Amidst the swift progress in unmanned aerial vehicle (UAV) technology, the enhancement of navigation precision and robustness is paramount for ensuring flight safety and managing the intricacies of various missions. T...
详细信息
Given the pressing demand for comprehensive environmental monitoring, unmanned Aerial Vehicles (UAVs) or drones have been extensively applied in environmental monitoring studies to address data collection and operatio...
详细信息
ISBN:
(纸本)9798350390797;9789532901351
Given the pressing demand for comprehensive environmental monitoring, unmanned Aerial Vehicles (UAVs) or drones have been extensively applied in environmental monitoring studies to address data collection and operations management thanks to their operational flexibility and low cost. The objective of the project MARIN is to set-up and test at sea a technological demonstrator of the enabling technologies for autonomous navigation. Integrating the UAVs with their video- analysis systems can enhance the role of the naval unit as an extended robotic platform that can enlarge the range and the operational capability of the unit itself. The goal of this study is to demonstrate the technological feasibility of an unmanned system for environmental monitoring and to develop an integrated unmanned system for the collection and analysis of environmental data for remote management using UAVs. This paper summarizes the work's progress and technical innovations, highlighting the significant technical challenges that the project has overcome. The validation of the system, carried out with in situ tests, confirmed its effectiveness and flexibility in various environmental scenarios and opens up new possibilities for environmental monitoring and sustainable management of natural resources, demonstrating the importance of technological innovation in this crucial sector and others.
Urban Air Mobility (UAM) includes new aeronautical applications encompassing the future on-demand urban human air transportation (e.g. air-taxi) and unmanned aerial system operations for goods delivery and public safe...
详细信息
Autonomous unmanned Aerial Vehicles (UAVs) have become essential tools in defense, law enforcement, disaster response, and product delivery. These autonomous navigationsystems require a wireless communication network...
详细信息
ISBN:
(纸本)9798350354102;9798350354096
Autonomous unmanned Aerial Vehicles (UAVs) have become essential tools in defense, law enforcement, disaster response, and product delivery. These autonomous navigationsystems require a wireless communication network, and of late are deep learning based. In critical scenarios such as border protection or disaster response, ensuring the secure navigation of autonomous UAVs is paramount. But, these autonomous UAVs are susceptible to adversarial attacks through the communication network or the deep learning models - eavesdropping / man-in-the-middle / membership inference / reconstruction. To address this susceptibility, we propose an innovative approach that combines Reinforcement Learning (RL) and Fully Homomorphic Encryption (FHE) for secure autonomous UAV navigation. This end-to-end secure framework is designed for real-time video feeds captured by UAV cameras and utilizes FHE to perform inference on encrypted input images. While FHE allows computations on encrypted data, certain computational operators are yet to be implemented. Convolutional neural networks, fully connected neural networks, activation functions and OpenAI Gym Library are meticulously adapted to the FHE domain to enable encrypted data processing. We demonstrate the efficacy of our proposed approach through extensive experimentation. Our proposed approach ensures security and privacy in autonomous UAV navigation with negligible loss in performance.
Marine robots, particularly unmanned Surface Vessels (USVs), have gained considerable attention for their diverse applications in maritime tasks, including search and rescue, environmental monitoring, and maritime sec...
详细信息
ISBN:
(纸本)9798350342291
Marine robots, particularly unmanned Surface Vessels (USVs), have gained considerable attention for their diverse applications in maritime tasks, including search and rescue, environmental monitoring, and maritime security. This paper presents the design and implementation of a USV named marineX. The hardware components of marineX are meticulously developed to ensure robustness, efficiency, and adaptability to varying environmental conditions. Furthermore, the integration of a vision-based object tracking algorithm empowers marineX to autonomously track and monitor specific objects on the water surface. The control system utilizes PID control, enabling precise navigation of marineX while maintaining a desired course and distance to the target object. To assess the performance of marineX, comprehensive testing is conducted, encompassing simulation, trials in the marine pool, and real-world tests in the open sea. The successful outcomes of these tests demonstrate the USV's capabilities in achieving real-time object tracking, showcasing its potential for various applications in maritime operations.
Recent advancements in unmanned Aerial Vehicles (UAV) navigationsystems are bringing the goal of fully autonomous missions closer. The development of safe navigation methods is a critical component in reaching this g...
详细信息
The traditional receiver autonomous integrity monitoring (RAIM) algorithm is used to detect the pseudorange estimation residuals of a single aircraft. For the relatively small and medium-sized pseudorange errors, RAIM...
详细信息
unmanned Aerial Vehicles (UAV) are highly versatile systems with applications expanding in various fields, for instance, Surveillance, Reconnaissance, Disaster Response, Agriculture, and many more. Although UAVs have ...
详细信息
The Flying Robot Trial League (FRTL), from RoboCup Brazil, is a competition that stimulates the development of autonomous and intelligent flying robots for inspection and operation in pipeline lanes and oil installati...
详细信息
ISBN:
(纸本)9798350310375
The Flying Robot Trial League (FRTL), from RoboCup Brazil, is a competition that stimulates the development of autonomous and intelligent flying robots for inspection and operation in pipeline lanes and oil installations. In this context, this work presents the system developed by the BDP-UaiFly Team for the 2022 competition, using the off-the-shelf Parrot Bebop 2 to execute the Equipment Transport phase. This paper presents in detail the system platform and the navigation and sensing strategies implemented for autonomous navigation and image processing. In particular, the strategy adopted for cargo transportation based on servo-visual control is presented. Practical experiments validate the proposed solutions for the phases of the challenge.
Spatial mapping creates a 3D reconstruction of a visualised area to reproduce a perception of the environment. This can be applied in robotics for manoeuvring in environments where Global navigation Satellite systems ...
详细信息
ISBN:
(纸本)9798350310375
Spatial mapping creates a 3D reconstruction of a visualised area to reproduce a perception of the environment. This can be applied in robotics for manoeuvring in environments where Global navigation Satellite systems (GNSSs) are inaccessible. Such devices capable of spatial mapping are stereo-vision cameras. These cameras possess two or more image sensors, simulating human binocular vision and giving it the ability to perceive depth. Using this hardware on an unmanned Aircraft System (UAS) introduces new capabilities for autonomous navigation and unmannedcontrol. This, in turn, introduces new possibilities for application. Such a use case would be for a General Visual Inspection (GVI) of aircraft in a hangar environment where access to GNSS is limited. Providing a flight plan to a UAS with a stereo-vision camera to assist with collision avoidance and to keep a consistent distance from the aircraft would provide a robust system for defect detection and localisation during a GVI.
暂无评论