Nandana Manoj’s Post

📃Scientific paper: Energy-Efficient UAV Swarm Assisted MEC with Dynamic Clustering and Scheduling Abstract: In this paper, the energy-efficient unmanned aerial vehicle (UAV) swarm assisted mobile edge computing (MEC) with dynamic clustering and scheduling is studied. In the considered system model, UAVs are divided into multiple swarms, with each swarm consisting of a leader UAV and several follower UAVs to provide computing services to end-users. Unlike existing work, we allow UAVs to dynamically cluster into different swarms, i.e., each follower UAV can change its leader based on the time-varying spatial positions, updated application placement, etc. in a dynamic manner. Meanwhile, UAVs are required to dynamically schedule their energy replenishment, application placement, trajectory planning and task delegation. With the aim of maximizing the long-term energy efficiency of the UAV swarm assisted MEC system, a joint optimization problem of dynamic clustering and scheduling is formulated. Taking into account the underlying cooperation and competition among intelligent UAVs, we further reformulate this optimization problem as a combination of a series of strongly coupled multi-agent stochastic games, and then propose a novel reinforcement learning-based UAV swarm dynamic coordination (RLDC) algorithm for obtaining the equilibrium. Simulations are conducted to evaluate the performance of the RLDC algorithm and demonstrate its superiority over counterparts. Continued on ES/IODE ➡️ https://etcse.fr/NQa ------- If you find this interesting, feel free to follow, comment and share. We need your help to enhance our visibility, so that our platform continues to serve you.

✨Highlights for this #Hot Article 1. The proposed Hull Drone Indoor Navigation (HDIN) dataset collected segmented indoor scenes along with identical labels based on the common Parrot AR. Drone platform, which aims to enrich the public limited UAV datasets and improve the performance of UAV indoor autonomous navigation. 2. The HDIN dataset comprises common indoor corridors' scenes (such as long straight hallways, L-shaped corners, and S-shaped corners), and includes consistent steering and collision labels for multi-task supervised learning. 3. According to the evaluation and comparison between the real-world outdoor self-driving dataset, the simple collection methodology without bespoke sensor installation proved that our HDIN dataset is valid or training visual-based UAV autonomous navigation networks. 🗞️The HDIN Dataset: A Real-World Indoor #UAV Dataset with Multi-Task Labels for #Visual-Based #Navigation 👨🏫 by Yingxiu Chang, Yongqiang Cheng, John Murray, Shi Huang, and Guangyi Shi 👉https://lnkd.in/gpV_X56j

Revolutionizing Public Safety: Acoustic Vector Sensor for UAV Detection The project focuses on the development of an Acoustic Vector Sensor (AVS) system for the detection and localization of Unmanned Aerial Vehicles (UAVs). It begins with the research and design of a signal simulator, followed by the construction of a real AVS system. Specialized algorithms are then created for real-time UAV detection, utilizing a large dataset generated under diverse signal conditions. A Convolutional Recurrent Neural Network (CRNN) is employed for UAV detection, achieving an impressive accuracy rate of 95%, even under challenging conditions. The project also emphasizes dataset quality enhancement through preprocessing techniques like bandpass and adaptive filtering. A novel method for UAV localization is introduced, using phase differences from multiple sensors to calculate the arctangent for precise source location estimation. Key technical achievements include the integration of additional sensors for azimuth, elevation, and range estimation in the AVS system. The spiking deconvolution algorithm is also utilized to improve the accuracy of time delay estimation between acoustic signals. The project is socially significant, addressing UAV detection challenges and contributing to public safety and security. Looking ahead, the project involves planned field experiments and extensive testing to validate the AVS system's real-world performance. The project team has already published research in the 2023 IEEE International Symposium on Smart Electronic Systems, showcasing the CRNN-based UAV detection approach. A patent for the newly developed AVS system is being prepared under the filing, highlighting the innovative contributions to acoustic sensing technology. #jiitnoida #JIIT #jaypee #Acoustic_Vector_Sensor #AVS #Unmanned_Aerial_Vehicles

