摘要: Uncrewed Aerial Vehicle (UAV) remote and autonomous operation is a growing industry with applications in defense and the commercial space. Operational environments for UAVs such as urban canyons, forested areas, and indoor spaces ... 展开 Uncrewed Aerial Vehicle (UAV) remote and autonomous operation is a growing industry with applications in defense and the commercial space. Operational environments for UAVs such as urban canyons, forested areas, and indoor spaces can deny GPS signals and prevent a receiver from determining a position, which can hinder the vehicle's ability to safely follow flight paths. Unreliable positioning from GPS requires UAVs to have an alternative means of localization, which can be accomplished by utilizing ultra-wideband ranging to landmarks or other aerial systems. Machine learning can be used to train models to utilize unfiltered data from inter-vehicle distance sensors on the agent and anchors to determine the location of the agent without access to GPS. This work explores using machine learning as an adaptable localization system using artificial neural networks and gradient descent. Fully trained artificial neural networks will be an alternate localization method capable of learning specific noise models and performing cooperative localization using unfiltered intervehicle ranges and anchor positions to provide an alternative means of localization on a global scale. 收起