An unmanned aerial vehicle (UAV) is a pilotless aircraft that is capable of flying and maintaining altitude without the need for a human operator, offers more cost-efficient solutions, and can carry out even important tasks cost-effectively. UAVs can provide several benefits and a wide range of uses because of their mobility, versatility, and flexibility at different altitudes. Over recent years, UAV technology has gained significant attention in various fields, such as traffic management, surveillance, agriculture, wireless communication, delivering medicine, border monitoring, photography, infrastructure inspection, post-disaster operations, etc. Despite the many benefits of UAVs, there are also many challenges related to UAVs, such as path planning, mission planning, optimal deployment, decision-making, collision avoidance, security, energy management, etc. The main aim of this proposed book chapter is to exploit algorithms that can provide optimal deployment and path-planning solutions for UAVs based on machine learning (ML) techniques.
Top1. Introduction
The research on Unmanned Aerial Vehicles (UAVs) is significantly growing due to their integral features such as flying and maintaining altitude without the need for any operator, offering promising solutions, and carrying out important tasks cost-effectively without putting human life at risk. UAVs can provide several benefits and a wide range of uses because of their mobility, versatility, and flexibility at different altitudes. As technology develops, the scope of UAV use cases grows (Aslan et al., 2022; Daud et al., 2022). UAVs have widespread uses in military operations, enemy identification, anti-poaching initiatives, border control, and marine surveillance (Hassija et al., 2020). Due to their portability, speed, and ability to operate in hazardous environments, UAVs play an important role in disaster management. With their help, rescue personnel are better equipped to do recovery operations and evaluate harm more quickly. UAVs also play a significant role in disaster preparation by aiding in the dissemination of vital supplies, easing speedy rescue operations, and delivering early warning signals. The role of UAVs in precision agriculture is transformative. By collecting data from ground sensors, spraying pesticides, detecting diseases, scheduling irrigation, and monitoring crop health, UAVs enhance productivity, crop yields, and overall profitability in farming systems. This technology optimizes agricultural practices and provides data-driven insights for smart decision-making (Macrina et al., 2020). Moreover, UAVs are actively integrated into road traffic monitoring systems. They play a crucial role in automating transportation operations, monitoring road conditions, and providing real-time assistance during accidents or traffic management scenarios. Law enforcement agencies utilize UAVs to track suspect vehicles, enforce traffic rules, and enhance road safety. UAV research is rapidly growing, driven by technological advancements and an expanding range of applications.
The use of UAVs to support conventional communication networks is the subject of cutting-edge study. UAVs equipped with communication interfaces, provide promising solutions for monitoring, inspecting, and delivering goods. UAVs can be used in 5G and beyond communication. More specifically, UAVs have been found highly beneficial in remote areas that are unreachable by humans due to their mobility and ease of deployment (Elnabty et al., 2022). The integration of UAV technology into next-generation communication highly depends on various emerging technologies such as Computer Vision (CV), Machine Learning (ML), Deep Learning (DL) (Mandloi et al.), Artificial Intelligence (AI), and Mobile-Edge Computing (MEC) (Khan et al., 2022b; Yagnasree & Jain, 2022). UAVs can be used as Aerial Base Stations (ABS) to significantly enhance communication coverage because of their flexible deployment, low cost, and high chance of line-of-sight (LoS) communication with ground users to improve wireless connectivity and coverage (Hoseini et al., 2021; Rolly et al., 2022). UAVs can also be used for data collection purposes from Internet-of-Things (IoT) nodes without installing costly infrastructures for data collection to enable a smart decision-making process (Lyu & Zhang, 2019). However, certain challenges are associated with UAVs, such as path planning, mission planning, optimal deployment, decision-making, collision avoidance, security, energy management, etc (Mozaffari et al., 2019; Shakhatreh et al., 2019). For instance, in path planning, if the trajectories of UAVs are not optimized, longer flight time may be required to reach a given target position. If proper mission planning is not done, more resources may be consumed. Energy management is one of the important issues of UAVs because they have limited power resources which can limit flight time. Traditionally, UAVs were operated manually through a high-level controller, and human resources were required. Recently, intelligence has been added to UAVs, such as preplanned or built-in controlled algorithms used for decision-making or autonomously completing the mission and making decisions based on environmental changes like reinforcement learning. In autonomous UAVs, decision-making is one of the major issues in different scenarios such as environmental conditions, bad weather, and rain situations. UAVs have security issues as well because they can be subject to attack by malicious UAVs or GPS spoofing. However, in this work, our main focus is to explore path planning and optimal deployment of UAVs.