Theses and Dissertations from UMD
Permanent URI for this communityhttp://hdl.handle.net/1903/2
New submissions to the thesis/dissertation collections are added automatically as they are received from the Graduate School. Currently, the Graduate School deposits all theses and dissertations from a given semester after the official graduation date. This means that there may be up to a 4 month delay in the appearance of a give thesis/dissertation in DRUM
More information is available at Theses and Dissertations at University of Maryland Libraries.
Browse
3 results
Search Results
Item Expanding Constrained Kinodynamic Path Planning Solutions through Recurrent Neural Networks(2019) Shaffer, Joshua Allen; Xu, Huan; Aerospace Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Path planning for autonomous systems with the inclusion of environment and kinematic/dynamic constraints encompasses a broad range of methodologies, often providing trade-offs between computation speed and variety/types of constraints satisfied. Therefore, an approach that can incorporate full kinematics/dynamics and environment constraints alongside greater computation speeds is of great interest. This thesis explores a methodology for using a slower-speed, robust kinematic/dynamic path planner for generating state path solutions, from which a recurrent neural network is trained upon. This path planning recurrent neural network is then used to generate state paths that a path-tracking controller can follow, trending the desired optimal solution. Improvements are made to the use of a kinodynamic rapidly-exploring random tree and a whole-path reinforcement training scheme for use in the methodology. Applications to 3 scenarios, including obstacle avoidance with 2D dynamics, 10-agent synchronized rendezvous with 2D dynamics, and a fully actuated double pendulum, illustrate the desired performance of the methodology while also pointing out the need for stronger training and amounts of training data. Last, a bounded set propagation algorithm is improved to provide the initial steps for formally verifying state paths produced by the path planning recurrent neural network.Item Seismic Resilience-based Design and Optimization: A Deep Learning and Cyber-Physical Approach(2018) Wu, Jingzhe; Phillips, Brian M.; Civil Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)With the growing acceptance and better understanding of the importance of uncertainties in seismic design, traditional design approaches with deterministic analysis are being replaced with more reliable approaches within a risk-based context. Recently, resilience has been increasingly studied as a comprehensive metric to assess the ability of a system to withstand and recover from disturbances with large uncertainties. For civil infrastructure systems susceptible to natural hazards, especially earthquakes as considered herein, seismic resilience could provide a measurement integrating both earthquake and post-earthquake performance. For structural engineers, improving infrastructure disaster resilience starts with the design of more resilient structures. This requires a quantitative approach to explicitly guild the design towards better resilience. However, when attempting to quantify the seismic resilience of a structure, large uncertainties lead to large computational costs associated with risk-based approaches. Additionally, the accuracy of numerical simulations under wide range of design scenarios is unknown. To address these challenges, this dissertation investigates the role of seismic resilience in structural design. This dissertation starts with a novel seismic protective device to improve structural resilience and follows with the development of a quantitative and efficient design, evaluation, and optimization framework for seismic resilience. This framework proposes metamodeling through deep neural networks for improved efficiency and cyber-physical systems for improved accuracy. Feedforward neural networks are adopted for fragility metamodeling, while online learning long-short term memory neural networks are developed for structural component metamodeling. Real-time hybrid simulation is used for the construction of cyber-physical systems. The proposed framework is demonstrated to have both improved accuracy and significantly reduced computational/experimental cost when compared to existing approaches. The applicability of the framework is illustrated through the optimization of structural systems for improved seismic resilience.Item LARGE-SCALE NEURAL NETWORK MODELING: FROM NEURONAL MICROCIRCUITS TO WHOLE-BRAIN COMPLEX NETWORK DYNAMICS(2018) Liu, Qin; Anlage, Steven; Horwitz, Barry; Physics; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Neural networks mediate human cognitive functions, such as sensory processing, memory, attention, etc. Computational modeling has been proved as a powerful tool to test hypothesis of network mechanisms underlying cognitive functions, and to understand better human neuroimaging data. The dissertation presents a large-scale neural network modeling study of human brain visual/auditory processing and how this process interacts with memory and attention. We first modeled visual and auditory objects processing and short-term memory with local microcircuits and a large-scale recurrent network. We proposed a biologically realistic network implementation of storing multiple items in short-term memory. We then realized the effect that people involuntarily switch attention to salient distractors and are difficult to distract when attending to salient stimuli, by incorporating exogenous and endogenous attention modules. The integrated model could perform a number of cognitive tasks utilizing different cognitive functions by only changing a task-specification parameter. Based on the performance and simulated imaging results of these tasks, we proposed hypothesis for the neural mechanism beneath several important phenomena, which may be tested experimentally in the future. Theory of complex network has been applied in the analysis of neuroimaging data, as it provides a topological abstraction of the human brain. We constructed functional connectivity networks for various simulated experimental conditions. A number of important network properties were studied, including the scale-free property, the global efficiency, modular structure, and explored their relations with task complexity. We showed that these network properties and their dynamics of our simulated networks matched empirical studies, which verifies the validity and importance of our modeling work in testing neural network hypothesis.