Release of Benchmark Dataset for UAV Positioning with UWB Sensors! In 2020, we at the AUSM Lab, under supervision of professor Gunho Sohn embarked on a journey to address a critical need in the realm of Unmanned Aerial Vehicle (UAV) positioning. Today, I am thrilled to announce the release of a benchmark dataset aimed at revolutionizing the development and testing of positioning methods utilizing Ultra-wideband (UWB) sensors. Why UWB? Precise positioning of UAVs is paramount for executing sophisticated civil and military applications in challenging environments. While state-of-the-art methods often rely on active range sensors, UWB emerges as a game-changer. Offering high precision, power efficiency, and immunity to multipath propagation and noise, UWB has garnered significant interest in the research community as a complementary positioning sensor. Closing the Gap: UWB Benchmark Dataset Despite the growing interest in UWB, there has been a glaring lack of benchmark data for researchers and developers to refine their positioning methods. To bridge this gap, I am proud to present a unique benchmark dataset, featuring UWB and IMU signals collected by a Q-Drone system across diverse environments. From indoor spaces to open fields, close to buildings, underneath bridges, and semi-open tunnels, this dataset provides a comprehensive testbed. What's Included? This benchmark dataset not only includes UWB and IMU signals but also offers ground truth UAV positions independently measured with robotic total stations. This holistic approach ensures researchers have a reliable reference point to validate and enhance their UWB-based positioning methods. Learn More For more in-depth information, you can refer to the publication detailing the dataset. Access the publication here: https://lnkd.in/dgBtYXkR Access the Dataset To empower the research community, our benchmark dataset is now publicly available. You can explore, experiment, and contribute to advancing UAV positioning methodologies. Visit [https://lnkd.in/dqxMBHKY] to access this invaluable resource and take your UWB-based positioning research to new heights! Global Impact I am delighted to share that the dataset has been downloaded extensively worldwide, and researchers are actively utilizing it to drive innovation in UAV positioning technology. Join this global movement and be part of the future of UWB-enabled UAV applications! #UAVPositioning #UWBTechnology #BenchmarkDataset #DroneTechnology #SpatialIntelligence  

✨Highlights for this #Hot Article (1) The effects of these parameters on dynamic gliding trajectories and energy acquisition were explored in terms of UAV mass, initial velocity, and initial angle of incision; (2) It was found that an increase in UAV weight favours energy harvesting from the wind and does not change the trajectory profile, both in that an increase in UAV load does not change the intended energy harvesting trajectory; (3) It was found that there exists an optimal speed for the UAV to begin dynamic gliding that maximizes the efficiency of energy acquisition; (4) It is found that the angle between the UAV and the wind at the start of dynamic gliding has a significant effect on the trajectory and energy acquisition and that the best flight strategy for the UAV is to start dynamic gliding by climbing against the wind;   🗞️Dynamic Soaring Parameters Influence Regularity Analysis on #UAV and Soaring Strategy Design 👨🏫by Wei Wang, Weigang An and Bifeng Song 👉 https://lnkd.in/g7N2SRna

🚁🌐🔍 Butterfly effect in action! 🦋 Researchers unveil a groundbreaking UAV path-planning algorithm inspired by butterfly behavior, optimizing navigation in 3D spaces. This tech promises enhanced efficiency and safety for UAV applications in rescue, surveillance, and agriculture. https://lnkd.in/g_B4NtVJ #UAV #Innovation #AI #Technology #Navigation #ButterflyAlgorithm #Robotics #Engineering #Optimization #FutureTech Nature Portfolio

We are thrilled to spotlight Dr. Richard Millar as one of the distinguished recipients of the 2024 Technology Maturation Awards at the GW Technology Commercialization Office. This award highlights projects that demonstrate significant potential for commercial application and societal impact through proof-of-concept, prototyping, technology development, and/or scale-up work.   Dr. Millar’s proposal assesses the feasibility and potential of a novel concept: the operation of multiple unmanned vehicles (UAV) commanded and supported by a manned “Tender” air vehicle carrying a pilot and flight manager. The "Tender" is equipped to monitor and manage multiple diverse UAVs over otherwise inaccessible terrain through wireless communication flexibly and economically.   There is commercial interest in deploying UAVs to analyze forest topography to help estimate future harvesting costs and yields, but this effort is limited by government restrictions on UAV overflight restrictions, which require direct visual human surveillance and control of UAV operations. Suppose a manned aircraft provides the visual oversight function, essentially overseeing multiple UAVs from a manned “Tender” vehicle, managing, and reporting the status of all UAVs operating beyond ground access. In that case, this will be a useful and viable option. This award will allow Dr. Millar’s team to personally test, refine, and perfect the technology in the field.   Read more about the technology: https://lnkd.in/dbfnYq7V   Congratulations to Dr. Millar and the team for this well-deserved recognition! We are excited to see how this project will further develop and see its impact on aerial fleet operations. Your hard work and dedication to pushing the boundaries of technology continue to inspire us all. Here's to more innovation and success in your journey ahead! #gwu #gwtco #TMA #UAV #gwseas #Innovation #AerialTechnology #ResearchAndDevelopment #DroneTechnology The George Washington University The George Washington University - School of Engineering & Applied Science

