NOC Innovations’ Post

Using video from an advanced ROV, scientists have spotted thousands of Port Jackson sharks blanketing the seafloor in Bass Strait’s Beagle Marine Park \>\> 🔗 https://hubs.ly/Q02LxPn00 🦈 Dr Jacquomo Monk of IMAS, the voyage leader, said, “We had been hoping to see the sharks again on this survey. Coming upon them twice in a 3000-square-kilometer park is like finding a needle in a haystack. It was very exciting when we managed to traverse over a rise in the reef to get a glimpse of the sharks snoozing 65-metres below the vessel in almost the same location as they were six years ago. “A spectacular scene was relayed to us by a remotely operated vehicle equipped with seven cameras that was custom built by Boxfish Robotics in collaboration with IMAS. There were thousands of sharks tightly packed like a carpet spread across the seafloor.” 👏 ➡️ Visit the Ocean Science & Technology website for further information. @[ NESP Marine and Coastal Hub](urn:li:organization:74921525); @[Boxfish Robotics](urn:li:organization:10803666) \#subsea \#environment \#robotics \#ocean \#unmanned

📃Scientific paper: Improving a Verified Flight Plan Generator: New Properties and Code Modifications Abstract: Paparazzi UAV (HBG14) is an open-source autopilot for unmanned aerial vehicles. The Paparazzi suite allows users to create missions expressed in a high-level FPL language and generate executable C code corresponding to that mission, while providing hardware and software solutions to implement those missions. As the generator plays a critical role in that process, a Verified Flight Plan Generator (PGH + 23) is being developed at ISAE-Supaero. This generator embedded formal proof of its correctness and other properties of the generated code. In this paper, we will present some demonstrations that were added to the generator and highlight some modifications that had to be implemented. Continued on ES/IODE ➡️ https://etcse.fr/pI7 ------- 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.

Almost twins Under development by blueflite, Slate and Cobalt are a pair of uncrewed, tiltrotor cargo vehicles with payload capacities of 2-5 kg, ranges from 20-90 miles and potential speeds of up to the 100 mph limit for UAVs in their weight class. The company’s CEO, Frank Noppel, says the UAVs are variants of a common platform with different propulsion and lift systems. Both have four pairs of propellers on tilting mounts that allow for thrust vectoring, but while Slate has wings to give it more range and speed, the wingless Cobalt boasts a larger payload and better hover performance. blueflite has facilities in Michigan and New York State. An entrepreneur by inclination, Noppel has a passion for aerospace, backed up by bachelor’s and master’s degrees in engineering from Karlsruhe University of Applied Sciences, and a PhD in aerospace and aeronautical engineering from Cranfield University. His resume includes full-time posts with Airbus and Rolls-Royce. His first start-up was Ambeo, a UK-based air-taxi operator, formed in 2008. Ambeo flew Citation Mustang very light jets between airfields around Europe up until the company’s dissolution in 2013. The idea that became blueflite dates back to 2017, when Noppel was working for McKinsey and Company, a global management consulting firm. “I was looking for an opportunity and, based on previous experience, there were two ingredients that I thought essential,” he says. “One is passion; setting up a company and making it work is a marathon that can go on for years. The other is high growth potential. I’m passionate about aerospace and robotics, so I was looking at the drone space, but it was when I considered the logistics angle that it clicked.” Read more ➡ https://lnkd.in/eGcJyHGk #uncrewedsystemstechnology #UAV #autonomoussystems #cargovehicles

I am delighted to share that our article presented at the CoDIT 2023 conference, titled "Dynamic Reward in DQN for Autonomous Navigation of UAVs Using Object Detection" has now been officially published in IEEE Xplore. Abstract: This paper discusses the implementation of a Deep Reinforcement Learning policy, based on DQN, which optimizes the navigation of the UAV to the front of wind turbine blades. The UAV was trained in simulation using Unreal Engine V4.27 coupled with AirSim. The action space of the UAV was discretized while allowing 6 different actions to be executed. A Yolov5 network trained with images of simulated wind turbines was used for detection and tracking, providing the DQN policy with state information, upon which it has been trained. In addition to this, the dynamic reward has been implemented, which combined both navigation and inspection objectives in the final evaluation of actions. Our tests showed that after 7500 time steps the exploration rate reached near 0, the mean length of the episodes increased from 10 down to 30, but the mean reward increased from around -60 to stabilizing the output at 26. These results suggest that the proposed method is a promising solution to optimizing the autonomous inspection of wind turbines with UAVs. #Research #IEEE #UAVNavigation #ObjectDetection #DRL #DQN You can access the full article here:

Completing the 27-hour Applied Control Systems 3: UAV drone (3D Dynamics & Control) course has been a wonderful delight. This course aligns with my thesis, which is about Validation Study on Quaternion-Based Control of Quadrotors Using Motion Capture Feedback. The course covers a comprehensive understanding of the quadcopter's control strategy using linear parameter varying model predictive control (LPV-MPC). Nonetheless, the mathematical model employing the Euler-Newton technique and the Euler rotation matrix is used in this course.

Check our recent publication in IEEE Transactions on Field Robotics targets applications for field deployment of marine robots in environments that require the vehicle to quickly react to changes in its surroundings. The paper presented field demonstrations of a UUV operating autonomously at an industrial-scale fish farm while being able to secure collision-free motion through a challenging and constantly changing environment. H.B. Amundsen, M. Føre, S.J. Ohrem, B. Haugaløkken and E. Kelasidi, “Three-dimensional collision avoidance and path planning for unmanned underwater vehicles using elastic bands”, IEEE Transactions on Field Robotics, 2024 Herman Biørn Amundsen, Martin Føre, Sveinung Johan Ohrem, Bent Oddvar Arnesen Haugaløkken, Eleni Kelasidi, Norges forskningsråd, SINTEF Ocean, Norwegian University of Science and Technology (NTNU)

How does learning to fly drones equate to life skills and a future career? In COMPTON UNIFIED SCHOOL DISTRICT, the scholars are finding out. Watch the video and you'll find out, too! #learning #Education #STEM #STEAM

Want to find out more regarding the "Applications of Digital Twins in UAVs" ? Have a look at our latest publication with Nikos Vitzilaios from USC Unmanned Systems & Robotics Lab and George Arampatzis, now available on IEEE Xplore.

🚀 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

"Uniting minds, uplifting ideas! Dr. NGP Institute of Technology became a hub of aerial brilliance as the #LiftOffWorkshop collaboration unfolded, proving that when minds collaborate, the sky's the limit in the world of drone technology." LiftOff, Drone Fabrication and Development workshop was split in 4 phases and went on for a span of 4 days, Various phases involved, 1. Physics behind UAV and UAS 2. Drone Assembly and Fabrication 3. Drone Programming and Calibration 4. Drone Simulation and Real World Flying #DronePilotTraining #DronePhysics #AerospaceEngineering #DroneAssembly #LiftOff #SpaceChase