UMD Theses and Dissertations
Permanent URI for this collectionhttp://hdl.handle.net/1903/3
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 given thesis/dissertation in DRUM.
More information is available at Theses and Dissertations at University of Maryland Libraries.
Browse
13 results
Search Results
Item Computational Methods for Natural Walking in Virtual Reality(2024) Williams, Niall; Manocha, Dinesh; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Virtual reality (VR) allow users to feel as though they are really present in a computer-generated virtual environment (VE). A key component of an immersive virtual experience is the ability to interact with the VE, which includes the ability to explore the virtual environment. Exploration of VEs is usually not straightforward since the virtual environment is usually shaped differently than the user's physical environment. This can cause users to walk on virtual routes that correspond to physical routes that are obstructed by unseen physical objects or boundaries of the tracked physical space. In this dissertation, we develop new algorithms to understand how and enable people to explore large VEs using natural walking while incurring fewer collisions physical objects in their surroundings. Our methods leverage concepts of alignment between the physical and virtual spaces, robot motion planning, and statistical models of human visual perception. Through a series of user studies and simulations, we show that our algorithms enable users to explore large VEs with fewer collisions, allow us to predict the navigability of a pair of environments without collecting any locomotion data, and deepen our understanding of how human perception functions during locomotion in VR.Item APPLIED AERIAL ROBOTICS FOR LONG RANGE AUTONOMY AND ADVANCED PERCEPTION(2024) Cui, Wei; Paley, Derek A; Aerospace Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)This dissertation addresses the challenges of conducting autonomous long-distance operations in settings where communication is restricted or unavailable. It involves the development of aerial autonomy software, ground station user interface, and simulation tools. Field experiments are conducted to assess the real-world performance and scalability of the developed autonomous multi-vehicle systems. A search and revisit framework involving multiple UAS engaged in expansive area exploration has been developed. By employing the ARL MAVericks autonomy stack, we have devised three system designs with improving levels of autonomy. This approach is effective in developing autonomous system capabilities for extended-range missions, enhancing effectiveness in reconnaissance, search, and rescue missions. Furthermore, the dissertation introduces an innovative application of enhanced target detection and localization techniques tailored specifically for small UAS deployment. Neural network fine-tuning and AprilTag detector selection are carefully conducted. Augmented by a meticulously designed workflow for performance evaluation and validation, our approach aims to improve the precision of target detection and localization using a single RGB camera module. Additionally, the dissertation presents the implementation of a specialized ground control user interface. Functioning as a centralized command center, the user interface facilitates real-time monitoring and coordination of heterogeneous aerial and ground robotic platforms engaged in collaborative search missions. By streamlining air-ground coordination and human-robot interaction, the custom user interface optimizes the collective capabilities of diverse aerial and ground robotic platforms, enhancing overall mission effectiveness. The experimental results from multi-vehicle autonomous search missions, evaluating centralized and decentralized control in beyond visual line of sight scenarios, are presented, proving the efficacy of the search and revisit framework operating in real-world scenarios. Finally, the dissertation covers the design and implementation of a resilient network link tailored for robotic platforms operating in environments with limited bandwidth. This essential infrastructure enhancement is devised to overcome communication constraints, ensuring reliable data exchange, and strengthening the resilience of autonomous systems in bandwidth-limited environments.Item Autonomous Robot Navigation in Challenging Real-World Indoor and Outdoor Environments(2024) Sathyamoorthy, Adarsh Jagan; Manocha, Dr. Dinesh; Electrical Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)The use of autonomous ground robots for various indoor and outdoor applications has burgeoned over the years. In indoor settings, their applications range from waiters in hotels, helpers in hospitals, cleaners in airports and malls, transporters of goods in warehouses, surveillance robots, etc. In unstructured outdoor settings, they have been used for exploration in off-road environments, search and rescue, package delivery, etc. To successfully accomplish these tasks, robots must overcome several challenges and navigate to their goal. In this dissertation, we present several novel algorithms for learning-based perception combined with model-based autonomous navigation in real-world indoor and outdoor environments. The presented algorithms address the problems of avoiding collisions in dense crowds (< 1 to 2 persons/sq.meter), reducing the occurrence of the freezing robot problem, navigating in a socially compliant manner without being obtrusive to humans, and avoiding transparent obstacles in indoor settings. In outdoor environments, they address challenges in estimating the traversabilityof off-road terrains and vegetation, and