Team Aereo is always soaring to new heights! 🎉 We are delighted to share that Hormazd Doctor, Aereo’s distinguished UAV quality control expert, will be leading an exclusive webinar hosted by the World Zarathushti Chamber of Commerce (WZCC). Around here, we call him Doctor, and it's easy to see why. With over four years in the UAV game and a B.E. in Electronics & Communication, he's renowned for his meticulous attention to detail and unwavering commitment to quality. He’s our go-to expert, ensuring every drone is top-notch by expertly inspecting batteries, motors, and all the crucial subsystems. When it comes to maintaining the highest standards, he's got it covered. 🙌  In this webinar, Hormazd will offer invaluable insights into the world of UAV technology, including: 𝐇𝐢𝐬𝐭𝐨𝐫𝐢𝐜𝐚𝐥 𝐏𝐞𝐫𝐬𝐩𝐞𝐜𝐭𝐢𝐯𝐞: A journey through the evolution of UAVs. 𝐓𝐞𝐜𝐡𝐧𝐢𝐜𝐚𝐥 𝐁𝐫𝐞𝐚𝐤𝐝𝐨𝐰𝐧: An examination of the subsystems that are the heartbeat of UAV functionality. 𝐈𝐧𝐝𝐮𝐬𝐭𝐫𝐲 𝐈𝐦𝐩𝐚𝐜𝐭: A discussion on how UAVs are revolutionizing various sectors. 𝐂𝐚𝐫𝐞𝐞𝐫 𝐎𝐩𝐩𝐨𝐫𝐭𝐮𝐧𝐢𝐭𝐢𝐞𝐬: An overview of the burgeoning career prospects in the UAV domain. At #Aereo, we’re proud of our team’s role in driving awareness, innovation, and growth within the drone technology ecosystem. Hormazd’s participation reflects our culture of innovation and our role as thought leaders in the #UAV community. Kudos to Hormazd! Let’s navigate the skies together. 🚀 #DroneTechnology #Webinar #WZCC #Innovation

🚀 Excited to share that my first paper has been published! 📝 Delving into the fascinating realm of Unmanned Aerial Vehicles (UAVs) and Machine Learning, our paper explores the intricacies of "Optimized Route Planning and Precise Circle Detection in UAVs with Machine Learning." 🛸 In this research, we tackle the challenge of optimizing route planning for UAVs while incorporating precise circle detection using advanced machine learning techniques. Our findings shed light on innovative methodologies to enhance UAV operations, paving the way for more efficient and reliable aerial missions. 🎯 I'm incredibly grateful to my co-authors and mentors for their invaluable support throughout this journey. This milestone marks the beginning of an exciting exploration into the intersection of UAVs, Machine Learning, and optimization. 🌐 I invite you to dive into our paper and join the conversation as we continue to push the boundaries of technology and innovation in the field of aerial robotics. Let's soar to new heights together! 🚁💡 #UAV #MachineLearning #Research #Innovation #Optimization

𝐎𝐩𝐭𝐢𝐦𝐢𝐳𝐢𝐧𝐠 𝐃𝐫𝐨𝐧𝐞 𝐅𝐥𝐢𝐠𝐡𝐭 𝐏𝐞𝐫𝐟𝐨𝐫𝐦𝐚𝐧𝐜𝐞 𝐰𝐢𝐭𝐡 𝐏𝐨𝐥𝐲𝐧𝐨𝐦𝐢𝐚𝐥 𝐓𝐫𝐚𝐣𝐞𝐜𝐭𝐨𝐫𝐲 𝐏𝐥𝐚𝐧𝐧𝐢𝐧𝐠 The defense industry is constantly seeking innovative methods to enhance the efficiency and precision of autonomous systems. Polynomial trajectory generation, specifically minimum snap trajectories, plays a crucial role in ensuring smooth and efficient paths for unmanned aerial vehicles (UAVs). This technique minimizes higher-order derivatives of position, enabling UAVs to perform high-speed maneuvers while maintaining stability and reducing mechanical stress. In defense applications, optimizing UAV trajectories can significantly improve mission success rates. For instance, in urban environments or dense forests, UAVs must navigate tight spaces and avoid obstacles while maintaining stable flight. Polynomial trajectory planning allows for the computation of smooth paths that adhere to the vehicle's dynamic constraints, ensuring minimal mechanical stress and energy consumption. By generating minimum snap trajectories, UAVs can execute intricate maneuvers with high precision, essential for tasks requiring stealth and agility. My recent project focused on developing a minimum snap trajectory planner for quadcopters using a seventh-order polynomial approach. This project involved creating a series of waypoints and using polynomial functions to interpolate these points, ensuring the trajectory was smooth and continuous. The system integrated advanced pathfinding algorithms, such as A*, to determine the optimal sequence of waypoints, and then applied polynomial interpolation to generate the final trajectory. This approach directly addressed the challenges of creating efficient and precise flight paths for UAVs, making it highly relevant to current defense technology needs. You can explore the details of my trajectory planning solution on my GitHub repository. #DefenseTech #UAV #TrajectoryPlanning #Innovation #AutonomousSystems #Engineering #Technology #PolynomialTrajectories