Autonomous Navigation for eVTOL: Review and Future Perspectives

IEEE Transactions on Intelligent Vehicles, Journal Year: 2024, Volume and Issue: 9(2), P. 4145 - 4171

Published: Jan. 11, 2024

This survey paper explores the emergent domain of electric vertical takeoff and landing vehicles (eVTOLs), emphasizing critical role autonomous navigation capabilities essential for their effective integration operation in complex urban environments. Pioneering this review is introduction a novel six-level autonomy concept eVTOLs, categorizing them based on degree intelligence. The offers comprehensive state-of-the-art developments that together fortify functionality with special focus enhanced perception, intelligent planning, advanced control. Perception technologies empower eVTOLs environmental awareness crucial navigating intricate airspace, while planning algorithms navigate paths through densely populated skies, ensuring optimal routing safety. Control strategies are developed ability to endow these stability agility needed execute flight dynamics. synthesis elements forms backbone outlining clear direction future eVTOL research. can serve as vital resource enhancing steering towards where they integrate effortlessly into transportation systems.

Language: Английский

---

Monitoring and prediction of the LULC change dynamics using time series remote sensing data with Google Earth Engine

Physics and Chemistry of the Earth Parts A/B/C, Journal Year: 2024, Volume and Issue: 136, P. 103689 - 103689

Published: Aug. 9, 2024

Language: Английский

---

Advanced Deep Learning Models for 6G: Overview, Opportunities and Challenges

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 133245 - 133314

Published: Jan. 1, 2024

The advent of the sixth generation mobile communications (6G) ushers in an era heightened demand for advanced network intelligence to tackle challenges expanding landscape and increasing service demands. Deep Learning (DL), as a crucial technique instilling into 6G, has demonstrated powerful promising development. This paper provides comprehensive overview pivotal role DL exploring myriad opportunities that arise. Firstly, we present detailed vision emphasizing areas such adaptive resource allocation, intelligent management, robust signal processing, ubiquitous edge intelligence, endogenous security. Secondly, this reviews how models leverage their unique learning capabilities solve complex demands 6G. discussed include Convolutional Neural Networks (CNN), Generative Adversarial (GAN), Graph (GNN), Reinforcement (DRL), Transformer, Federated (FL), Meta Learning. Additionally, examine specific each model faces within 6G context. Moreover, delve rapidly evolving field Artificial Intelligence Generated Content (AIGC), examining its development impact framework. Finally, culminates discussion ten critical open problems integrating with setting stage future research field.

Language: Английский

---

Target detection and classification via EfficientDet and CNN over unmanned aerial vehicles

Frontiers in Neurorobotics, Journal Year: 2024, Volume and Issue: 18

Published: Aug. 30, 2024

Advanced traffic monitoring systems face significant challenges in vehicle detection and classification. Conventional methods often require substantial computational resources struggle to adapt diverse data collection methods.

Language: Английский

---

Investigation of Unsafe Construction Site Conditions Using Deep Learning Algorithms Using Unmanned Aerial Vehicles

Sensors, Journal Year: 2024, Volume and Issue: 24(20), P. 6737 - 6737

Published: Oct. 20, 2024

The rapid adoption of Unmanned Aerial Vehicles (UAVs) in the construction industry has revolutionized safety, surveying, quality monitoring, and maintenance assessment. UAVs are increasingly used to prevent accidents caused by falls from heights or being struck falling objects ensuring workers comply with safety protocols. This study focuses on leveraging UAV technology enhance labor monitoring use personal protective equipment, particularly helmets, among workers. developed system utilizes tensorflow technique an alert detect identify not wearing helmets. Employing high-precision, high-speed, widely applicable Faster R-CNN method, can accurately without helmets real-time across various site conditions. proactive approach ensures immediate feedback intervention, significantly reducing risk injuries fatalities. Additionally, implementation minimizes workload supervisors automating inspections allowing for more efficient continuous oversight. experimental results indicate that system's high precision, recall, processing capabilities make it a reliable cost-effective solution improving safety. mAP, FPS 93.1%, 58.45%, 27 FPS. demonstrates potential compliance, protect workers, improve overall management industry.