understanding explicit social rules (e.g. crossing streets using crosswalks). The presented algorithms are designed to operate in real-time using the limited computational capabilities on-board real wheeled and legged robots such as the Turtlebot 2, Clearpath Husky, and Boston Dynamics Spot. Furthermore, the algorithms have been evaluated in real-world environments with dense crowds, transparent obstacles, off-road terrains, and vegetation such as tall grass, bushes, trees, etc. They have demonstrated significant improvements in terms of several metrics such as increasing success rates by at least 50% (robot avoids collisions and reaches its goal), lowering freezing rates by at least 80% (robot does not halt/oscillate indefinitely), increasing pedestrian friendliness up to 100% higher, reducing vibrations experienced in off-road terrains by up to 22%, etc over the state-of-the-art algorithms in various test scenarios. The first part of this dissertation deals with socially-compliant navigation approaches for crowded indoor environments. The initial methods focus on collision avoidance, handling the freezing robot problem in crowds of varying densities by tracking individual pedestrians, and modeling regions the robot must avoid based on their future positions. Subsequent works expand on these models by considering pedestrian group behaviors. The next part of this dissertation focuses on outdoor navigation methods that estimate the traversability of various terrains, and complex vegetation (e.g. pliable obstacles such as tall grass) using perception inputs to navigate on safe, and stable terrains. The final part of the dissertation elaborates on methods designed for detecting and navigating complex obstacles in indoor and outdoor environments. It also explores a technique leveraging recent advancements in large vision language models for navigation in both settings. All proposed methods have been implemented and evaluated on real wheeled and legged robots.Item The Learning and Usage of Second Language Speech Sounds: A Computational and Neural Approach(2023) Thorburn, Craig Adam; Feldman, Naomi H; Linguistics; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Language learners need to map a continuous, multidimensional acoustic signal to discrete abstract speech categories. The complexity of this mapping poses a difficult learning problem, particularly for second language learners who struggle to acquire the speech sounds of a non-native language, and almost never reach native-like ability. A common example used to illustrate this phenomenon is the distinction between /r/ and /l/ (Goto, 1971). While these sounds are distinct in English and native English speakers easily distinguish the two sounds, native Japanese speakers find this difficult, as the sounds are not contrastive in their language. Even with much explicit training, Japanese speakers do not seem to be able to reach native-like ability (Logan, Lively, & Pisoni, 1991; Lively, Logan & Pisoni, 1993) In this dissertation, I closely explore the mechanisms and computations that underlie effective second-language speech sound learning. I study a case of particularly effective learning--- a video game paradigm where non-native speech sounds have functional significance (Lim & Holt, 2011). I discuss the relationship with a Dual Systems Model of auditory category learning and extend this model, bringing it together with the idea of perceptual space learning from infant phonetic learning. In doing this, I describe why different category types are better learned in different experimental paradigms and when different neural circuits are engaged. I propose a novel split where different learning systems are able to update different stages of the acoustic-phonetic mapping from speech to abstract categories. To do this I formalize the video game paradigm computationally and implement a deep reinforcement learning network to map between environmental input and actions. In addition, I study how these categories could be used during online processing through an MEG study where second-language learners of English listen to continuous naturalistic speech. I show that despite the challenges of speech sound learning, second language listeners are able to predict upcoming material integrating different levels of contextual information and show similar responses to native English speakers. I discuss the implications of these findings and how the could be integrated with literature on the nature of speech representation in a second language.Item Minimal Perception: Enabling Autonomy on Resource-Constrained Robots(2023) Singh, Chahat Deep; Aloimonos, Yiannis; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Mobile robots are widely used and crucial in diverse fields due to their autonomous task performance. They enhance efficiency, and safety, and enable novel applications like precision agriculture, environmental monitoring, disaster management, and inspection. Perception plays a vital role in their autonomous behavior for environmental understanding and interaction. Perception in robots refers to their ability to gather, process, and interpret environmental data, enabling autonomous interactions. It facilitates navigation, object identification, and real-time reactions. By integrating perception, robots achieve onboard autonomy, operating without constant human intervention, even in remote or hazardous areas. This enhances adaptability and scalability. This thesis explores the challenge of developing autonomous systems for smaller robots used in precise tasks like confined space inspections and robot pollination. These robots face limitations in real-time perception due to