We conduct measurements of the compression (computing) time, transmission time, compression ratio, and reconstruction accuracy for real-world data sets so as to elucidate the trade-offs in employing voxel-based semantic compression for transmitting immersive environments over communication networks.

Immersive mixed reality in industrial applications requires low latencies; however, systems are commonly limited by the large amounts of generated data and the subsequent high traffic loads on the 5G network. Semantic or goal-oriented compression has emerged as a solution to this problem. In this study, we combine the generated data from several cameras at the network edge through multilevel semantic coding, which we refer to as MLcXR+. We define the overall MLcXR+ approach, including computation load placements on Edge Application Servers (EASs), and demonstrate feasibility in a 5G system with an open-source prototype on commodity hardware. We develop and evaluate two MLcXR+ modes: independent MLcXR+ (iMLcXR+), where the EASs operate independently, and dependent MLcXR+ (dMLcXR+), where the EASs form a chain of successive compression levels. From our evaluations with a reproducible dataset and our open-source prototype, we find that compared to prior state-of-the-art, our MLcXR+ approach can achieve a 3.5 times higher compression ratio factor, substantially reducing the data amounts sent over the 5G Data Network (DN) and processed at the Head-Mounted Display (HMD). We also find that iMLcXR+ at a single EAS, or dMLcXR+ with one or an appropriately configured higher number of EASs achieve the highest compression. Load balancing of the MLcXR+ computations over multiple EASs substantially reduces the iMLcXR+ compression performance, and can slightly increase the network transport delays of dMLcXR+ due to the compression chain. However, even load-balanced dMLcXR+ still incurs slightly less total computation (compression) and network transport delays than prior approaches, mainly due to the reduced HMD processing.