Language: Английский

---

A RF-Visual Directional Fusion Framework for Precise UAV Positioning

IEEE Internet of Things Journal, Journal Year: 2024, Volume and Issue: 11(22), P. 36736 - 36747

Published: July 15, 2024

Language: Английский

---

Energy‐Efficient Routing Algorithm for Optimizing Network Performance in Underwater Data Transmission Using Gray Wolf Optimization Algorithm

Journal of Sensors, Journal Year: 2024, Volume and Issue: 2024(1)

Published: Jan. 1, 2024

Due to the aquatic nature of communication in underwater world, acoustic sensor network (UASN) is commonly used. However, it has inherent limitations, such as limited bandwidth, high transmission energy, long propagation delays, void regions, and expensive battery replacement. Improving lifetime (NL) primary objective since replacing batteries UWSN very challenging. NL improved by having a packet delivery ratio (PDR), reduced dead nodes, energy consumption (EC). If two more node are depleted, they become causing partitions on resulting region problem. Void regions occur when no forwarder forward data packets toward sink node. nodes affect routing techniques’ overall performance regarding end‐to‐end delay (EED), loss, EC. So, this work avoid regions. For same, paper proposes hole detection algorithm. The algorithm selects best next hop based fitness function calculated gray wolf optimization (GWO) algorithm, considering only vertical directions despite horizontal directions, further reducing EED. proposed approach simulated using MATLAB, evaluation broadcast copies, PDR, EC, number (DNN), average operational time (AOT), NL, presented comparison with weighting depth forwarding area division depth‐based (WDFAD‐DBR) protocol for variance‐based opportunistic avoidance scheme (EDOVS) UASN. WDFAD‐DBR avoids holes selecting taking sum differences hops; comparison, EDOVS considers not parameters but also normalized residual energy. contributes developing an energy‐efficient that removes appropriate GWO increases avoiding balancing simulation results show gains than 20% less 60% broadcasted copies WDFAD‐DBR, 10% PDR lesser were sent along enhanced varying range showing better terms DNN values 61.6, 0.97, 35 (scenario 60 600 m) 64.1, 0.89, 25, respectively, variable size.

Language: Английский

---

Autonomous mission-oriented unmanned underwater vehicle control using directional policy optimization

Ocean Engineering, Journal Year: 2025, Volume and Issue: 320, P. 120242 - 120242

Published: Jan. 7, 2025

Language: Английский

---

KJA: Kookaburra Jellyfish Algorithm Based Task Offloading in UAV‐Enabled Mobile Edge Computing Network

International Journal of Communication Systems, Journal Year: 2025, Volume and Issue: 38(4)

Published: Feb. 10, 2025

ABSTRACT Mobile edge computing (MEC) is extensively utilized for supporting diverse mobile applications and the Internet of Things (IoT). One MEC's prime operations utilizing unmanned aerial vehicles (UAVs) included with MEC servers providing computational aids offloaded tasks by users in temporal hotspot regions or a few emerging situations like sports areas environmental disaster regions. However, despite various merits UAVs executed servers, it constrained their insufficient sensible energy consumption resources. Furthermore, owing to complication UAV‐aided systems, optimizations computation resource cannot be obtained better conventional optimization schemes. In this research, kookaburra jellyfish algorithm (KJA) presented task offloading UAV‐enabled network. The main objective enhance efficiency networks optimizing consumption, resources, communication time using KJA. Initially, network model simulated. Next, performed, thereafter, uploading carried out. Then, KJA consideration multiobjective models, namely, time, cost. Moreover, devised integrating (KOA) search optimizer (JSO). Afterward, process data transmission are conducted. addition, minimum energy, load, 0.448 J, 0.122, 1.036 s.

Language: Английский

---

Computationally Efficient Approach for 6G‐AI‐IoT Network Slicing and Error‐Free Transmission

International Journal of Network Management, Journal Year: 2025, Volume and Issue: 35(2)

Published: Feb. 23, 2025

ABSTRACT Many smart gadgets are connecting to the Internet, and Internet‐of‐Things (IoT) technologies enabling a variety of applications. Artificial intelligence (AI) Things (AIoT) devices anticipated possess human‐like decision‐making, reasoning, perception, other capacities with combination AI IoT. AIoT expected be extensively utilized across several domains, as by 6G networks. With AI's steady advancements in speech recognition, computer vision, natural language processing—not mention its ability analyze large amounts data—semantic communication is now feasible. A new paradigm wireless opened semantic communication, which seeks explore meaning behind bits only transmits information that may used, opposed attaining error‐free transmission. The IoT provides prominent features overcome various important issues cloud computing However, there bottleneck delay precision. Therefore, this paper proposed method problem. First, network slicing feature maps were extracted convolutional neural Next, processing reduced compression. Simulation results show approach makes 99.2% reduction complexity an 80% transmission compared traditional methods. Taking Resnet18 example, running time 0.8% method.

Language: Английский

---