computing, power, and sensing constraints. To address this, we draw inspiration from small organisms such as insects and hummingbirds, known for their sophisticated perception, navigation, and survival abilities despite their minimalistic sensory and neural systems. This research aims to provide insights into designing compact, efficient, and minimal perception systems for tiny autonomous robots. Embracing this minimalism is paramount in unlocking the full potential of tiny robots and enhancing their perception systems. By streamlining and simplifying their design and functionality, these compact robots can maximize efficiency and overcome limitations imposed by size constraints. In this work, a Minimal Perception framework is proposed that enables onboard autonomy in resource-constrained robots at scales (as small as a credit card) that were not possible before. Minimal perception refers to a simplified, efficient, and selective approach from both hardware and software perspectives to gather and process sensory information. Adopting a task-centric perspective allows for further refinement of the minimalist perception framework for tiny robots. For instance, certain animals like jumping spiders, measuring just 1/2 inch in length, demonstrate minimal perception capabilities through sparse vision facilitated by multiple eyes, enabling them to efficiently perceive their surroundings and capture prey with remarkable agility. This thesis introduces a cutting-edge exploration of the minimal perception framework, pushing the boundaries of robot autonomy to new heights. The contributions of this work can be summarized as follows:1. Utilizing minimal quantities such as uncertainty in optical flow and its untapped potential to enable autonomous navigation, static and dynamic obstacle avoidance, and the ability to fly through unknown gaps. 2. By utilizing the principles of interactive perception, the framework proposes novel object segmentation in cluttered environments eliminating the reliance on neural network training for object recognition. 3. Introducing a generative simulator called WorldGen that has the power to generate countless cities and petabytes of high-quality annotated data, designed to minimize the demanding need for laborious 3D modeling and annotations, thus unlocking unprecedented possibilities for perception and autonomy tasks. 4. Proposed a method to predict metric dense depth maps in never-seen or out-of-domain environments by fusing information from a traditional RGB camera and a sparse 64-pixel depth sensor. 5. The autonomous capabilities of the tiny robots are demonstrated on both aerial and ground robots: (a) autonomous car with a size smaller than a credit card (70mm), and (b) bee drone with a length of 120mm, showcasing navigation abilities, depth perception in all four main directions, and effective avoidance of both static and dynamic obstacles. In conclusion, the integration of the minimal perception framework in tiny mobile robots heralds a new era of possibilities, signaling a paradigm shift in unlocking their perception and autonomy potential. This thesis would serve as a transformative milestone that will reshape the landscape of mobile robot autonomy, ushering in a future where tiny robots operate synergistically in swarms, revolutionizing fields such as exploration, disaster response, and distributed sensing.Item Larrons En Foire: Perceptions and Changing Strategies in Russia and Britain durring the Balkan Crises(2023) Trombley, Josiah D; Dolbilov, Mikhail; History; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)With a contemporary diplomatic crisis between Russia and the West heating up due to the Russo-Ukrainian War, this thesis looks at an often undervalued Nineteenth Century crisis that offers lessons for the ongoing political situation. This thesis argues that, instead of merely being a starting point for many polities in Southern Europe, the Balkan Crisis of 1876-1878 and the subsequent Treaty of Berlin are not only important for Balkan and Ottoman history, but also provides a crucial window into how a crisis could lead to changes in governing and national ideologies. Crucially, this thesis argues that despite the Russian government’s lack of representative bodies, and the British government’s own incredibly limited electorate, the perception of popular support at home for the Balkan peoples abroad altered the way in which leaders of both empires made diplomatic decisions throughout the Balkan Crises. Furthermore, this public sentiment, in this case support for Balkan nationalism and pan-nationalism, became part of an enduring legacy in the political spheres of both St. Petersburg and London.Item Active Vision Based Embodied-AI Design For Nano-UAV Autonomy(2021) Jagannatha Sanket, Nitin; Aloimonos, Yiannis; Computer Science; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)The human fascination to mimic ultra-efficient flying beings like birds and bees hasled to a rapid rise in aerial robots in the recent decade. These aerial robots now posses a market share of over 10 Billion US Dollars. The future for aerial robots or Unmanned Aerial Vehicles (UAVs) which are commonly called drones is very bright because of their utility in a myriad of applications. I envision drones delivering packages to our homes, finding survivors in collapsed buildings, pollinating flowers, inspecting bridges, performing surveillance of cities, in sports and even as pets. In particular, quadrotors have become the go to platform for aerial robotics due to simplicity in their mechanical design, their vertical takeoff and landing capabilities and agility characteristics. Our eternal pursuit to improve drone safety and