Abstract
Fully autonomous aerial systems (FAAS) combine edge and cloud hardware with UAVs and considerable software support to create self-governing systems. FAAS complete complicated missions with no human piloting by sensing and responding to their environment in real-time. FAAS require highly complex designs to function properly, including layers of on-board, edge, and cloud hardware and software. FAAS also necessitate complex software used for controlling low-level UAV actions, data collection and management, image processing, machine learning, mission planning, and high-level decision-making which must integrate across the compute hierarchy effectively to meet autonomy goals in real-time. The complexity of even a relatively simple FAAS makes efficiency difficult to guarantee. Efficiency, however, is paramount to the effectiveness of a FAAS. FAAS perform missions in resource-scarce environments like natural disaster areas, crop fields, and remote infrastructure installations. These areas have limited access to computational resources, network connectivity, and power. Furthermore, UAV battery lives are short, with flight times rarely exceeding 30 minutes. If FAAS are inefficiently designed, UAV may waste precious battery life awaiting further instructions from remote compute resources, delaying or precluding mission completion. For this reason, it is imperative that FAAS designers carefully choose or design edge hardware configurations, machine learning models, autonomy policies, and deployment models. ii FAAS have the capability to revolutionize a number of industries, but much research must be done to facilitate their usability and effectiveness. In this dissertation, I outline my efforts toward designing and implementing FAAS that are efficient and effective. This dissertation will focus on the following five topics encompassing design, implementation, and applications of FAAS: §1. Creation of new general and domain-specific machine learning algorithms and careful utilization of others §2. Selection of hardware at all levels in the FAAS hierarchy §3. Power and environmental awareness informing selection and switching of autonomy policies, hardware devices, machine learning techniques and deployment characteristics. §4. Online learning capabilities resilient to limited cloud access, network interruption, and power scarcity. §5. Thorough applications which demonstrate the technological value of FAAS, drive adoption, and determine future research challenges.
ABSTRACT
This study was conducted to find out the social factors affecting effective teaching and learning in senior sec...
ABSTRACT
The nutritional status of children under five years is an indicator of nutritional situation in society. Research estimates that...
ABSTRACT
User satisfaction with residential houses generally is tied to many variables, but this research aims at examining user satisfac...
ABSTRACT
The study investigated the effects of physical distribution on sales of cons...
ABSTRACT
The study is aimed at analyzing the students view about the introduction of sex education into the secondary sc...
THE IMPACT OF PUBLIC SECTOR REFORMS ON GOVERNMENTAL ACCOUNTING PRACTICES
Abstract
This study investigates the effects of public...
THE ROLE OF BUDGETING IN PROJECT MANAGEMENT
The objectives of this research are to: (1) investigate the role of budgeting in project mana...
BACKGROUND OF THE STUDY
In today's culture, both the teaching of and the study of the English language are considere...
Statement of Problem
Manual office systems always put pressure on people to be correct in all aspect of their wor...
ABSTRACT: This research explores the role of early childhood education in reducing food waste among young children. Educating children about f...