improve power efficiency has givenrise to the research and development of smaller yet smarter drones. Furthermore, smaller drones are more agile and task-distributable as swarms. Embodied Artificial Intelligence (AI) has been a big fuel to push this area further. Classically, the approach to designing such nano-drones possesses a strict distinction between perception, planning and control and relies on a 3D map of the scene that are used to plan paths that are executed by a control algorithm. On the contrary, nature’s never-ending quest to improve the efficiency of flyingagents through genetic evolution led to birds developing amazing eyes and brains tailored for agile flight in complex environments as a software and hardware co-design solution. In contrast, smaller flying agents such as insects that are at the other end of the size and computation spectrum adapted an ingenious approach – to utilize movement to gather more information. Early pioneers of robotics remarked at this observation and coined the concept of “Active Perception” which proposed that one can move in an exploratory way to gather more information to compensate for lack of computation and sensing. Such a controlled movement imposes additional constraints on the data being perceived to make the perception problem simpler. Inspired by this concept, in this thesis, I present a novel approach for algorithmicdesign on nano aerial robots (flying robots the size of a hummingbird) based on active perception by tightly coupling and combining perception, planning and control into sensorimotor loops using only on-board sensing and computation. This is done by re-imagining each aerial robot as a series of hierarchical sensorimotor loops where the higher ones require the inner ones such that resources and computation can be efficiently re-used. Activeness is presented and utilized in four different forms to enable large-scale autonomy at tight Size, Weight, Area and Power (SWAP) constraints not heard of before. The four forms of activeness are: 1. By moving the agent itself, 2. By employing an active sensor, 3. By moving a part of the agent’s body, 4. By hallucinating active movements. Next, to make this work practically applicable I show how hardware and software co-design can be performed to optimize the form of active perception to be used. Finally, I present the world’s first prototype of a RoboBeeHive that shows how to integrate multiple competences centered around active vision in all it’s glory. Following is a list of contributions of this thesis: • The world’s first functional prototype of a RoboBeeHive that can artificially pollinateflowers. • The first method that allows a quadrotor to fly through gaps of unknown shape,location and size using a single monocular camera with only on-board sensing and computation. • The first method to dodge dynamic obstacles of unknown shape, size and locationon a quadrotor using a monocular event camera. Our series of shallow neural networks are trained in simulation and transfers to the real world without any finetuning or re-training. • The first method to detect unmarked drones by detecting propellers. Our neuralnetwork is trained in simulation and transfers to the real world without any finetuning or re-training. • A method to adaptively change the baseline of a stereo camera system for quadrotornavigation. • The first method to introduce the usage of saliency to select features in a directvisual odometry pipeline. • A comprehensive benchmark of software and hardware for embodied AI whichwould serve as a blueprint for researchers and practitioners alike.Item Perceptual Decision Impairments in Obsessive-Compulsive Disorder: State and Trait Symptom Effects and The Role of Working Memory(2020) Kaplan, Claire; Solway, Alec; Psychology; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Computational models of decision making have identified a relationship between obsessive-compulsive symptomatology and impairments in perceptual evidence accumulation. Past studies have suggested that these impairments in perceptual processing give rise to clusters of OCD symptoms (for example, not effectively “perceiving” that a door is locked or that one’s hands are clean gives rise to compulsive checking or washing). That interpretation has implications for our understanding of the disorder and warrants further testing; one way to investigate that is to determine whether such impairments correlate better with state-level symptoms (i.e., obsessions and compulsions during task performance) or trait-level symptoms (i.e., in general/past week). Using hierarchical drift-diffusion modeling, the current study examines this question in consideration of the alternate possibility that these decision impairments are simply a reflection of off-task processing of active obsessions and compulsions. We also examine whether working memory may mitigate such impairments, in light of prior studies that have associated larger working memory spans with better suppression of distractors and with faster perceptual evidence accumulation. 161 adults completed the random dot-motion task, OSPAN working memory task, and OCD symptom questionnaires online. Participants who reported greater obsessive-compulsive symptoms demonstrated slower evidence accumulation (“drift rate”) in the dot-motion task. These drift rate reductions were better explained by state-level symptom severity than trait-level severity. Working memory span showed a significant negative interaction with state-level symptom score on drift rate, however only for the easiest trials. While the current study does not negate a role of perceptual evidence accumulation deficits in the pathogenesis of OCD, these findings support the possibility that such deficits may also be brought about by active symptoms during task execution. We discuss using impairments in drift rate to approximate attentional bias for off-task symptoms, as this provides a novel computational framework in closer alignment with existing clinical models of OCD.Item IPADS IN THE SECOND LANGAUGE CLASSROOM: AN EXAMINATION OF IPAD USE BY TEACHERS THROUGH TPACK AND TEACHER PERCEPTION LENSES.(2017) Sharp, Steven Kary; Lavine, Roberta Z; Curriculum and Instruction; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)Research indicates a need for teacher education programs which include embedded computer assisted language learning (CALL) to support teachers’ technological pedagogical and content knowledge (TPACK) of how to employ technology in classroom settings. Researchers also indicate a need to better understand the knowledge-base of language teacher education (LTE), including a teacher’s possible 40 year career through ever changing technology. This mixed-method case study examines the use of iPads by four teachers, who represent maximum variation in their teaching and technology experience, in two mostly homogenous schools. The study looks specifically at how teachers’ perceptions of 1) teaching, 2) technology, 3) using technology and 4) their students shape the way they use iPads with English language learners. It also examines what supports facilitate the use of iPads for instructional purposes in second language classrooms. I focus on the use of iPads in a one-to-one implementation in a technologically embedded context because iPads are a relatively new innovation in classrooms, with the potential of changing instruction. Such changes may contribute to the challenges and benefits of being an effective teacher in the English language teaching (ELT) classroom. Research on the use of iPads in classrooms has been previously limited to mostly suggestions for use and has given little guidance in how this disruption will assist and challenge teachers. TPACK is used as a powerful construct based in a reconceptualization of the language teacher education (LTE) knowledge-base, indicating influences of context, teachers and their perceptions, identity and agency and activities in the classroom. These factors suggest ways which classroom technology and teacher, student, administrative and contextual influences may mediate the activities of teaching and learning in the classroom. The data show a correlation between teachers’ practices with iPads and their previous experiences using technology in the classroom. Teacher groupings demonstrated differences in teaching based on their experience using technology and teaching. Schools showed differences only in terms of some choices made by the administration. Students’ effects on the use of iPads is minimal, except for instances of how student behavior affected the classroom.Item Bioinspired Robust Underwater Behaviors Using Fluid Flow Sensing(2017) Ranganathan, Badri Narayanan; Humbert, Sean; Aerospace Engineering; Digital Repository at the University of Maryland; University of Maryland (College Park, Md.)The lateral line sense organ in fish detects fluid flow around its body, and is used to perform a wide variety of behaviors such as rheotaxis, wall-following, prey detection, and obstacle and predator avoidance. Currently there are no equivalent engineering analogues that can sense fluid flow perturbation to determine location of obstacles and demonstrate closed loop obstacle avoidance. In this dissertation we examine the potential and limitations of this sensor system with respect to obstacle detection, avoidance and rheotaxis. This dissertation presents the development of a novel bioinspired flow-based perception scheme for small and wide-field objects, design and development of a strain sensor system and a robust controller for closed loop demonstration of rheotaxis and small and wide field object detection and avoidance. Potential flow based models are developed for the above mentioned problems of interest. As the modeling technique is approximate, the uncertainties due to modeling and effect of rotation rate are accounted for and used in the synthesis of a robust H$_\infty$ control system. The perturbation signals are spatially decomposed using wide and small-field integration techniques to arrive at information regarding objects in the environment. A high-fidelity, computational fluid dynamic closed-loop simulation is carried out by interfacing control codes with an off-the-shelf software to demonstrate behaviors of rheotaxis, wall-following, tunnel centering and unstructured wide-field obstacle avoidance. A bio-inspired hair array sensor and its corresponding signal conditioning electronics were developed for detecting flow perturbations related to the behaviors of interest. The sensors that were manufactured were strain based and involved the use of micro and macro fabrication approaches. An instrumentation amplifier-based system was developed for signal conditioning. The hair array sensors along with the signal conditioning electronics weighed about 10 gms, which allows it to be easily carried on small scale fish robots. These sensors were integrated onto an airfoil-shaped robot and perturbation signals due to the motion of the robot near a wall and cylindrical objects were obtained and analyzed. The signals that have been measured by the sensor array help in quantifying the magnitude and structure of perturbation that is observed due to interaction with objects, and establishes requirements for sensor design for deployment on autonomous underwater vehicles. Closed loop behavior of rheotaxis was demonstrated in a flow tank.